diff --git a/01_materials/labs/lab_1.ipynb b/01_materials/labs/lab_1.ipynb index 25b751340..c7ca697e1 100644 --- a/01_materials/labs/lab_1.ipynb +++ b/01_materials/labs/lab_1.ipynb @@ -31,9 +31,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Matplotlib is building the font cache; this may take a moment.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "GPUs disabled, using CPU.\n" + ] + } + ], "source": [ "## Tensorflow GPU disabled by default. Comment the following lines to enable GPU if you have a working CUDA installation.\n", "import tensorflow as tf\n", @@ -54,7 +69,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -70,9 +85,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "(1797, 8, 8)" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "digits.images.shape" ] @@ -88,9 +114,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "(1797, 64)" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "digits.data.shape" ] @@ -106,9 +143,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "(1797,)" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "digits.target.shape" ] @@ -124,9 +172,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "# Selecting 9 random indices\n", "random_indices = np.random.choice(len(digits.images), 9, replace=False)\n", @@ -156,11 +215,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAeQAAAH3CAYAAABq7CzMAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjExLjIsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvgI3uAAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAN7JJREFUeJzt3Qd0VVW+x/ENREQQiQVRigTEgohGY0clWAY7QQfRsRDUEfU5A46VUZ/RsTAzlmDBrmHs2IKiMioaBhVFlCJ2QYqgqAMBQZpw3vrt9e5dyeWmwDkk/3Pz/ayVBbm52fck95/93/00CoIgcAAAoF41rt+XBwAAQkIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAAMafELWuSjPPfec+/TTTyP9xZaWlrpp06ZFWiYahldffdV9+OGHkZb5xhtvuIkTJ0ZaJhqGt99+240fPz7SMt955x331ltvRVpmJmgU15O6VGltscUWrlevXqHK+e2339xmm23mrr76anfjjTdGdn1bbrmlO++881xxcfFGl6G3Rkl97ty5btttt3UHHHCAv1bYU1ZW5pYtW+ZOOOGE0GW1b9/e5efnu8cff9xFZc8993RdunTxDcUwvvjiC/f111+7li1bugMPPND/DcKeDz74wM2bN8+dcsoprlGjRqHKOuigg1yzZs18jEflmGOOcT///LObPHlyqHK+/fZb99lnn/nr23///d1WW23l4izLxdT555/vK67333/fZSJVfP3793ffffed22+//XwluHLlSvfEE0+EboQgetdcc4375ptv3A8//JCRv97vv//enX766b4CVQWtz+fPn+/uv/9+H6ew5Y477nDPPPOMW7NmjcvKim01X6WlS5e6AQMGuNdee83H4y+//OI+//xz9/e//9396U9/cnGVee9UBlDiPfbYY32rT4m5devWbu3atT4ATzzxRN8i3Gmnner7MtGAqKc1c+ZMN336dNe5c2f/2NChQ90ZZ5zhOnXq5EdvgLpy7rnnurFjx/ppmH322cc/dvfdd/tkrLqxT58+sXwzMjoh6w3TMKKolbjDDju4fffd1zVt2rTK7/nqq6/8R05Ojh/mq8qsWbN8i0xDyBoq2XrrrWu8Hg0/q6d79NFHu1atWlU7HD979mz36KOP+mQsTZo0cf/4xz98D/n2228PNRSO+jFhwgS3cOHC5Pup91bx2Lx58yq/R9MVn3zyiWvTpo3Ly8urcvhxwYIFPlmuW7fOl6lYr4l69FOnTnWHHHKIa9u2bZXP+/jjj33Fd9111yWTsRQVFbl77rnH3XzzzaGHwlH3NNqhekYaN27sttlmG5/cqqubFL8fffSRy87O9lMWiuN0NBw9ZcoUt3r1al+PduzYscbrmT9/fjLB7rzzztVeg9b9KCknkrH8z//8jx8Z+Nvf/kZCtuiVV17xQ2vy66+/+oSonuZTTz2Vdtj3wgsvdJMmTfLzv5qDOeqoo/ywT4sWLZLPUXlnn322e++993wiVm9WFaEqpyuuuKLa61GCHT58uA/U3NzcaitK2W233So9rkpTc3dqaCCei2MUK7Jq1So/0qGKS8O+p5122nrPv+mmm9zTTz/ttt9+ex+PqthGjx7tk3PFobtBgwa5F1980SdiNTxV0eqx2267zVe0VRkzZoy75JJL/PcWFBRscDxuvvnmvuH6+uuv+4ZAda8FexRTiknR0LY6C5qT1bDvn//85/We//DDD7tbb73VTxUqxtToe/nll/3ahATFtWJKz9177719faVpRY2wPPDAA37UryoTJ050/fr1c3fddZe7+OKLq3yeRmrSxaMaq3pMw9j6u9puu+1c7AQx1a5du+DAAw/coO9Zs2ZNMGDAgGCHHXYIli9fnnxMv4add945ePjhh5PPnTRpUtC8efPg3HPPTT62evXqoHv37sGuu+4azJkzJ/n4Cy+84Mt49tlnk4+1aNEiGDx4cKXXf/TRR4NTTjkl+Pbbb6u9zvvuu8+X9/LLL1d6fOXKlUHjxo2DJk2aBOvWrdugnx2bVo8ePYI2bdps0PfoPbzmmmt8nM2bN69SbCser7322uRj33zzTbDjjjsGRxxxRKUyjjnmmGC77bYLPvnkk+Rj77//ftC0adPgn//8Z/Kxbt26BX369Kn0vWPGjPHxqFivztixY3083nXXXet9rW3btv5rFf8eUP/69+/v3xfVbxtixIgRvn6ZMmVK8jHVszvttFNw4YUXBmvXrvWP/fDDD0HXrl2DPfbYI/jtt9+Szz3vvPOCLbbYIpgwYULysS+++CLYZpttKtWHvXv3DvLy8iq99sSJE308vvbaa9Ve44wZM/zPduWVV673tQMOOMB/7d133w3iKOMT8tKlS4Px48f7pKmEed111/k3LFEJJRLyvvvuu973XnzxxUFWVlawaNEi//nTTz/tnzt69Oj1nturV6/g0EMPrTYh19bMmTP9H8Vpp51W6fGHHnrIv74+li1btlFlo34T8ooVK4L33nsvKC0t9fF49913+/dz1KhRlWJbjUY1ACu69dZb/XOnT5+eTLz6fPjw4eu9zsCBA4P27dtXm5BrS39DW221VXDwwQdXagiOGzcuGY+qJBG/hKyvqy5UnaZ4fPLJJ/333X777cnnqJ5t1qxZsh5MSNSHr776qv987ty5vsNw+eWXr/c6alyqDMV/VQm5ttQoUAOhc+fOwapVq5KPf/rpp77e1DWpERlHGT2HfP3117thw4b5+QvNSWiLxqJFi5JzbhVp+DmVFqpooYDm8A4//PDkPs7Fixf7ObP/b9Akh+80txIFzdNpXu7KK6/0Q4HaIvDll1+6++67zw8Rzpkzh+0mMaQhu8svv9yvN+jataufCtEQX7p41HBf6ha3xMIpTXl07949GY8qIzUetZ1PK/QVq7VZ31AdDTvee++9flHh7373Oz+8rqkbrWXYZZdd/FBndfPgsElTFRdccIGfB1Y8aapOw776SI1H1Z+pcVQxHrUIVUPgiamL1HjUKmhN7ylW9FphNG7c2A+Ja+HWYYcd5s455xxfvqZoFI9aCBvXeMzYhKx51sSik4suuij5uOYXNG+Suv063RuYeCxRaa5YscL/q3mTVKpclTijovloNQJGjRrl5+g0f6x5a60iVEXNfF28aL5YaxQuvfRSvzgvQQsDNZcbJh4Vz6oMU2neLqpjBv7whz/4RoL2Ro8bN87vi9fiwwcffNAn/g4dOkTyOqgbP/30k18hrxgZOXJksj5RYnv++edDxaPmjBPrDirSa1U3h7whtL5HhzmVlJT4Q0u0/1g/x7vvvutuuOEGt+uuu7o4ytiErJNgpLCwsNLjM2bMqHahQEWJoNK2Dkms/FPvtS7ecO2v00fC8uXL/aKzP/7xj5v8tREtNabUexg4cGDk8ThkyBDfc93UunXr5m655Zbk56q0lajVEM3Eva6ZTKN5SqBaoFqxcV9VPGqxV+rCvariUWWq17qp5eTk+E5XRVphrdHOigsf4yRjl0XuuOOO/l8N7yYsWbLED3Wko1NotJUpQcMrDz30kF9Wn1hFqBalhr2VkNPRyTjV0SpvLdfXddQksT0mdQheFZ96WYhnPCa2mYi2hGgEJx1tvUs0KkWV4YgRI/zKVg3TyfHHH+/L1apYfT3dlqnqqEJVPKYOT9Y2HjWMrd7x//7v/9b4/bAfj4ohbRtKt7VO20c1WleRpvPUS06cTqfOg3YCqAzVnxsaj/Pnz/fxmK4xmurHH39c7zHtQFAPWUk5rmLdrNV8sN7AVNojp1OF1Jrv27ev70GoNajhNvUuL7vssvW+56yzzvJzZCeddJKfS3nkkUf8sE7FIGzXrp3fBqVegZL3ySef7Pfu6f8axlZPQVtVwm57Eg27/Pe//3VHHHGEb5Uq2DRnqH91HbBHQ3fp4lH73hUbGvLVcaqaR9Zj2lOu+dh05wQrDhUDhx56qK88FYcaCtTcnNYrJKZJNA+ouTQ1HM8880yfsNUIffPNN/32lOqO36zttifR0KAarWoEaE5ZZ2MrFvUz1BTLqD8vvPBC2uktvd8aVdHUmOoZ1WOKXSVXfU8q7TnW49q3rtFBTVfoc9WTie1Feh0Nd2s+WaMp2iesqQwlWu3B19bTxDarMNueRNN4WpOh+l2vr0SsWL/zzjtd7969XVzFNiGrYlAgaZ9mKg2haI5BwaNWvN4sVWp6w9TD1BufSGoKIs1tqOLTwQfqhej7FKwKrtQTsXRSllpwqojU49WwnXrQSrZ77bVX8nkKlNSKSp/rtdRgqIl6Tqp8FXhqTOgwEc2R6A8H9mhfu5JhunhU4lSCVRwqHtUgUwyoJ6HKTQlZi1EqxrYqNA376fn6umJLh8Ho8dSKUr1p7a3X3tDESVo6l10xnaB4Tj0sRK+peKxNA08LDLWIR0lYDWEtzNGCSSV92KPeqhb2pfZqE5R41YnQKKBuZKKRP73HRx55pI/TinWZOgWJ8/61ZkANM9WnqkcVfxUpnjXs/eyzz/ppGq2d0KJa7WuuOK2iUR7toa+offv2Ph4r7muuihqf2nOsn08H1yiW9XdV8e8ojmJ7cwkAADJJxs4hAwAQJyRkAAAMICEDAGAACRkAAANIyAAAGEBCBgAgLvuQdYKLTvPRgQBV3SAdDZd2zukMXJ23XRdnbBOPIB6RifVjrRKykjGHx6MmOjq0Lg6KIB5RG8Qj4haPtUrI6hknCtRdNeqTTsgKq+IB+RurNudR12To0KGhy6h4J6v6ohN31GBLxMmmZikedfxkWFdddVXoMsLe0k4qns5UnzEdVkOORx1RaSEeozBs2LDQZSTOfY9LPNYqISeGqRVs9R1wOuItrCiGVaMYuo/iVmT1/X5UVFfTGZbiMYr7rkYRj6n3Tt4YiTOyw6jv96Ohx6OOaQ1L90e2oEUEP0t9vx8bGo8s6gIAwAASMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGBArW6/GJWpU6eGLmPIkCGhyyguLg5dRn5+fsaUkZub6xqisrKy0GUUFhaa+Lvo1KlT6DJGjx4duoyioqLQZWDj9erVK/Svb8CAARnz95kfQf1Yl+ghAwBgAAkZAAADSMgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMyKrLFysvLw9dRk5Ojombykfxs8yZM8fEdTRUUdwAPTc310RM9+zZM3QZ48ePD10G6lfHjh1NxHR2dnboMkpLS11DQw8ZAAADSMgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGBAVl2+WH5+vombZxcUFJi4qXwUZs+eXd+XEFuFhYWhyyguLg5dRqNGjZwFrVq1Cl1GWVmZiXqioSoqKgpdxpAhQ5wFS5YsMVE/1mVdTw8ZAAADSMgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGBAlouZKG4IH0UZUdz4umPHjqHLyM7ODl1GQxXFjcfLy8tDl1FWVha6jJKSktBljBw5MlY3c8f6CgsLTZQRhYKCgtBlTJ06NVYxTQ8ZAAADSMgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGBAlouZ7Ozs0GUUFRU5C6K4jihuTB/FjcCx8fLz8038+kaOHFnflwBE+ndRVlYWq/qRHjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAANIyAAAGEBCBgDAABIyAAAGkJABADCAhAwAgAEkZAAADCAhAwBgAAkZAAADSMgAABhAQgYAwICsunyx8vJyEzeLHjJkiInrmD17dugysPGmTp0a+tdXWFhoIpZKSkqcBTk5OfV9CbEVRf0YRUxHIYq6rbS0tMHFIz1kAAAMICEDAGAACRkAAANIyAAAGEBCBgDAABIyAAAGkJABADCAhAwAgAEkZAAADCAhAwBgAAkZAAADSMgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABWXX5YtnZ2SZu5l5UVBS6jL59+zoL3n777fq+hNjKzc0NXUZhYaGJeIziZykuLg5dBurX7NmzQ5dRWloauoyysrLQZeQ2wJimhwwAgAEkZAAADCAhAwBgAAkZAAADSMgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAHG5H3IQBP7fpUuXuvq2cuXK0GWsXbvWZYrly5eHLiPs+5r4/kScbGqZFo9R/N5+++230GX8+uuvocuw8J7ENR6j+N2tWLEidBlr1qzJmJheGsHvtHHjxnUWj42CWjzru+++cx06dAh1Uch88+bNc+3bt9/kr0M8ojaIR8QtHmuVkNetW+cWLFjgWrZs6Ro1ahTlNSIDKIR++eUX17Zt29CtydogHkE8IhPrx1olZAAAsGmxqAsAAANIyAAAGNDgE7JG7MeOHeu+/vrrSH+xb775pvviiy8iLRMNQ1lZmZs+fXqkZb777rtuypQpkZaJhuH99993kyZNirTMjz76yE2cODHSMjNBbOeQVWk1a9bMHXTQQaGX1m+22Wbu6quvdjfeeGNk17flllu68847zxUXF4cq55tvvnFz58512267rdtrr71YVGfUBx984LcN9erVK3RZWomZn5/vHn/8cReVPffc03Xp0sWVlpaGXimqmNQCz9zcXJeVVaudk6hj06ZNc99//73r3bt36DpDdazqWtW5UTnmmGPczz//7CZPnhyqnIULF/qOj65v77339v/GWWz/ms4880xfcan1lom+/fZbd8YZZ/iekgJt1qxZrnnz5r6SPvjgg+v78pDi0ksv9Ynqhx9+yMjfjSrPwsJCP/KjRKyfU3teH3roIXfiiSfW9+UhxS233OKeeeYZv6c4ExtNy5cvdxdccIEbNWqU6969u1/FrJhUB2jgwIEurhr8kLVFq1ev9i3IH3/80X355Zd+uHHOnDlun332cccee6zfggbUpX79+vkhxo8//tg3gtVgPO2009wpp5zCUDjq3AX/n4zffvtt38tWPfnXv/7VnXvuuX4KMq4yr+lUwYQJE5InWamVuMMOO7g99tij2r1gOnRCPZ2cnBz/UdNQiYa71WNQ77Umev7s2bNdjx49/JBfVV577TX31VdfuQcffNC1a9fOP9a0aVN3++23u44dO/p/b7311hpfD7ao4lBPU5o0aeJat27tunXr5mOoKmqUff75565NmzZu9913r/J5ixcvdp9++qnfo62pjezs7BqvR408lb3vvvu67bffvtrhTw1XalpHfz+iYVD1wh555BF30003ueeee67G14Mtn3zyiZs/f77/v+rEbbbZxk9tVDfsW15e7kftFF/qmVY1HL5s2TJfvjoXihnFek0WLlzoG3d6/k477VTl83766Sf3xBNPuLPPPtsdcsghyccvv/xyd99997mioiLfoYmjjE7Ijz76aLI3qfk9VVhKhE899VTaYd/LLrvMjRkzxrVo0cIHnVr/JSUllQJUFeof//hHnzQVvDo6UXO8w4YNcxdddFG116NgGT58uA86JfGqKBmLKuuKFKS6/ldffZWEHEPPP/98sje5atUq30DTMa5qePXp02e952v47Z577vEVpZKiKh8lPn2eoLgePHiw+9e//uV222033/BUuRpCv+GGG6qdP3zxxRfdJZdc4v8tKCjY4HhUI7RTp06+R6KlKBwaFC+vv/66e+ONN/z/NbStjogS7m233ebXv6RSvXnttdf65Kr6UfGmNQkVk6fW5Kinetddd/nYUH2l52oYWXVfdY3PCRMm+JEYfe/FF19c5fN0nYq31HhUo6Jr166+bl60aFGlv5PYCGKqXbt2wYEHHrhB37NixYqgf//+QYcOHfz/Zc2aNVrUFuy+++7BnXfemXzuf/7zn6BZs2bBRRddlHzst99+C/bbb7+gU6dOwZdffpl8/LHHHvNlvPTSS8nHWrRoEQwePLjS6993331B7969g5kzZ1Z7nSNGjPDlvfLKK5UeX716ddC4ceMgKysrWLdu3Qb97Ni0evToEbRp02aDvkfx9Je//CVo2bJlsGDBgkqxvdtuuwWXXXZZ8n3+9NNPg9atWwfHHXdcpTIKCgqCrbfeOpg0aVLysbfeesvHSMV47tatW9CnT59K3/viiy/6eHzvvfeqvc5XX33Vx+M999yz3tfat2/vvzZ37twN+tmxaame0/ui+q22FGu33nqrj51PPvkk+bjqWdV555xzTrI8vd9dunQJcnNzg7Vr1yafe/HFFwdNmzYNxo4dm3xs6tSpQatWrYIrrrgi+ZjiLi8vr9LrT5gwwT9esR5NZ/r06f5nGzp06HpfO+igg/zXaoppqzI+Ia9cuTL46KOPgtdffz147bXXgltuucW/YZMnT66UkPfaa6/1vveCCy7wwVVeXu4/f+655/xz9W+qww47LOjZs2e1Cbm2lOwbNWoUDBgwoNLjjz/+uH99fSxbtmyjykb9JmTFmyqUN99808fjI488sl5MKba33357H7sVDRs2zD/3s88+858rrvW5KtFUZ511VtCxY8dqE3JtLV682MdzxfiWd955JxmPM2bM2KiyUb8JWUlY8TRu3Dgfj6NHj/bfV1xcnHyO6tnNN988+Omnn9LWR6pbZf78+UGTJk2CIUOGrPc6Sp7NmzcPVq1aVWVC3pCGbNu2bX2jteLP9/XXX/vGhK6pYoMgTjJ6yFpDLxq207DJzjvv7LbYYgu3ZMmS5FxxXl5e8rnptk9pWFvDzBpyOeyww9w777zjH9c8nVab/n+Dxj/WqlUrP+QShV133dUPDenaNdeo+RAtWtC8sVaWa94n7sv7GyLNe/3lL3/xMaPhPk2NaI4tEY8VaUpj8803r/RYYppFc9EamkvEm9YXpMajHtMcsYYgazOfXB19v4Ybzz//fD+0ffrpp/stNTfffLNfZ6F1EfrbQrxoqkGLo1Qnat5WWzU17aCP1HhU/bnddttVGY9HH320X/SnKZitttpqvXhUnanpFU1/aKovjCZNmrj777/f/f73v/evq+F1rbLWmgbdBEkLDuMajxmbkN966y0/J/yPf/zDT/Yn/Pvf//YJLnX7tYIxVeKxxC3NEgvEHn744bSvqcVaUbn++ut9I0ArCTU/qIPJx40b54YOHeorWwUl4kMV0YABA9yFF17ok1tiYaEaWlqsFSYeNTedroGmPahR3MJOtHpVi8UUi2pYaF/8008/7T8ee+yxOrnLF6KjOVYlNO3a0PupOiURU4qzMPGoOlb78tPFY1RbsE444QS/HkN1sbZ3qRGgNRdaSHbddde5XXbZxcVRxiZkLYeX1IVWn332Wdrnq1WVSnt/RSubpXPnzv5fLbRRi3FTO+qoo/xHggJfga6KHfGi3qx6D+qRVFzlH0U8ajTlyCOPdJva/vvv7z8q0s+jXkqiQkc8fPjhhz6BqndZ8b2rKh41CpK6cK+qeFSjsy7qqK5du663uPXOO+/020N33HFHF0cZuw85scxeQ2sJGjLRitZ0NMRScZhGqw61pUPDKxpeFA3VaRixqi1H2qJSHa1+1TCRhldqom0sqbSSW38UWkGL+Mejeq9333132udrR4AqzQS97w888IAfNjz88MP9Y8cff7wvV1Mz6Q7cqykeNaSteKzpeVXFo3YxqFJWgwDxj0dRLzPdanlNfYwePbrSY5rOU32o3mpiCFt1pZKi6s9UNcXZwoULfTxq10pNdD3pVo2PHz/eb3uKq1j3kDX3kW4TuIYvdGiB9kdqWEZD1+pdanhDp19dc801633PH/7wB59w9a+GYpS4FRhK1AlqCWrITq0/VWYnn3yyX1qvSumll17yvQdVjmG3PcmVV17p512OOOII36PSH8Mrr7zinn322WSLFLZoPjhdPGqrh3qRGprWljnt51WvZOTIkX4YT9MrqU466SR31VVX+aSr1r6G5fQ8vf+J+TGtjdDnffv29VuitC9Te+0Vm4pbPU9fD7vtSdRw0FoKXY9eV9tlNFStk7pSe82wQ0kq3bkLGlHRlNgVV1zh9wyrHtP0mNbSKNZS6XHF64wZM/waF2291OcjRozwe+RF02iKNw2Dq5eqNQea09WaF40QqcOjQ47CbnuSF154wV+vtqaqkapyVb9qXYP+duIqtglZZwZrg3i6s6I1nKxhZZ0qpNaa5thUqd17772+ktIbnwgiBasqRVVoaumrPM33KaBU2Sj4Kjr11FOTwam5EvVMdEaweq8VN6mrAtaQSkX6XK+lBkNNFFxPPvmkr+DVmND13HHHHb7ChT2KCTXk0sWjHlcF+N577/kGmfZJaqGU4k3HoirRVjyERrGt+drEWej/+c9/fLzqhKz99tuvUtk9e/b089BqKOp52hevoUNVaIq1hEMPPdSvQ6hIr6nnJP4WqqNrffnll33DUPOP2gOqvdGKfdijBr96kar/0tFZ6apb1NBSr1L14jnnnOOTmerHiofQqOerRqXWtag8rRvQIlataVGHoSIdFqJhbx3xq3hXbKsDoXqzYqNPcbx06dJK37vDDjv4eKxNh0PXqjhX40FHZmrOWK+nv5s4i+3NJQAAyCQZO4cMAECckJABADCAhAwAgAEkZAAADCAhAwBgAAkZAIC47EPWARW6r7AOBOCep0ilnXM6fUz7XNMdQhA14hHVIR4R13isVUJWMtaJK0B15s2bVyc3GSAeURvEI+IWj7VKyOoZJwqszSlTDcGYMWNCl6G7rISlu5uElbit5MZS609nfifiZFOzFI86djKswYMHOwsGDhwYuozCwsLQZXTq1CnU9+sEKHUgGmI8RiGK28jqVohhvVvNMZu1ddxxx4Uu46mnnqqzeKxVQk4MUyvYMiHgotC8efPQZeg4urCiGCKO6j2tq+kMS/EYRRxYmQZKvf/yxogiCRKP9Uv36Q4rqtssWqhj6zIeWdQFAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAANIyAAAGEBCBgDAABv3yKpjUdyzderUqaHLKCgoCF1GWVlZ6DLKy8tD3w85jj766KPQZZx66qmhy5g8eXLoMvLy8kKX0blzZ2fBsGHD6vsSYis7Ozt0Gbm5uSbqpdLSUhPXUZfoIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAANIyAAAGEBCBgDAABIyAAAGkJABADCAhAwAgAEkZAAADMhyMVNQUBC6jJycnNBlFBcXm7gBdxQ3Ew/7+1i6dKmLo1mzZoUuY9999w1dRl5enomf5dtvvw1dBjZeWVlZ6F/fkiVLQpcxZMiQ0GWUlJSYuI6yCH6ndYkeMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAANIyAAAGEBCBgDAgKy6fLHS0tLQZYwePdpZMHz4cGfBo48+Wt+XEFt5eXmhy/j4449DlzFo0KDQZYwaNSp0GdnZ2aHLQP3+/lu1ahW6jL59+4Yuo2PHjqHLmD17doOLaXrIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAANIyAAAGEBCBgDAABIyAAAGkJABADCAhAwAgAEkZAAADCAhAwBgAAkZAAADsuryxQoKCkzcgHvJkiWhy9h7771DlzFt2rTQZeTm5oYuo6Hq3Llz6DIWLVoUuoxZs2aFLuP+++8PXUZeXp6JMhqqKP6Wy8rKQpdRXFwcuoyRI0eGLqO8vDx0GdnZ2S5O6CEDAGAACRkAAANIyAAAGEBCBgDAABIyAAAGkJABADCAhAwAgAEkZAAADCAhAwBgAAkZAAADSMgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABJGQAAAzIcjEzdepUEze+zsnJMVFGFDc1x8bbeuutQ//68vLyMuYtiOL3gfqtD0pKSkKXUVZWFrqMhogeMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAANIyAAAGEBCBgDAgCwXMzk5Oc6C0tJSEzcCx8Z74IEHQv/6Bg0aFLqMmTNnhi6jc+fOocuYNWtW6DLy8vJCl4H4i6KezjFS19clesgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAAOy6vsC4qq8vDx0GYWFhZFcCzZOv379Qv/qFi9eHLqMvLy80GV07tw5dBmnnnpq6DK23nrr0GWgfpWVlfEW1BN6yAAAGEBCBgDAABIyAAAGkJABADCAhAwAgAEkZAAADCAhAwBgAAkZAAADSMgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAEJf7IQdB4P9dunTppr6e2FixYkXoMjLl95n4ORJxsqlFFY9R/P5XrlwZuowofm9r164NXcbq1aszIqbjGo9WLF++PHQZv/32W+gylmbI73ND4rFRUItnfffdd65Dhw7RXB0y1rx581z79u03+esQj6gN4hFxi8daJeR169a5BQsWuJYtW7pGjRpFeY3IAAqhX375xbVt29Y1brzpZ0GIRxCPyMT6sVYJGQAAbFos6gIAwAASMgAABpCQnXPvv/++XygUpQ8//NDNmTMn0jLRMEyZMsXNnDkz0jKnT5/uvvrqq0jLRMPw6aefus8++yzSMr/44gs3Y8aMSMvMBLGdQ1al1bRpU9etW7fQy/M322wzd/XVV7sbb7wxsuvbcsst3XnnneeKi4tDlfPTTz/51Xnbbrut69ixY2TXh2ipwtIWqH333Td0WVqJmZ+f7x5//HEXlT333NN16dLFlZaWhiqnvLzcffvtt36Bp8qDTd988437+eef3UEHHRS6LJXRrFkzV1ZW5qJyzDHH+OubPHly6C1a33zzjb++XXbZpU4WlW5Ksb36E0880Z177rkuU33//ffuuOOOc+3atXNnnXWW6969u9tnn33ctGnT6vvSkMb555/v369Mpb2UZ555ptt+++3d6aef7g488EC38847u7fffru+Lw1pXHPNNe7ggw+OZD+wRatWrXJ/+tOffEfllFNOcT179vQN2eeff97FWWwTcibTIQ9qQWpIRz0vDRkpQe+www7uqKOO8r1moC4pCb/88svu3Xff9cONCxcu9L34448/3n3++ee8GahTf/7zn919993nRo8e7XvIP/zwgxs4cKDr37+/Gz9+fGzfjYxOyFOnTvXzw/rQ0Eht5ok1JKfv++9//1vt85YtW+Z7q0qYtT0lSXPKupZff/212ueNHTvWz/kNHTo0OSzYokULd/fdd/thnjvuuKNWrwdblLgS8ag1BrNnz67x9J5EnKlBVlOPQQ04xY3+XxuqxHQtixcvrvZ5ahC++uqr7oILLnD777+/fywrK8tPx+hcgr/97W+1ej3YonUKiXicNGmST2za418dTcsoxubOnVvt89QzV7wrdmt78teiRYv8taixV9PzHn74YXfqqae63r17Jx+/4YYb3I477uiuvfZaF1cZnZBvuukmN2TIEP9xzjnnuF133dXttddePuGmozlkDQ1rCKRNmza+Akod8tHQnVpi2223nX/e7373Ox8ETzzxRI3Xo0SqYaSaFtckFlDsvffelR7XEKHmpseMGVOLnx7W3Hvvvcl41BC3YrFz585u3LhxaZ//yCOPuD322MNXPBqOO/nkk32CTj3u8vLLL3fbbLONHzIvKCjww8q33XZbjdfz9NNP+3isqUdRVTxqHlnX/8orr9TZMZWIzpNPPpmMxwsvvNAdcMAB/vCKZ555Ju3zNUKy++67+16o3vdevXqtlzwVBzfffLOvH4888kgfu61bt3Z//etfa0z2b731lo/HZ599ttrnffnll74TlBqPTZo08Wsl3nnnHd+xytizrOMq9Y1dsmSJnwf7/e9/7ysZLQpLUKWiCk8LqEQ9AlVuSoC33nqrf0wBdcIJJ7hZs2a5iRMn+jldueeee/w8r5K4hpSrkpOT4+fe1NutzhZbbJH2LFc1DnSGtoYMET933nlnpc/1XqoyVKWl91QVV4J6IVtttZVfQKWKRj1q9QYKCwvdc889l3yeGpoatnvppZd8BSj6f9++fV12dna16yzUkFQ8KplvTDwmHtOHTvLTegfEh3qSFXuTql/UyxwwYICv29SBSdD7qwacer2Kh6+//trHm+rI9957L3mCo0b11BhUB0VxLZrmUOxuvvnm7rrrrqvyerbddlsfj5qaCxOPahQoaaus2Aliql27dsGBBx5Y4/PWrl0bzJw5M5g0aVIwceLEYPjw4WrKB1OmTPFfX7Nmjf+8a9euwbp16yp97znnnBM0a9Ys+OWXX/znL7/8sn/uk08+ud7r6FqOOuqo5OctWrQIBg8evFE/24wZM/zrDBo0qNLjzz//vH9cH8uWLduosrFp9OjRI2jTpk2tnjt37txg8uTJPh5HjRrl388XX3yxUmxvs802wfLlyyt93w033OCf+9VXX/nPp0+f7j+/+eab13uN/v37B126dEl+3q1bt6BPnz4b9bP9/PPP/u+gd+/elR7Xz5CIR8Us7ND7r/dF9VtNFixYEHz00Uc+Ht9++23/fXfddVelum2zzTbzz6vokUce8c/V98jChQv98y666KL1XuPSSy8NWrZsGaxevdp/rljKy8vbqJ9tzZo1QevWrYPu3btXqrPnzJkTbL755v6axo4dG8RRRveQNc+g1Yaas1XvVC2rxJCf5kByc3OTz+3Ro8d653QfdthhfthQ8yD6emLZ/9Zbb+3npNUSSwzVqXcQ1YpTbeVSz2n48OG+N60FXmrxqXWp4cgff/zRtzYRLxry0/uquVsN+em9XbNmjf9a6pyctk81b958vXgUzfdpi0diqFk9itR41JCh5gTVY1BPOwz1XG655RZ3ySWX+B66FnhpTlt/W3pt/TzadoJ40dDuRRdd5KfQEtNhiTowNR71dY2opIvHDz74wC/wU09Z8awbEaXGo2JQ5zmrZ61pmDCysrLcXXfd5c444wzXp08fN2jQIF92UVGRr5vjHI8Zm5A1TKJ9wKo09EZp2E/eeOMNP++bOp/RqlWr9cpIPJZYlJAYIlF56YQNtNT55kMPPdTP52gYSXM7WtI/bNgwP7ypoER8aOhZaw5UiWh1aKJBpQpKQ4Nh4lGVU8XplwQN2dV2gVdN1JDQ+oqSkhK/NkNJWq/773//2z366KN1cpcvREfTd5p+U0dDiVTJWNR5UUMxTDxq/3y6/e6Kx6jWGvT//3ns+++/3/3973/3Cf/KK6908+fP98PwakDEUcbW6qoo5IorrkgmY6lq/jXdqVqJxxKVzU477eT/VZKsi0M6VIHrI0GVq1qjibkZxIdGT9R7uPTSSyuNbkQRj2q8aR/mpqY5w8Q8dYIavOodMWITL6pHlJS1lzeRjEUjcemkW1VdVTxqHlkNz01t//33T676T1BnSx2juDYQM3aVtYYuEkvkK65IffDBB9M+//XXX6+0v1ctxJEjR/qhwa5duyZbZYnhknQ0bBLFtidJ9xwtClJSvuyyy2r8ftiMx4rb6dRbGDFiRNrna5ok9WhBTZ9ooVYi+WoPsD7f2His7banquJRiya1yEen3CH+8ShVxZKmyRKdnIrxqPowcSCOetuaGlRMp9sKWlM8Lqrltqeq4lGjotqxEOdtT7HuIWs+WG9gKg25qBepoV7Nd2nJvVa0ajX0SSed5D755JP1vkcrr/v16+fnI9Ri1LCiKpvXXnstOa+i5KzHtUVAqw61KlsrVLXqWitb1ULUXuGqqCejeWEd+1lx/jodtVz1R3PEEUf44+C0klYNhMcee8xfB+xRDzhdPKrSOvroo12nTp38Vjrt29UQs9Y4aKuJ9p2n0nCiDj/QrgDN3WmFq7a7/etf/0qu0ld8JFazap2BVsdqTlcNvzfffNNXgIqbqqhMzQu/+OKLfrVsdTRVonljNQK03UlTP2ogai/y4YcfvlG/L9RNT7jiCGHFNQr77befH+ZVw1D1mEb+1LNM9/xDDjnEJ+vEFIt2oWgbn+Ii0RvVEcQqQwla022qJzWfrGHkCRMm+EZmur+Pitue+vXr51/n4osvrvbn0t+BRp1Ub2u9hJLxP//5T78F8LTTTnNxFduErIBSq01zW6kUMHrDtPhFW5a0DF+VmhK05r5UWSW2eijZam5DFaOGWjQfoUUOaulpbiX1bGJtI9FeOVWmmr9QMOvwDlW0xx57bPJ5Kk9lbMy2J1GwP/DAA74BoMaEtiGox6R5E9ijhXjaNpIuHhMJTJWG4kvvrXq22rKkhTHqeVRcMKOY0x5lxZQWUymWtaVOcasGWkWq/HRwx0MPPeSfp4MbFCNK6KqsErRnM3UYr7bbnhLrJpT8NT+onox+Xv191NSwRP1Qo13vraZI0lEy06igkpga+lrwqng5++yz/WLBilNy2turBqSSr+LxhRde8PPH+lfb6ypSvactpYrHUaNG+U6TylKjTZ2RBI06pu4V3raW255EfxuJhqpGevTzauuqGgJxFtubSwAAkEkydg4ZAIA4ISEDAGAACRkAAANIyAAAGEBCBgDAABIyAABx2YesU6t0EIb2U6begAHQzjkdQqHztnWIyaZGPKI6xCPiGo+1SshKxjpxBaiO7iVdF2fIEo+oDeIRcYvHWiVk9YwTBYa9lVtYqae7bAwd6RbFrcvC0q3PwtLpYvVNd3lRgy0RJ5uapXjUkYBh6QSssNIdB1sf8VgXNxWoSUOOxyjqx6uuuspEPLZKc4ep+ohpnXpXV/FYq4ScGKZWsNV3wKXeFmxj6MzVsKIYuo/iDjn1/X5UVFfTGZbisTbHoNYk3a0TN1S684c3lI5PDKu+34+GHo9R1I9W4jErglvMpt5TfGNE9Z7WJh5Z1AUAgAEkZAAADCAhAwBgAAkZAAADSMgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMCA8Pe3qmMFBQWhy5g9e7aJ67j++utDl5Gbm2viZ4mjKO4d26tXr9BldOzYMXQZOTk5ocsYOHCgiXiMooyGKj8/31lQXFzsLCgqKopV/UgPGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAANIyAAAGEBCBgDAABIyAAAGkJABADCAhAwAgAEkZAAADCAhAwBgQJaLmfHjx4cu44477ghdRklJibMgOzu7vi8htqZOneoy5Sbqubm5ocvYZ599QpdRXl4euoyGKop4nDZtmon60crfRWFhoYsTesgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAAOyXMwMHjzYxI2vc3JyQpeB+pWfnx+6jJ49e4YuY+DAgS5TlJeX1/clxFZ2dnboMlq1ahW6jEsuucTEdZSUlIQuo6CgwMUJPWQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAANIyAAAGEBCBgDAABIyAAAGkJABADCAhAwAgAFZLmaKi4tNlBHFjdhzcnJCl4H6VVZWZqKMKPTq1St0GVOnTm1wN5WPShT1wezZs0OXUVRUFLqM4cOHhy6joAHGAT1kAAAMICEDAGAACRkAAANIyAAAGEBCBgDAABIyAAAGkJABADCAhAwAgAEkZAAADCAhAwBgAAkZAAADSMgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABWfV9AXGVnZ0duowlS5ZEci2It/z8fGdBq1atQpeRm5sbybWg/uqlIUOGhC6jpKQkdBkNET1kAAAMICEDAGAACRkAAANIyAAAGEBCBgDAABIyAAAGkJABADCAhAwAgAEkZAAADCAhAwBgAAkZAAADSMgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABWXX5YkVFRaHLuP7660OX0bFjx9BlFBQUhC4D8VdaWhq6jNmzZzsLlixZErqM7OzsSK4F9WfIkCGhyyguLo7kWhoaesgAABhAQgYAwAASMgAABpCQAQAwgIQMAIABJGQAAAwgIQMAYAAJGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAAOy6vLFioqKQpdRWFho4jpKSkpCl9GqVavQZeTk5IQuAxsvNzfXxA3hy8vLQ5cxePDg0GXk5+eHLgP1q6ysLHQZpaWlkVxLQ0MPGQAAA0jIAAAYQEIGAMAAEjIAAAaQkAEAMICEDACAASRkAAAMICEDAGAACRkAAANIyAAAGEBCBgDAABIyAAAGkJABADCAhAwAgAEkZAAA4nI/5CAI/L9Lly519e2XX34JXcbq1atDl5H4nWTC7yPs+5r4/rr6nWRaPK5bty50GVH87letWhW6DAvvSUOOxyhE8XvLlN9FXcdjo6AWz/ruu+9chw4dIrk4ZK558+a59u3bb/LXIR5RG8Qj4haPtUrIasEvWLDAtWzZ0jVq1CjKa0QGUAipp9i2bVvXuPGmnwUhHkE8IhPrx1olZAAAsGmxqAsAAANIyAAAGEBCBgDAABIyAAAGkJABADCAhAwAgAEkZAAAXP37P7a6DmiWsj6wAAAAAElFTkSuQmCC", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "# Selecting 9 random indices of images labelled as 9\n", "random_indices = np.random.choice(np.where(digits.target == 9)[0], 9, replace=False)\n", @@ -201,7 +271,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -227,11 +297,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "X_train shape: (1437, 64)\n", + "y_train shape: (1437,)\n", + "X_test shape: (360, 64)\n", + "y_test shape: (360,)\n" + ] + } + ], "source": [ "print(f'X_train shape: {X_train.shape}')\n", "print(f'y_train shape: {y_train.shape}')\n", @@ -265,9 +346,18 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Before one-hot encoding: 6\n", + "After one-hot encoding: [0. 0. 0. 0. 0. 0. 1. 0. 0. 0.]\n" + ] + } + ], "source": [ "from tensorflow.keras.utils import to_categorical\n", "\n", @@ -298,11 +388,93 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
Model: \"sequential\"\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1mModel: \"sequential\"\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ dense (Dense)                   │ (None, 64)             │         4,160 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_1 (Dense)                 │ (None, 64)             │         4,160 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_2 (Dense)                 │ (None, 10)             │           650 │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+       "
\n" + ], + "text/plain": [ + "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n", + "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", + "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n", + "│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m4,160\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m4,160\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense_2 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m650\u001b[0m │\n", + "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Total params: 8,970 (35.04 KB)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m8,970\u001b[0m (35.04 KB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Trainable params: 8,970 (35.04 KB)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m8,970\u001b[0m (35.04 KB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Non-trainable params: 0 (0.00 B)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "from tensorflow.keras.models import Sequential\n", "from tensorflow.keras.layers import Input, Dense\n", @@ -335,7 +507,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "metadata": { "collapsed": false }, @@ -365,11 +537,38 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/5\n", + "\u001b[1m36/36\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.5448 - loss: 1.6612 - val_accuracy: 0.7986 - val_loss: 0.6976\n", + "Epoch 2/5\n", + "\u001b[1m36/36\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 737us/step - accuracy: 0.8712 - loss: 0.4730 - val_accuracy: 0.8993 - val_loss: 0.4012\n", + "Epoch 3/5\n", + "\u001b[1m36/36\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 791us/step - accuracy: 0.9130 - loss: 0.3110 - val_accuracy: 0.9062 - val_loss: 0.3298\n", + "Epoch 4/5\n", + "\u001b[1m36/36\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 717us/step - accuracy: 0.9487 - loss: 0.2231 - val_accuracy: 0.9271 - val_loss: 0.2679\n", + "Epoch 5/5\n", + "\u001b[1m36/36\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 770us/step - accuracy: 0.9530 - loss: 0.1775 - val_accuracy: 0.9306 - val_loss: 0.2365\n" + ] + }, + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "model.fit(\n", " X_train, # Training data\n", @@ -393,11 +592,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 14, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 734us/step - accuracy: 0.9194 - loss: 0.2174\n", + "Loss: 0.22\n", + "Accuracy: 91.94%\n" + ] + } + ], "source": [ "loss, accuracy = model.evaluate(X_test, y_test)\n", "\n", @@ -416,11 +625,29 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m12/12\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 1ms/step \n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "# Get the predictions for the test data\n", "predictions = model.predict(X_test)\n", @@ -493,30 +720,88 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 40, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "train loss 0.818, train acc 75.50%\n", + "test loss 0.866, test acc 73.89%\n" + ] + } + ], "source": [ "# 1. Decreasing the learning rate\n", - "from tensorflow.keras.optimizers import SGD\n" + "from keras import optimizers\n", + "from tensorflow.keras.optimizers import SGD\n", + "\n", + "\n", + "def build_model(n_hidden_layers=2):\n", + " layers = [Input(shape=(64,))]\n", + " layers += [Dense(64, activation='relu') for _ in range(n_hidden_layers)]\n", + " layers += [Dense(10, activation='softmax')]\n", + " return Sequential(layers)\n", + "\n", + "def run(optimizer, n_hidden_layers=2, epochs=5, batch_size=32):\n", + " m = build_model(n_hidden_layers)\n", + " m.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])\n", + " m.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_split=0.2, verbose=0)\n", + " t_loss, t_acc = m.evaluate(X_train, y_train, verbose=0)\n", + " print(f'train loss {t_loss:.3f}, train acc {t_acc*100:.2f}%')\n", + " loss, acc = m.evaluate(X_test, y_test, verbose=0)\n", + " print(f'test loss {loss:.3f}, test acc {acc*100:.2f}%')\n", + "\n", + "\n", + "build_model()\n", + "\n", + "run(optimizers.SGD(learning_rate=0.001))\n", + "\n" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 41, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "train loss 1.491, train acc 41.82%\n", + "test loss 1.563, test acc 41.11%\n" + ] + } + ], "source": [ - "# 2. Increasing the learning rate\n" + "# 2. Increasing the learning rate\n", + "\n", + "build_model()\n", + "\n", + "run(optimizers.SGD(learning_rate=0.1))" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 42, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "train loss 0.158, train acc 94.50%\n", + "test loss 0.168, test acc 93.89%\n" + ] + } + ], "source": [ - "# 3. SGD with momentum\n" + "# 3. SGD with momentum\n", + "\n", + "build_model()\n", + "\n", + "run(optimizers.SGD(learning_rate=0.01, momentum=0.9))" ] }, { @@ -534,21 +819,48 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 43, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "train loss 0.116, train acc 97.15%\n", + "test loss 0.195, test acc 93.61%\n" + ] + } + ], "source": [ "# Adam optimizer\n", - "from tensorflow.keras.optimizers import Adam" + "from tensorflow.keras.optimizers import Adam\n", + "\n", + "build_model()\n", + "\n", + "run(optimizers.Adam())" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 46, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "train loss 0.138, train acc 96.45%\n", + "test loss 0.170, test acc 94.44%\n" + ] + } + ], "source": [ - "# Extra hidden layer\n" + "# Extra hidden layer\n", + "\n", + "\n", + "build_model(n_hidden_layers=3)\n", + "\n", + "run(optimizers.Adam())" ] }, { @@ -564,9 +876,35 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 47, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 47, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "predictions_tf = model(X_test)\n", "predictions_tf[:5]" @@ -574,9 +912,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 48, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "(tensorflow.python.framework.ops.EagerTensor, TensorShape([360, 10]))" + ] + }, + "execution_count": 48, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "type(predictions_tf), predictions_tf.shape" ] @@ -590,9 +939,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 49, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 49, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "import tensorflow as tf\n", "\n", @@ -617,9 +979,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 50, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 50, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "predicted_labels_tf = tf.argmax(predictions_tf, axis=1)\n", "predicted_labels_tf[:5]" @@ -636,11 +1009,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 51, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "# Get the values corresponding to the predicted labels for each sample\n", "predicted_values_tf = tf.reduce_max(predictions_tf, axis=1)\n", @@ -696,9 +1080,18 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 52, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/mchebotarov/Developer/MachineLearning/Deep Learning/deep_learning/deep-learning-env/lib/python3.11/site-packages/keras/src/layers/core/dense.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", + " super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n" + ] + } + ], "source": [ "from tensorflow.keras import initializers\n", "from tensorflow.keras import optimizers\n", @@ -723,9 +1116,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 53, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "[,\n", + " ,\n", + " ]" + ] + }, + "execution_count": 53, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "model.layers" ] @@ -739,18 +1145,67 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 54, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "[,\n", + " ]" + ] + }, + "execution_count": 54, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "model.layers[0].weights" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 55, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "array([[ 0.00015817, -0.01590087, 0.00103594, ..., 0.00962818,\n", + " 0.00624957, 0.00994726],\n", + " [ 0.0081879 , 0.00756818, -0.00668142, ..., 0.01084459,\n", + " -0.00317478, -0.00549116],\n", + " [-0.00086618, -0.00287623, 0.00391693, ..., 0.00064558,\n", + " -0.00420471, 0.00174566],\n", + " ...,\n", + " [-0.0029006 , -0.0091218 , 0.00804327, ..., -0.01407086,\n", + " 0.00952832, -0.01348555],\n", + " [ 0.00375078, 0.00967842, 0.00098119, ..., -0.00413454,\n", + " 0.01695471, 0.00025196],\n", + " [ 0.00459809, 0.01223094, -0.00213172, ..., 0.01246831,\n", + " -0.00714749, -0.00868595]], shape=(64, 64), dtype=float32)" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "w = model.layers[0].weights[0].numpy()\n", "w" @@ -758,18 +1213,43 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 56, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "np.float32(0.008835949)" + ] + }, + "execution_count": 56, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "w.std()" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 57, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n", + " 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n", + " 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n", + " 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], dtype=float32)" + ] + }, + "execution_count": 57, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "b = model.layers[0].weights[1].numpy()\n", "b" @@ -777,9 +1257,56 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 58, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 424us/step - accuracy: 0.2178 - loss: 2.2867\n", + "Epoch 2/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 430us/step - accuracy: 0.4746 - loss: 1.7419\n", + "Epoch 3/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 417us/step - accuracy: 0.7070 - loss: 1.0259\n", + "Epoch 4/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 458us/step - accuracy: 0.8615 - loss: 0.5442\n", + "Epoch 5/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 428us/step - accuracy: 0.9402 - loss: 0.2830\n", + "Epoch 6/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 400us/step - accuracy: 0.9624 - loss: 0.1895\n", + "Epoch 7/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 405us/step - accuracy: 0.9603 - loss: 0.1564\n", + "Epoch 8/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 399us/step - accuracy: 0.9645 - loss: 0.1341\n", + "Epoch 9/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 414us/step - accuracy: 0.9749 - loss: 0.1024\n", + "Epoch 10/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 400us/step - accuracy: 0.9798 - loss: 0.1003\n", + "Epoch 11/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 390us/step - accuracy: 0.9791 - loss: 0.0796\n", + "Epoch 12/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 413us/step - accuracy: 0.9889 - loss: 0.0594\n", + "Epoch 13/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 385us/step - accuracy: 0.9715 - loss: 0.0969\n", + "Epoch 14/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 375us/step - accuracy: 0.9910 - loss: 0.0448\n", + "Epoch 15/15\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 382us/step - accuracy: 0.9903 - loss: 0.0445\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "history = model.fit(X_train, y_train, epochs=15, batch_size=32)\n", "\n", @@ -797,9 +1324,48 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 59, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "[,\n", + " ]" + ] + }, + "execution_count": 59, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "model.layers[0].weights" ] @@ -825,20 +1391,231 @@ " to deal better with such bad initializations?" ] }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.2387 - loss: 2.0478 - val_accuracy: 0.3333 - val_loss: 1.7045\n", + "Epoch 2/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 809us/step - accuracy: 0.4475 - loss: 1.4938 - val_accuracy: 0.4556 - val_loss: 1.2610\n", + "Epoch 3/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 727us/step - accuracy: 0.6061 - loss: 1.1331 - val_accuracy: 0.7056 - val_loss: 0.9818\n", + "Epoch 4/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 709us/step - accuracy: 0.7717 - loss: 0.8720 - val_accuracy: 0.8000 - val_loss: 0.7735\n", + "Epoch 5/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 698us/step - accuracy: 0.8580 - loss: 0.6276 - val_accuracy: 0.9111 - val_loss: 0.5219\n", + "Epoch 1/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.2971 - loss: 2.0106 - val_accuracy: 0.3778 - val_loss: 1.6514\n", + "Epoch 2/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 807us/step - accuracy: 0.4969 - loss: 1.4775 - val_accuracy: 0.4889 - val_loss: 1.2811\n", + "Epoch 3/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 772us/step - accuracy: 0.6159 - loss: 1.1425 - val_accuracy: 0.5944 - val_loss: 1.0068\n", + "Epoch 4/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 762us/step - accuracy: 0.7077 - loss: 0.8725 - val_accuracy: 0.6861 - val_loss: 0.7960\n", + "Epoch 5/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 760us/step - accuracy: 0.7975 - loss: 0.6728 - val_accuracy: 0.8639 - val_loss: 0.6315\n", + "Epoch 1/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.1051 - loss: 2.3029 - val_accuracy: 0.0778 - val_loss: 2.3031\n", + "Epoch 2/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 830us/step - accuracy: 0.1072 - loss: 2.3026 - val_accuracy: 0.0778 - val_loss: 2.3036\n", + "Epoch 3/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 731us/step - accuracy: 0.1072 - loss: 2.3025 - val_accuracy: 0.0778 - val_loss: 2.3042\n", + "Epoch 4/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 705us/step - accuracy: 0.1072 - loss: 2.3024 - val_accuracy: 0.0778 - val_loss: 2.3045\n", + "Epoch 5/5\n", + "\u001b[1m45/45\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 745us/step - accuracy: 0.1072 - loss: 2.3023 - val_accuracy: 0.0778 - val_loss: 2.3049\n" + ] + }, + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 70, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Your code here\n", + "\n", + "#very small\n", + "input_dim = 64\n", + "hidden_dim = 64\n", + "output_dim = 10\n", + "\n", + "normal_init = initializers.TruncatedNormal(stddev=1e-3, seed=42)\n", + "\n", + "model = Sequential()\n", + "model.add(Dense(hidden_dim, input_dim=input_dim, activation=\"tanh\",\n", + " kernel_initializer=normal_init))\n", + "model.add(Dense(hidden_dim, activation=\"tanh\",\n", + " kernel_initializer=normal_init))\n", + "model.add(Dense(output_dim, activation=\"softmax\",\n", + " kernel_initializer=normal_init))\n", + "\n", + "model.compile(optimizer=optimizers.SGD(learning_rate=0.1),\n", + " loss='categorical_crossentropy', metrics=['accuracy'])\n", + "\n", + "\n", + "model.fit(\n", + " X_train, y_train,\n", + " epochs=5,\n", + " batch_size=32,\n", + " validation_data=(X_test, y_test)\n", + ")\n", + "\n", + "#larger scale\n", + "normal_init = initializers.TruncatedNormal(stddev=1e-3, seed=42)\n", + "\n", + "model = Sequential()\n", + "model.add(Dense(hidden_dim, input_dim=input_dim, activation=\"tanh\",\n", + " kernel_initializer=normal_init))\n", + "model.add(Dense(hidden_dim, activation=\"tanh\",\n", + " kernel_initializer=normal_init))\n", + "model.add(Dense(output_dim, activation=\"softmax\",\n", + " kernel_initializer=normal_init))\n", + "\n", + "model.compile(optimizer=optimizers.SGD(learning_rate=0.1),\n", + " loss='categorical_crossentropy', metrics=['accuracy'])\n", + "\n", + "\n", + "model.fit(\n", + " X_train, y_train,\n", + " epochs=5,\n", + " batch_size=32,\n", + " validation_data=(X_test, y_test)\n", + ")\n", + "\n", + "\n", + "#weights all zero\n", + "zero_init = initializers.Zeros()\n", + "\n", + "model = Sequential()\n", + "model.add(Dense(hidden_dim, input_dim=input_dim, activation=\"tanh\",\n", + " kernel_initializer=zero_init))\n", + "model.add(Dense(hidden_dim, activation=\"tanh\",\n", + " kernel_initializer=zero_init))\n", + "model.add(Dense(output_dim, activation=\"softmax\",\n", + " kernel_initializer=zero_init))\n", + "\n", + "model.compile(optimizer=optimizers.SGD(learning_rate=0.1),\n", + " loss='categorical_crossentropy', metrics=['accuracy'])\n", + "\n", + "\n", + "model.fit(\n", + " X_train, y_train,\n", + " epochs=5,\n", + " batch_size=32,\n", + " validation_data=(X_test, y_test)\n", + ")\n", + "\n", + "\n", + "#RUNNING WITH ADAM\n", + "\n", + "#very small\n", + "input_dim = 64\n", + "hidden_dim = 64\n", + "output_dim = 10\n", + "\n", + "normal_init = initializers.TruncatedNormal(stddev=1e-3, seed=42)\n", + "\n", + "model = Sequential()\n", + "model.add(Dense(hidden_dim, input_dim=input_dim, activation=\"tanh\",\n", + " kernel_initializer=normal_init))\n", + "model.add(Dense(hidden_dim, activation=\"tanh\",\n", + " kernel_initializer=normal_init))\n", + "model.add(Dense(output_dim, activation=\"softmax\",\n", + " kernel_initializer=normal_init))\n", + "\n", + "model.compile(optimizer=optimizers.Adam(),\n", + " loss='categorical_crossentropy', metrics=['accuracy'])\n", + "\n", + "\n", + "model.fit(\n", + " X_train, y_train,\n", + " epochs=5,\n", + " batch_size=32,\n", + " validation_data=(X_test, y_test)\n", + ")\n", + "\n", + "#larger scale\n", + "normal_init = initializers.TruncatedNormal(stddev=1e-3, seed=42)\n", + "\n", + "model = Sequential()\n", + "model.add(Dense(hidden_dim, input_dim=input_dim, activation=\"tanh\",\n", + " kernel_initializer=normal_init))\n", + "model.add(Dense(hidden_dim, activation=\"tanh\",\n", + " kernel_initializer=normal_init))\n", + "model.add(Dense(output_dim, activation=\"softmax\",\n", + " kernel_initializer=normal_init))\n", + "\n", + "model.compile(optimizer=optimizers.Adam(),\n", + " loss='categorical_crossentropy', metrics=['accuracy'])\n", + "\n", + "\n", + "model.fit(\n", + " X_train, y_train,\n", + " epochs=5,\n", + " batch_size=32,\n", + " validation_data=(X_test, y_test)\n", + ")\n", + "\n", + "\n", + "#weights all zero\n", + "zero_init = initializers.Zeros()\n", + "\n", + "model = Sequential()\n", + "model.add(Dense(hidden_dim, input_dim=input_dim, activation=\"tanh\",\n", + " kernel_initializer=zero_init))\n", + "model.add(Dense(hidden_dim, activation=\"tanh\",\n", + " kernel_initializer=zero_init))\n", + "model.add(Dense(output_dim, activation=\"softmax\",\n", + " kernel_initializer=zero_init))\n", + "\n", + "model.compile(optimizer=optimizers.Adam(),\n", + " loss='categorical_crossentropy', metrics=['accuracy'])\n", + "\n", + "\n", + "model.fit(\n", + " X_train, y_train,\n", + " epochs=5,\n", + " batch_size=32,\n", + " validation_data=(X_test, y_test)\n", + ")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": {}, + "outputs": [], + "source": [ + "# It seems in all cases the accuracy is around 10%. It may happen due to the network not learning \n", + "# anything meaningful due to poor initialization." + ] + }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ - "# Your code here" + "#Running with Adam optimizer it does help compared to SGD, but not for zero-initialized weights." ] } ], "metadata": { "file_extension": ".py", "kernelspec": { - "display_name": "deep-learning-env", + "display_name": "deep-learning-env (3.11.14)", "language": "python", "name": "python3" }, diff --git a/01_materials/labs/lab_2.ipynb b/01_materials/labs/lab_2.ipynb index a45b46e9e..4aa40bceb 100644 --- a/01_materials/labs/lab_2.ipynb +++ b/01_materials/labs/lab_2.ipynb @@ -22,7 +22,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ @@ -36,9 +36,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "sample_index = 45\n", "plt.figure(figsize=(3, 3))\n", @@ -58,7 +69,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, "outputs": [], "source": [ @@ -91,7 +102,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -101,18 +112,43 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "array([0., 0., 0., 1., 0., 0., 0., 0., 0., 0.])" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "one_hot(n_classes=10, y=3)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "array([[1., 0., 0., 0., 0., 0., 0., 0., 0., 0.],\n", + " [0., 0., 0., 0., 1., 0., 0., 0., 0., 0.],\n", + " [0., 0., 0., 0., 0., 0., 0., 0., 0., 1.],\n", + " [0., 1., 0., 0., 0., 0., 0., 0., 0., 0.]])" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "one_hot(n_classes=10, y=[0, 4, 9, 1])" ] @@ -143,7 +179,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": { "collapsed": false }, @@ -164,9 +200,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[9.99662391e-01 3.35349373e-04 2.25956630e-06]\n" + ] + } + ], "source": [ "print(softmax([10, 2, -3]))" ] @@ -181,9 +225,18 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[9.99662391e-01 3.35349373e-04 2.25956630e-06]\n", + " [2.47262316e-03 9.97527377e-01 1.38536042e-11]]\n" + ] + } + ], "source": [ "X = np.array([[10, 2, -3],\n", " [-1, 5, -20]])\n", @@ -199,18 +252,36 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "1.0\n" + ] + } + ], "source": [ "print(np.sum(softmax([10, 2, -3])))" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "softmax of 2 vectors:\n", + "[[9.99662391e-01 3.35349373e-04 2.25956630e-06]\n", + " [2.47262316e-03 9.97527377e-01 1.38536042e-11]]\n" + ] + } + ], "source": [ "print(\"softmax of 2 vectors:\")\n", "X = np.array([[10, 2, -3],\n", @@ -227,9 +298,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[1. 1.]\n" + ] + } + ], "source": [ "print(np.sum(softmax(X), axis=1))" ] @@ -251,9 +330,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 14, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.01005033585350145\n" + ] + } + ], "source": [ "def nll(Y_true, Y_pred):\n", " Y_true = np.asarray(Y_true)\n", @@ -279,9 +366,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "4.605170185988091\n" + ] + } + ], "source": [ "print(nll([1, 0, 0], [0.01, 0.01, .98]))" ] @@ -295,9 +390,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 16, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.010050335853503449\n" + ] + } + ], "source": [ "# Check that the average NLL of the following 3 almost perfect\n", "# predictions is close to 0\n", @@ -329,11 +432,28 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 18, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "ename": "NotImplementedError", + "evalue": "You need to correctly implement the LogisticRegression class.", + "output_type": "error", + "traceback": [ + "\u001b[31m---------------------------------------------------------------------------\u001b[39m", + "\u001b[31mNameError\u001b[39m Traceback (most recent call last)", + "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[18]\u001b[39m\u001b[32m, line 49\u001b[39m\n\u001b[32m 47\u001b[39m \u001b[38;5;28;01massert\u001b[39;00m(model.loss(np.zeros((\u001b[32m1\u001b[39m, \u001b[32m64\u001b[39m)), np.zeros(\u001b[32m1\u001b[39m)) > \u001b[32m0\u001b[39m)\n\u001b[32m 48\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m:\n\u001b[32m---> \u001b[39m\u001b[32m49\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m NotImplementedError(\u001b[33m\"You need to correctly implement the LogisticRegression class.\"\u001b[39m)\n", + "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[18]\u001b[39m\u001b[32m, line 29\u001b[39m, in \u001b[36mLogisticRegression.loss\u001b[39m\u001b[34m(self, X, y)\u001b[39m\n\u001b[32m 27\u001b[39m \u001b[38;5;66;03m# Compute the negative log likelihood over the data provided\u001b[39;00m\n\u001b[32m 28\u001b[39m y_onehot = one_hot(self.output_size, y.astype(int))\n\u001b[32m---> \u001b[39m\u001b[32m29\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m nll(y_onehot, self.forward(X)) / len(x)\n", + "\u001b[31mNameError\u001b[39m: name 'x' is not defined", + "\nDuring handling of the above exception, another exception occurred:\n", + "\u001b[31mNotImplementedError\u001b[39m Traceback (most recent call last)", + "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[18]\u001b[39m\u001b[32m, line 49\u001b[39m\n\u001b[32m 45\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m 46\u001b[39m \u001b[38;5;28;01massert\u001b[39;00m(model.forward(np.zeros((\u001b[32m1\u001b[39m, \u001b[32m64\u001b[39m))).shape == (\u001b[32m1\u001b[39m, \u001b[32m10\u001b[39m))\n\u001b[32m 47\u001b[39m \u001b[38;5;28;01massert\u001b[39;00m(model.loss(np.zeros((\u001b[32m1\u001b[39m, \u001b[32m64\u001b[39m)), np.zeros(\u001b[32m1\u001b[39m)) > \u001b[32m0\u001b[39m)\n\u001b[32m 48\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m:\n\u001b[32m---> \u001b[39m\u001b[32m49\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m NotImplementedError(\u001b[33m\"You need to correctly implement the LogisticRegression class.\"\u001b[39m)\n", + "\u001b[31mNotImplementedError\u001b[39m: You need to correctly implement the LogisticRegression class." + ] + } + ], "source": [ "class LogisticRegression:\n", "\n", @@ -350,8 +470,8 @@ " \n", " def forward(self, X):\n", " # Compute the linear combination of the input and weights\n", - " Z = None\n", - " return None\n", + " Z = np.dot(X, self.W) + self.b\n", + " return softmax(Z)\n", " \n", " def predict(self, X):\n", " # Return the most probable class for each sample in X\n", @@ -363,7 +483,7 @@ " def loss(self, X, y):\n", " # Compute the negative log likelihood over the data provided\n", " y_onehot = one_hot(self.output_size, y.astype(int))\n", - " return None\n", + " return nll(y_onehot, self.forward(X)) / len(x)\n", "\n", " def grad_loss(self, X, y_true, y_pred):\n", " # Compute the gradient of the loss with respect to W and b for a single sample (X, y_true)\n", @@ -388,7 +508,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 19, "metadata": { "collapsed": false }, @@ -411,11 +531,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "def plot_prediction(model, sample_idx=0, classes=range(10)):\n", " fig, (ax0, ax1) = plt.subplots(nrows=1, ncols=2, figsize=(10, 4))\n", @@ -449,11 +580,33 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Average NLL over the last 100 samples at step 100: 339\n", + "Average NLL over the last 100 samples at step 200: 115\n", + "Average NLL over the last 100 samples at step 300: 196\n", + "Average NLL over the last 100 samples at step 400: 83\n", + "Average NLL over the last 100 samples at step 500: 129\n", + "Average NLL over the last 100 samples at step 600: 65\n", + "Average NLL over the last 100 samples at step 700: 434\n", + "Average NLL over the last 100 samples at step 800: 136\n", + "Average NLL over the last 100 samples at step 900: 80\n", + "Average NLL over the last 100 samples at step 1000: 112\n", + "Average NLL over the last 100 samples at step 1100: 197\n", + "Average NLL over the last 100 samples at step 1200: 222\n", + "Average NLL over the last 100 samples at step 1300: 393\n", + "Average NLL over the last 100 samples at step 1400: 65\n", + "Average NLL over the last 100 samples at step 1500: 125\n" + ] + } + ], "source": [ "lr = LogisticRegression(input_size=X_train.shape[1], output_size=10)\n", "\n", @@ -489,11 +642,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 22, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "plot_prediction(lr, sample_idx=0)" ] @@ -525,18 +689,30 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 23, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "def sigmoid(X):\n", " # Clip X to prevent overflow or underflow\n", " X = np.clip(X, -500, 500) # This ensures that np.exp(X) doesn't overflow\n", - " return None\n", + " return 1 / (1 + np.exp(-X))\n", "\n", "\n", "def dsigmoid(X):\n", - " return None\n", + " s = sigmoid(X)\n", + " return s * (1 - s)\n", "\n", "\n", "x = np.linspace(-5, 5, 100)\n", @@ -556,7 +732,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 24, "metadata": {}, "outputs": [], "source": [ @@ -581,17 +757,17 @@ "\n", " def forward_hidden(self, X):\n", " # Compute the linear combination of the input and weights\n", - " self.Z_h = None\n", + " self.Z_h = np.dot(X, self.W_h) + self.b_h\n", "\n", " # Apply the sigmoid activation function\n", - " return None\n", + " return sigmoid(self.Z_h)\n", "\n", " def forward_output(self, H):\n", " # Compute the linear combination of the hidden layer activation and weights\n", - " self.Z_o = None\n", + " self.Z_o = np.dot(H, self.W_o) + self.b_o\n", "\n", " # Apply the sigmoid activation function\n", - " return None\n", + " return softmax(self.Z_o)\n", "\n", " def forward(self, X):\n", " # Compute the forward activations of the hidden and output layers\n", @@ -602,7 +778,8 @@ "\n", " def loss(self, X, y):\n", " y = y.astype(int)\n", - " return None\n", + " y_onehot = one_hot(self.output_size, y)\n", + " return nll(y_onehot, self.forward(X)) / len(X)\n", "\n", " def grad_loss(self, X, y_true):\n", " y_true = one_hot(self.output_size, y_true)\n", @@ -665,7 +842,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 25, "metadata": {}, "outputs": [], "source": [ @@ -675,27 +852,60 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 26, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "np.float64(2.3221346378453624)" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "model.loss(X_train, y_train)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 27, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "np.float64(0.1054354944335298)" + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "model.accuracy(X_train, y_train)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 28, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "plot_prediction(model, sample_idx=5)" ] @@ -711,9 +921,32 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 29, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Random init: train loss: 2.32213, train acc: 0.105, test acc: 0.089\n", + "Epoch #1, train loss: 1.80088, train acc: 0.365, test acc: 0.389\n", + "Epoch #2, train loss: 1.21834, train acc: 0.703, test acc: 0.696\n", + "Epoch #3, train loss: 0.83248, train acc: 0.868, test acc: 0.830\n", + "Epoch #4, train loss: 0.60525, train acc: 0.916, test acc: 0.893\n", + "Epoch #5, train loss: 0.46104, train acc: 0.941, test acc: 0.922\n", + "Epoch #6, train loss: 0.37028, train acc: 0.953, test acc: 0.937\n", + "Epoch #7, train loss: 0.31422, train acc: 0.955, test acc: 0.937\n", + "Epoch #8, train loss: 0.28180, train acc: 0.955, test acc: 0.933\n", + "Epoch #9, train loss: 0.26090, train acc: 0.954, test acc: 0.933\n", + "Epoch #10, train loss: 0.24119, train acc: 0.957, test acc: 0.937\n", + "Epoch #11, train loss: 0.22129, train acc: 0.959, test acc: 0.937\n", + "Epoch #12, train loss: 0.20288, train acc: 0.962, test acc: 0.944\n", + "Epoch #13, train loss: 0.18736, train acc: 0.963, test acc: 0.944\n", + "Epoch #14, train loss: 0.17431, train acc: 0.967, test acc: 0.944\n", + "Epoch #15, train loss: 0.16315, train acc: 0.969, test acc: 0.944\n" + ] + } + ], "source": [ "losses, accuracies, accuracies_test = [], [], []\n", "losses.append(model.loss(X_train, y_train))\n", @@ -736,9 +969,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 30, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "plt.plot(losses)\n", "plt.title(\"Training loss\");" @@ -746,9 +990,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 31, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "plt.plot(accuracies, label='train')\n", "plt.plot(accuracies_test, label='test')\n", @@ -759,9 +1014,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAxcAAAGICAYAAAAzjx2DAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjExLjIsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvgI3uAAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAS+hJREFUeJzt3Qd4FFX7+P0bCISeIL2ELk2UIlWkKCCgFBV4KAoPoqJiARTFKFXAoI8oWBAQUEQUEUUQAQFRAVGKFBFEigKRXhNqaPNe9/n9Z99Nsptkk8lms/l+rmsIOzvl7MzuzNxzzrknm2VZlgAAAABAGmVP6wIAAAAAgOACAAAAgGOouQAAAADgCIILAAAAAI4guAAAAADgCIILAAAAAI4guAAAAADgCIILAAAAAI4guECatGjRQiIjI4N+K6blc956660yZsyYgCkPAAS6atWqyZtvvplhy2zQoEGi43ZKx/m6XH/Q5yXfc8898u6770qg2blzp9k3ixcvdo378ccfzbitW7c6tp70WKY/fffdd+Z6IiYmRgIdwUUAOnHihPkBpGSYN29ehpZ1z549cvjwYQl2afmcf/31lxw5ciRgymOfaH799VcZNGiQ3HLLLea7dO3aNUfLCASb6Ohoeemll+SOO+4wvxsN8vX1gQMH0rTcYcOGSePGjR0rZ6Cu09fj5rFjxzJsmbt27Up03E7puFq1aklUVFSKl+sPM2fOlNWrV0uPHj0k0Fy6dMnsm9jYWNe4c+fOmXEXL170aVnLli0z57Pt27cnei+1y0xvZ8+eldmzZ0vHjh1N2fW36UmrVq3k/PnzGRKc+iokowuAxAoVKiRff/11vHFPPPGEOTD88ccf8caXLFkyQzfhTz/9JHnz5s3QMsB3Tz31lGzatEn+85//SIkSJWT58uUm4ADg2eeffy59+vSRpk2bmqC8fPnyJqjQO8FVq1aVjz76SLp165aqzac3Cnbv3u3XTZ8R68xMNmzYIAULFkzVdHoBe/To0TQt10l6bB89erT07t1bChcuLJmBBvB//vmn+Z35QgMUbwFEapeZni5fviyVKlWSu+66yxw/HnzwQa83DnPkyCHPPPOMPPfcc/Liiy8G9L4kuAhA+gXS6NVdvnz5zN+E4zOa/iiQ+bzxxhuSJ08e8/9169ZldHGAgKa1fHrS12D8k08+kWzZspnxWnuhTU0eeOAB8365cuWkUaNGGV1cOODGG290dLrUTu9Uc5q///7bBBeZhV7zOH29kx7LTKucOXOamxS5c+eWM2fOJDu9BiADBw6UDz/8UAYPHiyBimZRmZjdlv+ff/6Rvn37Sp06dWTy5Mmmik1/QB988EGiebp06WKm9XTy1ANP3bp1pV69evL000+bJgCpaftvl2vv3r3Sq1cvs0w98dpNB/Ruma5Ly3vvvfd6rL7UctpNv2rWrCl33nmnvPrqq3LhwoVEd2SmTJliyqHrHTBggPmBdu/e3eOBNLWf05OUltG9KZNuh9q1a0v79u1N9a0nqS2j3kHVsqxfvz7Zae3AAkDyXn75ZQkJCZF33nnHFVjY9LWO1/eHDh3qGq+/YT0OJaTHaP2d2scJPR5r81Y9brk3ebUvNF544QVzfNOmI1oObbN/++23m74DV69ejbdsp9bpiS/lsKeNi4uTV155xTS/0uOlbc6cOdKhQwcTnDVv3lzGjh1rmqx4smPHDvOZ9LjZqVMnU1ue0N133x3vWKzNR/QGiq4/tctMad8I9+nsJs16N/rjjz92lenRRx9NdrmrVq0yQaqeF3UarR1L2HxKj+26jxs2bGi2vdZA6/k/OV9++aXccMMNZrne+qGkZJvY02rNgJZDm3/p51T6md977z1p06aN2a+6D/R7d/369XjL0M/05JNPmvOb1iR89tlnPvWP0PW8//77Zp/r+rUpkb0MveDWa4CE5+dvvvkmyWXq937EiBFmm+oy9bpkwYIF8abRZei8ev3y1VdfScuWLc2+6t+/v9nvCTVt2tSUMTl6/NDAIqW0tkKvdXSfBjQLmcI999xj5ciRI964fPnyWf/5z3+sFi1aWF999ZW1bNky66OPPrJOnz6t7VusqKioRMu59dZbrZYtW8Yb98EHH5hl9+vXz/rxxx+tlStXWu3atbOKFStm/f3330mWq3Tp0tZ///vfROXq1q2b1bZtW+vbb7+1Vq1aZTVo0MCqUqWKtWfPHrP+b775xoxv3LixVaJECevChQvxlrFv3z7rzz//NMOmTZusDz/80IqIiLDuvvvueNMNGDDACgkJscaOHWutW7fOmjlzptW+fXurXr16VvPmzdP1c6a0jO77acGCBdaaNWushx56yMqWLZs1Z86cVJXRU3lGjBhh9vsPP/xg+UL3lc535coVn+YDsoKYmBjzm9TfYVL0eKfT6fRKjz8NGzZMNN3o0aPN7+3s2bPm9YEDB6wuXbpY4eHhruOJDlevXjXvP/DAA+b3rn/feecdc5ybOHGilTt3bqtnz57xlu3UOj3xpRz2tA8++KCZZu3atdYrr7ziOmbrdho+fLj166+/WrNmzbKKFy9u1apVyzp37pxrGVpeXc4dd9xhLVq0yJwvevToYebV84c7PTban+G3334zx1E9r+hx150vywwLC7OefPJJn8bp9tMy5MqVy+rdu7erTNHR0UkuY8KECaYMTz/9tLV69WprxYoVpoy6DQ8ePGim0c+ly3388cfN9tTt//7771s1a9a0kqPn3rvuusvje75sE51W96lOu3DhQmvJkiXWp59+al28eNFq2rSpOU9NnTrV2rBhgzkfFilSxExvO378uFWuXDnrxhtvtObPn2/OhXque+qpp8yyP/vsM9e0um4d98svv7jG6XVCkyZNzPdWv1e6DXQ6Lf/HH39snTx50ozX+ebNm+fa/vZv0tMydR7dPnru1vOxvvfCCy+Y8/PIkSNd0+n3VOfV97S8P//8s1mHfnf13J5Q8eLFrapVq1q+sK/dHn744SSnGzhwoLnucf+9BBqCi0weXISGhlr//vuva9z169d9Ci50Xj1gPfLII/Gmu3z5slWpUiVz4Zma4CJ//vzWsWPHXOP0wKhlqly5snX48GHX+K1bt5rxeiBKztKlS820W7ZsMa937NhhXutJyt13331nDgzuwUV6fM6UlNHeHnoCdt9PqnXr1lbRokWtS5cu+VxGT+XRA7ceSM+fP2/5guAC8E5/y/qb1gu/pNgXSHpM8+VCX+nFROHChT0uVy+c9Hg2bdq0eOPfffddsxy9AWFzap1pLYc9rV5oup+b7PNAZGRkvGXoBZ2O1xskNn1doEAB68SJE/Gm1RtSeiGYVCCk9MJPl6E3tFKzzNQEFzY9L2sQ5UnC6Xfv3m3O7XrB6E4vpPU4b19o6rbR5ep2THh+SIpOrxei3i5YfdkmOq2e2/Vc4758DRyzZ89urV+/Pt4y9Oai+w0v+6L4n3/+iTddx44dUxRc6Llex2lwlZC9Hb744gszjQY4CXla5qBBg8x3ddu2bfGm1X2kn+mvv/6KF1y4B0tKA1kdv3nz5njjd+/enexNy9QGF2+++aaZ7o8//rACFc2iMrlmzZpJ6dKlXa8TVtknRzuOazXjww8/nKgdoLYlXrJkSarKpVXiRYsWdb3Wqsbs2bNL5cqVTQdi280332yaE2gqOnfHjx83GRO02lSrubU6Uju1K3taO21dz549482rHaMSdnRKj8+ZkjLatOrffT8pbTKmy7CbMaW1jEWKFDFloIM94Bz9Tdq/w6TY79vTOy3hcc5u9rlo0aJ0WV9ay6HXou7T6rnp22+/Nf/XjvHutJ+KHrsSLsPTsVyPm9pM9Pfff3eN0w6w2sFVj7M33XSTWZZ2evV0LE7pMv1Fm7dopr6Ex31tuqpNjOzjfpkyZUwzr1GjRsXLeJXc91KbSWuztfDwcK/T+LJNWrdubc417vt17ty55lxev379eNO2bdvWNPmxP4Pu/yZNmiTqUK3NhVPiiy++ME2RPGU5S247eKNl0ubHeg5399BDD5kmXe7pcVXCpA12UzNtKuaucuXKUqFCBUkP9r48efKkBCo6dGdyZcuWTdP8+/fvdx3s9SL//9VmmXHajlAzL2jWBV/b6OuBMGEn9QIFCiQarwemsLCweD8SzeGsByntfKUX71WqVDEXzJrCT9uC2lkg7PaoCZepEl7IO/05U1pGW0RERKJl2OPszBDptS8ApF6pUqXM30OHDiU5nf1+emTw0wu/hL97PZ7qsdOfqcB9KYdOayciSbiNPJ23tDN8wgvZ5I6beqGpN2i0DXrx4sVNWmC9qNMybtmyxaRd9fVYrMv0J/u4r8kC9Aac+3Ffg4jTp0+7zgu6ff73v/+Zfiw1atQw/Rq0T15SiVV0H+h5VlOYeuPLNvG07+zPYF+g259BBw1s7HO1Lkv7i6Rk/Z78+++/Jrhxkn4nNTDy9H2030+qrNqXRXnqd5Fe7H2pv71ARXCRyXnqCKQXuXow8ZSKTQ9W7ncw7C/npEmTXCfRlKwjORpM+DLePQ2q3snRg9Vvv/1mOn3ZEnZcy58/v/mrB9+EJzEdl56fM6VltJ06dcrrOLts6bUvAKSe3qjQizft4Kp3mD0dw3S8dsjVC1v7xoYek+wLQ3epeXaD3szQu6h68Wm7cuWKuSvtfoHh5DrTUg5vxyp7Gi1jwiBMbzAlXEZKjpvamVcvWrWzrt7ksW3bts3jZ0jJMv3JXueMGTOSrF3QG05vv/22vP766ybph37fpk+fLlOnTjVpxb1lQdLvqwZeSX0HfNkm3var/ka0LJ5o8Gmfs5NaV3I0ha/TF/Fadk+/GfuGZ8LPn5JrmPRm78uEN1EDCc2iglCuXLlM0yPNTuROXx88eDDeOM1wpDSzk7cH9fna1Cqt9ESlEp585s+fH++1XTWaMKuFptzTOxzp+TlTWkbbL7/8kqi5xA8//GCqcu2q5EDcFwDEpHzUC1hvF0+asU7fd08NqXc+9QaEXny7X4DoRWFCesGWMOOSO13Gzz//HG+cLkcv9G+77bZ0WWdayuGNPc33338fb7w+E0Kf4aRNZtzps50SPtxTj5taM6FZjVJzLE7JMtPKl21rH/f1xpS3437CZWuz4+HDh5uMRnoTUVPNJkXPlZs3b/b6flq3iX4Gzfqo+8BT+e19o/tfmwEnvPGp60oJXY/e0EvqIYR28JPS7a9l2rhxY6KnXq9YscL8TfidDAQbN240NzKKFSsmgYrgIkhpdbC24bcPKBrpaprEihUrxptOfzjahlBTB7qnXtMLYW2LqKlV/U1TuOlFtKa805OWnhw13V3CBz5plbBemOvn0gfjKL0DoalxE1YTO/05U1pGmzbd0tSCdoChbYunTZsm/fr1c7VfTWsZfUlFCyDlHnvsMdN/QNNcarpNO8WpnRZT887r+/p7dj8G6wWLHiOUXrxpE0pPD1DT45U2e/RW86n91yZMmOC6aaJpvbUseoGhzWnSY51pKYc3moJbm9ho8yW7CZSWV9u36/H0+eefjze9XjwNGTLEdaGo6XP1Scb6IDH7jrL2s1Djx483x2E9Hmuwl/BGmi/LTCvdtlpzkjANqyfar0K3i25H9351+h3Tc7im1FW63bXPgaYCVvpZ7Rtr1atXT3Id2vdB93PCm25ObZORI0eav3r+sptI2dcdet5au3atea3nNj1Hawpd+zekgVFSgY87Dai0BkdT5tqp7fU7ruW1t5197tdmcSmh1wsa7Gi6YLu5kT77SZueaZ9W7VOZGk1TmIrWVxrga81Vu3btJKBldI9ypC1bVMIsFe5ZBzT1nGZBKFWqlFW9enWTzcBTKlpNQarZRDR1X968ea2yZcuav5rBwT2rgi/ZojyVS7NkPPbYY4nGa8aShNkRJk2aZDJY3HDDDWbQVIcbN25MlFnqyJEjVps2bVyfU7MqaXo7/ZytWrVK18+Z0jLa20OzrOi6NUOUZoV64oknEmX6SGkZ05qKVjNqaJo8HfQz6Hz26169eiU7P5DVaFYcTf1ZrVo185usWLGi+W3rb0bHJ8zi457hR1Ny6m968uTJHjM3aarM+vXrm6xymlFPl6nHcPe0rprNpkaNGuY4p8c7Tcm5d+/edFmnJ76Uw57WE80i2LVrVytnzpxWyZIlTfagunXrJsoApOUdMmSISXuraT31PKGfS7P7JMwUNX78eLMvdBo9Fvft29ekdNVl6LEuNctMS7YozRqo5dDl63Z1zwDoafq4uDhr6NCh5tygn0OzNOnfzp07mwxbdtay7t27m/F6XihUqJBVvnx5a8qUKVZyYmNjzXH+tddeS/SeL9vEntaTXbt2WR06dDDnNl2Ofv90/+rncv9eaQpa/W7oOjR1rX5GPWenJFuU0gxJeg2j10O6fP1cmvHQTtmrdPvq90q3j25/TZub1DI19a+m9NXvpP5mtGx6Hjxz5oxrGjtbVMKsUppmWMfr9kttKtrOnTubaTVFry5LvyP2+VgzbrnTdPaeyhFosuk/GR3gIHl6x0Gj6qpVq7rGaedhbcuo7Sm90faJeqdD2+bpnSG9q6DtZb11oNKqfb17odO7t6v1RpvwaB8P9yppb+XSu/p6By3heG2upW0x3bNI2Xck9O5ToUKFzN0TvUuoTZ50XXYbTvc2m7p97HLrNFp17O0BPU58zpSW0X176Ps6vd4pSthPxJcyeiqP7msdtMNdchmj9G6ht46gOm9aEwUAwUzvvuoxRztz6m8/KfrgOm32o/2oQkNDTVtu7YSsx/KEzRx1vC5b73jrk5y1fbdm0tH+BHoO0NO1djDV5pRJNYlI6zo98aUcemzRMiTV0Vjf1+YtemxMmKnIzvKk47W2RO9y6/r0GOrt2KbHSj226jx6PtHz3r59+8zx07777ssyPZ2vUjrOPjfottJy6LHeTjzibXql21W3ne4L+5ydkL6ny9XPlNx3z53WGmhTMd0G7vtY16G1FuPGjUt2m7hvP2/08+pn0LJ560Oin0EzUel20Ol0vVqz4r6v9Hyu02hmKU/9PLQ5nJ7vdLt6yhSl89vnUP0d6LqSW6b+FnS5On3C97WWT7eNtv7Qpuc2Xb5ew+j1i/vn3bNnj9nOKckYpddlnvrIKvdtorSWS79bqc3k6S8EFwg62nZXnxD61ltvuZ7WCQCZkftFPeVAaukNJW2+ph3CtRmap+ACgW39+vWm+bQ2+dKUy4GMbFHI1L755htzh6Fly5bm7r7eqdJ84XpnRfN0AwCQ1WkN0datW/2a1QjO0loTrflK+JyQQESHbmRqmldbOy9q1apWZeqPT6tINdODnX8aAICsTs+RgZy+FEnT5C+ZIbBQNItCULD7MmhAkbA/BgBkVinpv5CVygFnpaQfBeArggsAAAAAjqBZFAAAAIDM2aFbU5BpOi9NrcXThgFkZto50k5dmJKUxkgbzh8AEPjnPL8HFxpYeHvGAgBkRpo73c5jj/TD+QMAMl5y5zy/Bxf2w0DsB6ggZVavXh2Qm2r27NkSqA4cOCCBSB+CE6j69++f0UXIVPTBSnqzxP0hR0g/nD8AIPDPeX4PLuymUBpYEFykXHJPc84o7k+qDDQhIYH5GBdPTwYNFPwmU4cmnv7B+QMAAv+cRyNhAAAAAI4guAAAAADgCIILAAAAAI4IzEbpAAAACEjXrl2TK1euZHQx4LCcOXNKjhw50rwcggsAAACk6DkHR44ckTNnzrC1glR4eLiUKFEiTYlKCC4AAACQLDuwKFasmOTNm5dMeUEWOF64cEGOHTtmXpcsWTLVyyK4AAAAQLJNoezAonDhwmytIJQnTx7zVwMM3c+pbSJFcAEASJW///5bZs2aZe52vfbaaymaZ/PmzbJw4UK5evWqtG3bVpo0acLWBzIBu4+F1lggeOX9f/tX93dqgwuyRQEAfPbAAw9I69atZfXq1fLee++laJ6PP/5YGjVqZJpWnDt3zsz/xhtvsPWBTISHhga3bGnoa2EjuAAA+OzJJ5+U3bt3S5cuXVI0vdZuDBgwQEaNGiXvv/++vPXWW/L222/L0KFDTbABAAgOBBcAAJ/ddtttkj17yk8hP/30k2mv/eCDD7rGde/eXa5fvy5LlixhDwBAkKDPBQAg3e3atUty5colZcqUcY3Lnz+/FC9e3NSAeBIXF2cGW2xsLHsKCEDlX/zWb+vaN+4en6b/+uuvzU0NbYqJAA0uPv30UxkzZozs379fbrzxRnn11Vfl7rvvTp/SAQCCgjaLKlCgQKLxBQsWNO95EhUVZZpRBRt/XYj5ehEGAH5vFrVs2TL573//K4MHD5Z9+/ZJz5495d577zXZPwAA8EYDi5iYmETjT58+7THoUJGRkWYee4iOjmYDA0ixNWvWyH333Sfnz583HZV10GvYOXPmSJEiRUwyirJly5qsSHv27JF3331XqlWrFm8ZK1asSNTJeePGjdKyZUuTWUmfB/HQQw/JyZMn2TOpCS40q8c999wjffv2laJFi8oLL7wgtWrVMh3zAADwpkaNGib9rJ7AbadOnTL51PU9T0JDQ03NhvsAACl1++23y/z58yVfvnzmIXE62BnqNBhYtGiRyXinz/CoXLlyipt4amDRtWtXOXz4sAk0tD+Z9iGDj8GF7pC1a9fKHXfcEW+8bmAdDwCAu+HDh5uTt32S1zt8kydPdr0/depUc+evXbt2bDgAfqfHoHLlyvk0z/jx480x6/HHH5ewsDApXbq0qQHRGg7tMgAf+lycPXvWVCvpE/vcaQ1GUmkE6ZAHAMHno48+ki1btsi2bdvk8uXLMnDgQDP+ueeek4iICNeJW99r37696cw9Y8YM6dy5s+zYscPUSixdulSmTZsm4eHhGfxpAGQ12hzTPlb5QmsqtDvAvHnzXLUhOtgPFi3nY7ASjNKcLUpTEdobNSt1yAOArExvLJUvX94MHTp0cI3XoME2evToeE2e9IncmhlK++9pE6k333xTKlSo4PeyA4De8EgJTZed8LXeTNHjF9IYXGiEp9XXx48fjzde28tqKkFvtEPes88+Gy+VYGoiRQBA4ND+d8l59NFHE40rVaqU9OnTJ51KBQDx5cyZM1GA4E2hQoVMkgl3CVNl161b19wg0WX68qyfrCTFW0V7yjdq1Mg8CMndypUrzcOUvKFDHgAAADKCNlO6ePGibNq0KdlpGzdubBJNaJNOTZGt2aa0BY67559/3mRM1Zsn2sdCM9nptXBKbrhkFT6FXFoDsXDhQvOsC+2D8c4775idNWDAgPQrIQAAAJAKNWvWlEGDBplmmXYqWm8qVqwo06dPl3HjxkmJEiVk6NChrv5kNk1Vq0GHZoq6+eabTdNQDUA06EAq+lxoVDZlyhR5+eWXpVevXuYhenPnzpX69ev7shgAAAAEiUB/YKP2j0jYR8Jb6tjevXubwV3CgKR27dqyePHidChpFu3Qrc+40AEAAAAA3NETBQAAAIAjCC4AAAAAOILgAgAAAIAjCC4AAAAAOILgAgAAAIAjCC4AAAAAOILgAgAAAIAjCC4AAAAAOILgAgAAAHDIlClT5JVXXnG9njBhgowbNy5Ny3RiGQH7hG4AAAAAnv3555+yb98+1+s//vhDzp07l+LNNX78eLl+/bo8//zzqV5GRiK4AADAj/a91t4/Kxpn+Wc9QLZs/tsGVub7Xg8aNEiuXr2a4um3bduWaHpfl5GRCC4AAAAQlH766SeZNGmSvPTSSzJjxgw5cOCANGrUSAYOHCihoaHxphk2bJi8/fbbcvDgQZk2bZqULFlS/vrrL5k8ebL8888/UrZsWXnkkUfklltuibeOpUuXysyZMyVXrlzSqlWrRGVYvny5XLp0SWrVquUat2vXLtN8au/evVKtWjV59tlnpVixYma9Or1lWdK2bVtXTYanZaxdu9Z8puPHj0vVqlVlwIABUrp0adf72owqd+7cUq5cOfn222/lwoULct9990nXrl0lPdHnAgAAAEHp8OHDMn/+fGnfvr25AO/YsaMJFnr37p1oms6dO8utt94qTz/9tISFhcnPP/8st912m+TJk8dMX6RIEbn99ttNMGJbuHChWWblypWlXbt25mJfB3fapGnLli2u16tWrZI6derIiRMnpEePHnLDDTeYdaumTZtKjRo1pHr16iYA0kEDhoTLWLJkibRo0cLM27NnT9mxY4cpuy7TptOPGDFCpk+fLq1btzbr7NWrl3z55ZeSnqi5yCR+/PFHCUQaqcM37geHQKMHMQAAgsmVK1fk/fffNwGGqlu3rrnQfvHFF81fexq9ptFaDdtTTz0lQ4YMkRdeeMG8vv/++03TpJEjR8oPP/xgxkVGRppah9GjR5vXnTp1MjUFSXnyySelW7du8YKQxx9/3PzVAEiDCV2PXXPhifbH6N+/v7z++uvmdZcuXUxQorUVb7zxhmu6EiVKyIIFCyRHjhyuJldz5851BTPpgeACAAAAQSt79uzxLtS1aZFewK9bt84VXGgTqYYNG7qm0RoAvRmotRZa06DNlHQ4dOiQGdTZs2dNjYEGLrY8efJIy5Yt5eLFix7LcuzYMVMLoU2d3BUsWDDFn0c7dm/fvl0mTpzoGqfBQ4cOHcxncqefyQ4sVIUKFVyBUXohuAAAAEDQ0gv+kJCQRBfzp0+fdr3Onz+/ZHPrmB4TE2P+/uc//zF9ItzZy7LnTxgYFCxY0GtwYWd8KlSoUKo/j71ebbrlTl+fOnUq3jjtB+JOP6NmokpPBBcAAAAIWufPn5ejR49K8eLFzevLly9LdHS0lC9f3us8pUqVMhfmWqPhrXmS1n7kzJnTdMquXbu2a/yePXukQIECSS5Xazzq16/vcRr3IMfbenUZu3fvlnr16sXrJK41ExmNDt0AAAAIanafCPXmm2+a2oe77747ydoO7fz86quvmmDBpkHJp59+av6vzY26d+9umjhpJia1atWqJJsdafamBx54QKKiolzNq7S51axZs1zTFC1aVI4cOZJkMy/txK3r1aZZdl+KefPmxeuonlEILgAAABC0tBbh77//Np2ltb+FBhqaBjZhs6KEtE+DZm+6+eabTd8F/XvnnXfGq5XQDtTahKpSpUqmM3jv3r1NRqnklqtNrapUqWKyUWkHcO2HYdPO3uvXrzfL01oT7V+RkHbk1loTXW/jxo3NtA8//LBpxpXRaBYFAACAoH2wnTYhWrx4sQkw9DkXGiQULlzY9b6mdNUMSgnly5fP1FJoqlp93oU+h0IDFPcO0trMaevWrbJx40aznho1apinc7v3uUj4ADwNTr7++mvz7Iz9+/ebQEOzOtk0payO16ZTWjOhzaASLkNrN3755RcTlGgncTvLlDvNZJWwr8mDDz5oUuamJ4ILAAAABL2KFSuaISG9sHe/uE9IH6angzd6Ae+ewrZagg7gN910k8f5tH+Etz4S2uG7SZMmrtfh4eEep6tZs6bXcrk/cM+mz+PQIT3RLAoAAACAIwguAAAAEJS8NXlC+qFZFAAAAIJSck2e4DxqLgAAAAA4guACAAAAKaLPZEDwshzYvwQXAAAASJI+U0HZD4tDcLrw//avvb/90ufi+vXrsnTpUtm0aZPce++9SabAAgAAQOanz3bQdKj6TAWVN29eyZYtW0YXCw7WWGhgoftX97P7szzSNbhYvny5PP7443LjjTfKd999J+XLlye4AAAAyALsjtF2gIHgEx4enuYO8D4FF/o0wxUrVpgHfhCtAgAAZB167acPk9MnVV+5ciWjiwOHaVOotNRYpCq4qFu3bppXCAAAgMxLL0CduAhFcEr351zExcWZwRYbG5veqwQAAACQAdI9W1RUVJSEhYW5hoiIiPReJQAAAIBgDC4iIyMlJibGNURHR6f3KgEAAAAEY7Oo0NBQMwAAAAAIbjxEDwAAAID/ay727dsnn3zyiev1ggULzLg6derIPffc40yJAAAAAAR/cHHt2jW5dOmS+f/LL79s/uprch0DAAAA8Cm4qFSpkowZM4atBgAAACAR+lwAAAAAcATBBQAAAABHEFwAAAAAcATBBQAAAABHEFwAAHx2+fJlGTZsmNx8881SvXp1GTRokJw7dy7Jefbu3SsPPfSQmadGjRrSvXt3+f3339n6ABBECC4AAD7r37+/fPzxxzJhwgSZNm2aLFu2zAQL3sTFxUmLFi3kxIkTMmvWLJk7d67kyJHDNQ4AkAVT0QIA8O+//8qMGTPkq6++kpYtW5oNMmXKFGnatKls2rRJ6tatm2gj7dmzx8w3f/58qV27thk3btw4+fTTT2Xr1q2u5QAAMjdqLgAAPlm9erVYliWtW7d2jWvSpIkUKFBAVq1a5fU5SRUqVJAvv/xSrl+/bub//PPPpVixYlKnTh32AAAECWouAAA+0RqI/PnzS758+VzjsmXLJkWLFpWDBw96nCd37tyycuVKufvuu+Wdd96R7NmzS6FCheT777+XG264wWtTKh1ssbGx7CkACHDUXAAAfKI1DyEhie9N5cyZU65du+ZxnosXL0qnTp1MDYbWbvz888/SrFkzM+7UqVMe54mKipKwsDDXEBERwZ4CgABHcAEA8InWUMTExMjVq1fjjdeO2fqeJ9rXYtu2baYzt/bJ0IxR2m9D55k5c6bHeSIjI8167CE6Opo9BQABjuACAOCTBg0amD4Ta9eudY3buXOnnDx50rzniTZv0uxQ7k2ptKZDm0tdunTJ4zyhoaFSsGDBeAMAILDR5yKTOHPmTEYXAQ6xM+UAmVXNmjVNk6ahQ4fKN998Y4KEIUOGmGdXaGpZm9ZQdO3a1dRANG/e3DSlGjFihIwePdr0udA0tlpz4d4xHACQuVFzAQDw2Zw5cyRXrlymGZR2yD569KgsWLDA1E7YDh06ZJozqYoVK8oXX3xh0tdqVikdJk6caJ6VUa9ePfYAAAQJai4AAD4rWbKkrFixQs6ePWs6cYeHhyeaZvPmzfGaQbVv394MFy5cMJ3CNeMUACC4EFwAAFJNayCSCkA8yZs3L1scAIIUzaIAAAAAOILgAgAAAIAjCC4AAAAAOILgAgAAAIAjCC4AAAAAOILgAgAAAIAjCC4AAAAAOILgAgAAAIAjCC4AAAAAOILgAgAAAIAjCC4AAAAA+D+42Lp1qzzwwANSpkwZKV68uLRv396MAwAAAACfgoshQ4aYgOLXX3+VLVu2SNGiReXOO++UQ4cOsSUBAACALM6n4GLp0qXSo0cPU3NRsmRJmTx5ssTGxsry5cvTr4QAAAAAgr/PxZkzZ+TatWtSoEAB50oEAAAAIFMKScvMgwYNktKlS0ubNm28ThMXF2cGm9Z0AAAAAAg+qa65GD58uCxcuFDmzZsn+fLl8zpdVFSUhIWFuYaIiIjUrhIAAABAsAUXY8aMkfHjx8vixYulYcOGSU4bGRkpMTExriE6Ojq1ZQUAAAAQTM2ixo4da2ojvv32W2nWrFmy04eGhpoBAAAAQHDzKbh47bXXTGChNRbNmzdPv1IBAAAACO5mUSNHjpQLFy5Iy5YtJSQkxDW88sor6VdCAAAAAMFXc3Hu3DmxLCvR+OzZ05TRFgAAAEBWCy5y5MiRfiUBAAAAkKlR5QAAAADAEQQXAAAAABxBcAEAAADAEQQXAAAAABxBcAEAAADAEQQXAAAAABxBcAEAAADAEQQXAAAAABxBcAEAAADAEQQXAAAAABxBcAEAAADAEQQXAAAAABwR4sxikN7Kly/PRg4StWvXzugiAAAApAtqLgAAAAA4guACAAAAgCMILgAAAAA4guACAAAAgCMILgAAAAA4guACAAAAgCMILgAAAAA4guACAAAAgCMILgAAAAA4guACAAAAgCMILgAAqWJZlmzfvl22bt0q165dS/F8Z8+elU2bNsmpU6fY8gAQZAguAAA+27lzp1SrVk1atmwp7du3l/Lly8v69euTnOf69esyZMgQKV68uDz88MNSt25diYyMZOsDQBAhuAAA+Fxj0a1bN6lRo4YcOnRIoqOjpU2bNtKlSxeJi4vzOt/LL78sH374oWzYsEE2b94s//zzj5QtW5atDwBZObg4evSofPLJJzJhwgRZvHixT1XhAIDMb+PGjfL777/L0KFDJXv2/zuNDBs2zAQZy5cv9ziPNoHS84ZOd9NNN5lx2bJlkyeeeMKvZQcABFBwMXXqVGnWrJl8//335o7TgAEDpHbt2nLy5Mn0KyEAIKBorYMGFXXq1HGNK1eunBQrVsy858nPP/8sly5dkg4dOsjBgwfNdLGxsUmuR2tBdBr3AQAQRMGFto/VzntarT1x4kTTIU/vVM2cOTP9SggACChaCxEeHu6qtbAVLlzYaydtbT6l07/11lvSoEED6dOnj+l78dJLL3ldT1RUlISFhbmGiIgIxz8LACADg4t69epJSEiI67X+P0eOHBIaGupwsQAAgSpnzpymFiKhixcvSq5cubzOox26T5w4Ifv37zcZppYtWyavv/66fPnllx7n0c7eMTExrkFvZgEAAtv/Hymk0PHjx2XKlCly/vx5WbFihXTs2NFk/UiqWtu9gx/V2gCQuWkTqAsXLsiZM2dMDYa6evWqHDt2zGsHbc0mpR555BHXTaqmTZua/herV6+Wzp07J5pHb1xx8woAgrxDt2YJ0TtWmqf89OnTpgrc0x0sG9XaABBcWrRoYWoiFi5c6BqnHbk14GjVqpVrnKam1VoK1bhxYylYsKDpb2G7cuWKCUiKFi3q508AAAiYmgvtsDdmzBjzf629uOWWW2TkyJEmC4i3au1nn302Xs0F7WYBIPMqUqSIDB48WAYOHGhqLLR2QZ9f0bdvX6lataprOq3Z1r4V48aNkzx58sjo0aPl+eefl8uXL0vJkiVl+vTpJuOgzgcAyKLBhbt8+fKZu1FbtmzxOg3V2gAQfMaOHSsVK1aUr776ygQYGmw89dRT8aZp2LChqzmUeuaZZ6R06dIye/ZsU8tRs2ZNefvtt02gAQDIgsGFpg50Tz147tw5k17w7rvvTo+yAQAClD6jQvtP6ODNggULEo3TvhWe+lcAALJgcKEpA7XPRa1atUxWED1xaOrB4cOHp18JAQAAAARfcLFkyRKT1WPdunWmM5+2l23ZsqW5gwUAAAAga/O5z4WmDtQBAAAAANKUihYAAAAAPCG4AAAAAOAIggsAAAAAjiC4AAAAAEBwAQAAACBwUHMBAAAAwBEEFwAAAAAcQXABAAAAwBEEFwAAAAAcQXABAAAAwBEEFwAAAAAcQXABAAAAwBEhziwG6e3ee+8NyI08YcIECVT79++XQLRv3z4JVGfOnJFAFB4entFFAAAAKUDNBQAAAABHEFwAAAAAcATBBQAAAABHEFwAAAAAcATBBQAAAABHEFwAAAAAcATBBQAAAABHEFwAAAAAcATBBQAAAABHEFwAAAAAcATBBQAAAABHEFwAAAAAcATBBQAAAABHEFwAAAAAyNjgYtKkSRISEiLdunVzpiQAAAAAsl5w8fvvv8u4ceOkTp06cu3aNedLBQAAACD4g4vz589L9+7d5b333pPixYunT6kAAAAABH9w8fTTT0vz5s2lQ4cO6VMiAAAAAJlSiC8Tf/bZZ7J27VrZtGlTiueJi4szgy02Nta3EgIAAAAIrpqLffv2mVqL2bNnS968eVO8gqioKAkLC3MNERERqS0rAAAAgGCoudiyZYucPHlSGjZs6Bp3/fr1/1tISIjs3btXypUrl2i+yMhIefbZZ+PVXBBgAAAAAFk4uOjUqZNcuXIl0bjcuXPL559/bgIMT0JDQ80AAAAAILilOLjIli1bogBCx3kaDwAAACDr4QndAAAAAByRpiqHhQsXOlMKAAAAAFk7uMienYoPAAAAAP+H6AAAAACAIwguAAAAADiC4AIAAACAIwguAAAAADiC4AIAAACAI3j6HQAgVTZv3mxSkl+9elXatm0rTZo0SfG8H374oWzdulX69+8vVapUYQ8AQJCg5gIA4LOPP/5YGjVqJEeOHJFz585J69at5Y033kjRvCtXrpTIyEiZOHGiHDhwgK0PAEGEmgsAgE8uXLggAwYMkFGjRsmLL75oxt10003y1FNPyYMPPiglSpTwOu/x48floYcekkmTJknnzp3Z8gAQZKi5AAD45KeffpIzZ86YQMLWvXt3uX79uixZssTrfJZlSZ8+faRfv37SoEEDtjoABCFqLgAAPtm1a5fkypVLypQp4xqXP39+KV68uOzevdvrfG+++abExsaa2o7Dhw8nu564uDgz2HReAEBgo+YCAOBzs6gCBQokGl+wYEHznicbN26UcePGyaxZsyRHjhwpWk9UVJSEhYW5hoiICPYUAAQ4ai4AAD7RwCImJibR+NOnT3sMOtQrr7xigoMJEyaY19oJXL3//vuyd+9eeeyxxxLNo52+n3322Xg1FwQYABDYCC4yifLly0sg2r9/f0YXIdNZsGCBBKrw8PCMLgIygRo1apj0s3v27JHKlSubcadOnZJjx46Z9zzp27ev7Nu3z/XaDk60KZUOnoSGhpoBAJB5EFwAAHxy++23S8mSJWXy5Mmu9LNTp06VvHnzSrt27VzTDR8+3HTcbt++vdx7773xlvHvv//KyJEj5f7775dWrVqxBwAgSBBcAAB8op25Z8yYYVLJ7tixw9QuLF26VKZNmxav9ksDjsuXL5vgAgCQNRBcAAB8pk/k1sxQy5YtM02kNBNUhQoV4k0zevRor82kNAh56623pGrVqmx9AAgi2SxNPO5H2iFPs35oe1vNLILMLVu2bBldBDjIz4eDTI/jGds7Vfx13OT3DCADznmkogUAAADgCIILAAAAAI4guAAAAADgCIILAAAAAI4guAAAAADgCIILAAAAAI4guAAAAADgCIILAAAAAI4guAAAAADgiBBfJl6zZo38+OOP8cblzp1bBg8e7ExpAAAAAGSNmgsNLCZPniyXLl1yDXFxcelXOgAAAADBWXOhypQpI2PGjEmf0gAAAADIOsHFqVOnZOLEiaY5VP369aVu3brpUzIAAAAAwd2hO1u2bLJr1y5ZtWqV3HbbbdKvX78kp9dmU7GxsfEGAAAAAFk8uOjSpYvs2LFD3nvvPZk9e7bpgzFjxgz5/PPPvc4TFRUlYWFhriEiIsKJcgMAAADIzMFFtWrVJEeOHK7XjRo1Ms2ifvjhB6/zREZGSkxMjGuIjo5OW4kBAAAABEefi4SyZ88u586d8/p+aGioGQAAAAAEN59qLjZt2pTo9W+//SYtWrRwulwAAAAAgrnmYvjw4XL58mWpU6eOnDhxQubMmSNdu3aVPn36pF8JAQAAAARfcLFo0SJZvXq1rFu3TsqVKydPPPGE1KtXL/1KBwAAACB4+1w0bdrUDAAAAACQpudcAAAAAIAnBBcAAAAAHEFwAQAAAMARBBcAAAAAHEFwAQAAAMARBBcAAAAAHEFwAQAAAMARBBcAAAAAHEFwAQAAAMARBBcAAAAAHEFwAQAAAMARBBcAAAAAHBHizGKQ3vbt28dGDhLNmzfP6CIAAACkC2ouAAAAADiC4AIAAACAIwguAAAAADiC4AIAAACAIwguAAAAADiC4AIAAACAIwguAAAAADiC4AIAAACAIwguAAAAADiC4AIAAACAIwguAAAAADiC4AIAAACAIwguAAAAADiC4AIA4LPLly/LsGHD5Oabb5bq1avLoEGD5Ny5c0nOs3TpUrn//vulWrVq0rRpU3n33Xfl6tWrbH0ACCIhvs5w+PBhefnll2Xx4sWSLVs26dmzp4wZM0by5MmTPiUEAASc/v37y/Lly2XGjBmSO3du6devn+zevVsWLVrkcXodP2nSJHn00UelRo0asn37dnn88cdlz549MmHCBL+XHwAQAMHFmTNnpEmTJubEsGbNGilatKh8/PHH5m7Ufffdl05FBAAEkn///dcEFV999ZW0bNnSjJsyZYqpjdi0aZPUrVs30Tzt2rWT9u3bu15XrVpV9u/fLyNGjJC33nrL3KwCAGSx4GLcuHFy4cIFmTt3ruTNm9eMe/rpp9OrbACAALR69WqxLEtat27tGqc3ngoUKCCrVq3yGFzkyJEj0bgrV65ISEgIgQUAZNXgYv78+aaGwg4sAABZj9Zc5M+fX/Lly+capzUPWpt98ODBFC3j2LFjpsaiR48eXqeJi4szgy02NjaNJQcABFSH7r///tucPDp27GjuUFWqVEmGDBliajO80RODnhDcBwBA5nX9+nVT45BQzpw55dq1a8nOrx2/O3XqJKVKlZLXX3/d63RRUVESFhbmGiIiItJcdgBAAAUXekJ57bXXpHv37ubO1SeffCKffvqpyRLiDScHAAguepMpJiYmUaanEydOmPeScv78ebnnnnvk4sWLsmzZsni1HwlFRkaa9dhDdHS0Y58BABAAwUWJEiXkrrvuMhmi9C5S48aNZeDAgaYPhjecHAAguDRo0MD0uVi7dq1r3M6dO+XkyZPmPW+0llsDC00O8v3330vhwoWTXE9oaKgULFgw3gAACKLgQjvsZc8ef5bkMnxwcgCA4FKzZk1p1qyZDB061NQoaNCgTWQ1k2CLFi1c02nHbq29VlpTodmiNLBYuXJlsoEFACALBBfPPfecqcbW9IPal2Lz5s3y9ttvm2ZSAICsY86cOZIrVy7TDOqGG26Qo0ePyoIFC+JlhTp06JAJPtQXX3whP/zwg2naVKtWLSlTpoxrOH78eAZ+EgBAhmWLatiwoXz++eemqVO3bt1MMynN9DFq1ChHCwUACGwlS5aUFStWyNmzZ00n7vDw8ETT6A0ou09Fly5d5M477/S4LGoxACALP6FbM0XpAACAZg5MKgCxaQpz0pgDQPDzqVkUAAAAAHhDcAEAAADAEQQXAAAAABxBcAEAAADAEQQXAAAAABxBcAEAAADAEQQXAAAAABxBcAEAAADAEQQXAAAAABxBcAEAAADAEQQXAAAAABxBcAEAAADAEQQXAAAAABwR4sxikN7Cw8MDciMPGDBAAtWZM2ckEH300UcZXQQAAIB0Qc0FAAAAAEcQXAAAAABwBMEFAAAAAEcQXAAAAABwBMEFAAAAAEcQXAAAAABwBMEFAAAAAEcQXAAAAABwBMEFAAAAAEcQXAAAAABwBMEFAAAAAEcQXAAAAABwBMEFAAAAAEeE+DLx5MmT5cSJE4nGV6pUSXr06OFMiQAAAAAEf81FXFycXLp0yTXExsbKsGHDZMOGDelXQgAAAADBV3MxYMCAeK/nzp1r/j7yyCPOlgoAAABA1upzMX36dGnSpInUqFHDuRIBAAAACP6aC3cHDhyQFStWyIwZM5JtSqWDTZtSAQAAAAg+qa65+PDDD6VAgQLStWvXJKeLioqSsLAw1xAREZHaVQIAAAAItuDCsiwTXDzwwAOSN2/eJKeNjIyUmJgY1xAdHZ3asgIAAAAItmZR2hxq//798uijjyY7bWhoqBkAAAAABLfsqe3IXa9ePaldu7bzJQIAAACQNYKLU6dOyddff52iWgsAAAAAWYfPwcWhQ4dk8ODBPJEbAAAAQNr6XNSsWVPGjBnj62wAAAAAglyaHqIHAAAAADaCCwAAAACOILgAAAAAkHHPuQAAAADggGzZ/LcZLSvdV0HNBQAAAABHEFwAAAAAcATBBQAAAABH0OcCAJAqlmXJjh075OrVq+YZSDly5EiXeYBM3c7dD23cgUBCcAEA8NnOnTulU6dOEhMTIzlz5jTjvvzyS2nQoIGj8wBAuiPQdBTNogAAPtHah27dukmNGjXk0KFDEh0dLW3atJEuXbpIXFycY/MAADIfggsAgE82btwov//+uwwdOlSyZ/+/08iwYcNMwLB8+XLH5gEAZD5+bxald69UbGysv1edqQXq9grkO46XL1+WQBSo+xKp35f2cS2r2Lx5swkQ6tSp4xpXrlw5KVasmHmvffv2jsyjxxf3Y4w2p1L8hlKIY01gYD8gkL4LaShDSs95fg8uzp49a/5GRET4e9VAQPjss88yughIh+NaWFhYltmup06dkvDwcFcNhK1w4cLmPafmiYqKklGjRiUaz/kjhbLQdzKgsR8QSN8FB8qQ3DnP78FFqVKlTDV4gQIFJFsaO9BoBKUnGV1ewYIFHStjMGObsc34njlH797oQVaPa1mJdsa+dOlSovEXL16UXLlyOTZPZGSkPPvss67X169fN4GIBiRpPX9kpmMmZWAbBMp3IaPXTxkydl+k9Jzn9+BC71qVKVPG0WXqRiW4YJulN75nbDNPslKNhXtzpgsXLsiZM2dMbYTS1LLHjh2TsmXLOjZPaGioGdzZ82bF3z9lYBsEyncho9dPGTJuX6TknEeHbgCAT1q0aGFqIhYuXOgap52yNXho1aqVa9z69etl//79Ps0DAMjceM4FAMAnRYoUkcGDB8vAgQNN7YPWLgwZMkT69u0rVatWdU3XsWNH6dOnj4wbNy7F8wAAMrdMHVzoyWnEiBGJqs3BNuN7lrH4bQa/sWPHSsWKFeWrr74ywYIGDk899VS8aRo2bCjly5f3aZ5AEwjfZcrANgiU70JGr58yBNa+8CabldVyKAIAAABIF/S5AAAAAOAIggsAAAAAjiC4AAAAAJC1O3RrZ8A//vjDPHypevXqfnugUmYWExMjf//9t5QuXVqKFSuW0cXJVHbu3CknTpyQevXqSe7cuTO6OAFPH3S2b98+qVKliuTPnz+jiwOkmj6g6ujRo+a7nFF5/fVcd+7cOWnUqFGGrP/IkSNm0M74GbUNNKWxnsMqVKhgHsKbUfS49u+//0rNmjX99swV3fdbtmxJNL5WrVp+3xbaTVfPhzly5DC/CX/xtg2UZpsrWrSo38py+vRp8z3Ily+f+U2EhIT4fR9ER0fL8ePHzT7IyN+DV1YmtGbNGqtkyZJW2bJlraJFi1o1atSw9uzZk9HFClh//fWX1alTJ6tQoUJW7dq1rfz581vt27e3Tp06ldFFyxT++OMPK1++fJr4wNq9e3dGFyegXbhwwerTp4+VJ08e69Zbb7UiIiKsd955J6OLBfjs4sWL1v3332++y9WqVTN/3377bb9uyZkzZ1p169Y1x+6wsDDL31auXGnVr1/fKlGihFWrVi2zDQYMGGBdv37db2VYunSpVbNmTatSpUrmr5Zh8ODBfi2D7ejRo1apUqXMuWDJkiV+W++GDRvMOhs1amQ1adLENWzfvt3yp2XLllnlypUz1176fbjtttus6Ohov6x7586d8T67DlWqVDHb5bvvvvNLGa5du2Y9/vjj5juo11J6ftNhxYoVlr/s3LnTnFv12lf3QYECBfx+XEqJTBdcnDt3zhzonnnmGfP66tWrVps2bcwBEJ4tXrzY+vrrr10H4+PHj1tVq1a1evXqxSZLwcWyntBeeOEFgosU6N69u3XjjTe6TjhxcXHW1KlT+Z4h03nxxRetMmXKWIcOHTKv58+fb44Bv/76q9/K8NJLL1kbN240AXpGBBf629X12zZv3mxutLz33nt+K8P06dOtvXv3ul7r9s+WLZvZH/6k58+2bdtaQ4YMybDg4vTp01ZG2bp1q5UrVy7rtddei1eudevWZViZ+vXrZ36jeh3oD3PnzrWyZ89ubdmyxfWd6Nu3rwk4/aVOnTrWPffcY126dMm81t9naGiotWrVKiuQZLrgwt65egfB9uOPP5of3rZt2zK0bJnJ0KFDrQoVKmR0MQLeo48+au5UrF69muAiGXoXTX+HCxcu9M/OAdJR8eLFrZEjR8YbpzcaHnvsMb9v94wKLjxp1aqV1aNHjwxbv17Qae37u+++69f16kV169atTbCZUcGF/tUAT2+y+lvXrl3NHfNAcf78eatgwYLW8OHD/bZODaq1psC91uyDDz6wcufObWo10psGl/o9+Oqrr+KNb9asWcDdLM50Hbo3b94sERER8foMNGjQwPUeUmbDhg1SuXJlNlcS5s2bJ6tXr5bx48eznVLg+++/N32g2rRpY/r2/P7773LhwgW2HTKdQ4cOmX4Wt956a7zxeq7JyueZixcvmv4f/j53xMbGypo1a2TJkiXy4IMPmgcz9ujRw2/rX79+vbz11lvy0UcfZWj/zvvvv9987kKFCrmedO/P43v79u3NMf23334z/U4y0hdffGH6YfTt29dv69Rtr30sHnnkEVm2bJl8+umnMm7cOImKipLs2dP/cjpfvnzmHHvw4EHXOK0kOHz4sNkngSQkM3YULVy4cLxxefLkMYO+h+TpAXL58uWycuVKNpcX2lmrf//+snTpUsmbNy/bKYUXZEWKFJHevXvLunXrzHbTTph64H366afZhsg07HNJwnONvs7K55lBgwbJlStX5IknnvDrevU48uKLL5ptrxdWeky54YYb/BbY6EXlpEmTpFSpUqZju79pMLFixQpp2bKlK9jR/+v3cdiwYem+/suXL7uSdNidp//55x+56aabZM6cOVKmTBnxt+nTp8tdd90l5cqV8+t+0HPZkCFDZOPGjXLy5Em58cYbpUOHDn5Zf86cOc11iT6VWzuRa3KD2bNnm47dgZZoJtPVXOjGvXTpUrxxGrnpl18jOiTtm2++kccee0zeffddad68OZvLi379+pmDt96l0Ttm27ZtM+P17sDevXvZbl5+mxpg6F1FPfFs375dPvjgAxkwYIA5EAOZ6busEp5r9M59Vj3PjBo1Sj755BP5+uuvpWTJkn5d980332yOwzt27DB3jJ9//nlzcekPGtRoUKEX1FoGvbBXenzTWhx/qFSpkiuwsGvQHn74YXNh7w+aGUotXrxYfv75Z9m0aZMJ+OLi4vweaKpdu3aZVgWPPvqoX9c7c+ZMeeaZZ0wtztatW+XAgQPmu3nHHXeYY4M/jB8/Xt544w1TBv1/7dq1zXdBb7AHkkwXXGiUqlVAGlDY9PW1a9ekbNmyGVq2QPftt99K165dzRczIw4ImYmeSDTVm55YdHj//ffN+P/9738yf/78jC5eQNKgQmnwatM7fpomT0/KQGahTW+1mYN78wOlr7PieWbMmDHm2KfnkNtvvz1Dy9KwYUNp1qyZaSLlD3r80usN+1wwduxYM/7DDz/0W4DjSfHixRN9P9MzuNDfRLt27Vzff01J3LNnT3OR728zZswwn99fNQa2RYsWme+/pgBWeozQaym9VvBXc8ns2bPLQw89ZJqFaaD97LPPmmBPUyMHkkzXLKp169bmroV+ofUAoxYsWGCqhJo2bZrRxQtYeiDu3LmzvP766zRRSQGtanSnF8f6/dI7RfRV8axVq1auCzKtrrXzgZ8/f96vOciBtNImfbfddpssXLjQtPFX+j3WpikjR47MUhv41VdfNc2QNLDIiNpu3e7a1tymNxK1eY59/k9vr732WrzX2ixKa270Jl3btm0zZBsobdrszwtK7UunNdLutN+Fv4/t2s9EaxD69OnjqmH0F/2sf/75pwk27b43GljY7/nDxYsX49VSaA3aqlWr/FaLFbTBhUaMejf0v//9rznoaYcebf/20ksvZdjDfQKdfvHuu+8+0xmsbt26rrvIeiGoJ1DACXpHS5tAaRWtNqHQk6FW22owdu+997KRkenu1uvNrMjISGncuLG88847JpGINpn0F72Q0XbdmiBBL6rtY3edOnUSXWymh7fffltefvllsy20jbe9/rCwMNMcxB/q169vOu3q+s6ePWtqDPQCX/t/ZBX6HdSLam0apftBm6f98ssvpk+gv+j3QBMcPPfccybQ0IQd2g9Ffxf+pEGuJlvQTtX+prXyWmuigY1ehx47dsz0f9Ag0183HWfMmGGaB2rnem2GrDc7tCxdunSRQJJNU0ZJJqP9K/QLrVVC2v5V78jrzob3L6MOCYWGhpp2e0ie9rnQ6s/PP//cPOEcnl2/ft1817Q2UQ8tejLSiwB/PckWcJK2L3/vvffMxYxe3GqzmBIlSvhtI+tNM7055Ckphz8uZgYPHiy//vprovEa3PjrolIv4LSPoPbb0ju2t9xyizkWu2eM9Cft2NyxY0dz40SbaPmDBpazZs0yLRC0FqNatWqmBYI/OzMr7W+oNTa7d+82/VB69eplAnB/0htXWmOi/fkygl7Ya1Cl20CbzGmLBg06/NWh2rIs0xxP+z7pNZzeNNbmaRmZxSxoggsAAAAAgSfTdegGAAAAEJgILgAAAAA4guACAAAAgCMILgAAAAA4guACAAAAgCMILgAAAAA4guACAAAAgCMILgAAAETkxIkTMmfOHPNA0PScJyOWCfgLD9EDAABBKyYmxjzdWumTjPPnzy9ly5aV6tWrS0hISLxp16xZY566fPHixRQ/dTnhPPpU8ZUrV0q3bt1S/eTk1JQDCBTxf1UAAABBJDo6Wnr06CF33XWXFCpUSC5cuCDbt2+Xs2fPyuDBg82QPfv/NeQoWrSoCQpy5MiR4uUnnGfHjh1mfV26dEkUvABZAd96AAAQ9MaOHSv16tVzvV60aJF0795dTp8+LVFRUWZc4cKF5d57700UXGzatEkOHTpkajt0mqVLl0rnzp0lZ86c8ebRWhKttVBz5841QUulSpWkfv36Xps/rV+/XvLlyyeNGjWS0NBQj9OdO3fOlFflypXLLPOWW25JVDOi0+nyrly5IrfeeqsUKVIkRe8BTiK4AAAAWU779u1l+PDhMmzYMHnuuefMxfbOnTtNrYMGC3ZzpF69esmCBQukSZMm8tdff0m1atVMMysNSsLDw+PNo7Uh2qRJ6Tx68X/nnXd6DC7eeOMNs/46deqYgOHUqVOycOFCKVeuXKJpz58/L19//bX5f1xcnAkSbrzxRlm8eLHkzZvXjN+4caO0bdtWKleubD6L1s688sorpvxJvQc4jeACAABkSR07dpQhQ4bIL7/8Ih06dEj0/jfffGNqILTm4qabbjIX9hoseFOmTBkTMPzwww8ye/Zsr82ili1bJi+88IIJDvSiX2ngon0sPClevLjp4G27dOmS3HbbbfLOO++Y8qvx48dLp06dZPr06a5ptBzJvQc4jeACAABkSSVKlDB/jx8/7vH9efPmyd13320CC6XNlp555hlZu3ZtmtY7c+ZMadmypSuwUFWrVk1yHsuyZPPmzXLgwAETHERERJgaDFuePHlk//79cubMGVOjojUv7dq1S/Y9wGmkogUAAFmSNmNS2ufBW2fw8uXLxxuX8HVqaIBQpUqVFE9/5MgRufnmm03tw9SpU00Tqb1795rMVLZRo0aZPh6lSpWSZs2amX4ksbGxyb4HOI3gAgAAZEnaHErVrl3b4/s33HCDudvvTvtapJXWHpw8eTLF07/++usm05XWPmhTKm0i1aJFC1ObYdOaDG1udfDgQRk0aJAJQFq1apXse4DTCC4AAECWo0GC3tHXPhTemiRpJ+7vvvvO9LWwaUftpOhzNJQ2XfJG0+Jqp3D35ljXrl3zGrhozYV24LZT5uqyv/3223jTaOCgNAi57777ZOTIkfLbb7+Z7FBJvQc4jT4XAAAg6Omd+z179phO05otSTtca2Ym/evNY489ZjpN613+Bx98ULZt2yZffvmlec/bA/K0uVOBAgUkMjLSdLrWDE0Js0X169dPvvjiC2nYsKH079/fZIv67LPPZOLEidKgQYNEy9RMVL179zZNsooVKyYzZswwNSqlS5d2TaM1EvpEb63R0I7kkyZNMvNputyk3gOcxhO6AQBA0Pr333/Ng/LsgEBTt+oTups3b24G9yBBMzaNGDFCZs2a5brw1n4NGmDocy5q1KhhgoX777/f1GbohbqneTZs2GCCFp1XL+g1mEhIaw0++eQTk7pWm0n17NnTPH/CWzk0c5U+60KDhDvuuMOM1yBJayGUNpGaP3++yQJ19epVE7joMjVwSeo9wGkEFwAAAF7o8ye074VNA5Xvv//eZG4CkBjNogAAALzQ5kg1a9Y0fR5+/fVXU9ugTZgAeEbNBQAAgBcxMTEybdo02bFjh0nl2q1bNxNsAPCM4AIAAACAI0hFCwAAAMARBBcAAAAAHEFwAQAAAMARBBcAAAAAHEFwAQAAAMARBBcAAAAAHEFwAQAAAMARBBcAAAAAHEFwAQAAAECc8P8B2nVbf5r+STcAAAAASUVORK5CYII=", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "plot_prediction(model, sample_idx=4)" ] @@ -781,11 +1047,83 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "sample 107: p(true class 5) = 0.0002\n", + "sample 99: p(true class 4) = 0.0368\n", + "sample 170: p(true class 5) = 0.0655\n", + "sample 255: p(true class 8) = 0.0887\n", + "sample 69: p(true class 8) = 0.1621\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAxcAAAGICAYAAAAzjx2DAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjExLjIsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvgI3uAAAAAAlwSFlzAAAPYQAAD2EBqD+naQAATRBJREFUeJzt3Qm8FuP///FP62lftO+pKAmVVEpERdFiybeyfbNl+aIiEpUiiq8oS7IU2fcWJEkoQtIiEhUtCu2nfZ//4319f3P/73POfU5nmXOf+9zn9Xw8Rs7cs1z3zNwz85nruj6Tz/M8zwAAAAAgi/JndQEAAAAAQHABAAAAIDDUXAAAAAAIBMEFAAAAgEAQXAAAAAAIBMEFAAAAgEAQXAAAAAAIBMEFAAAAgEAQXCBL2rZta4MGDYr7rZiV73nqqafaiBEjYqY8ABDrGjRoYI899liOLbN58+YpztvpHZfR5UaD3pd8wQUX2FNPPWWxZvny5W7fTJ8+PTTuiy++cOOWLFkS2HqyY5nR9Mknn7j7icTERIt1BBcxaPPmze4HkJ7h3XffzdGyrly50v766y+Ld1n5nr/++qv9/fffMVMe6du3b8Tj6fTTTw+0nEA8Wbdund1zzz129tln28knn+yCfP29du3aLC13yJAhUf/t5cQ6M3re3LhxY44t87fffktx3k7vuFNOOcVGjhyZ7uVGw6RJk2zu3LnWq1cvizX79u1z+2bHjh2hcbt27XLj9u7dm6FlzZw5013Lfv755xSfZXaZ2W3Hjh02fPhwa9OmjTVu3Ni6d+9us2fPTjFd+/btbffu3TkSnGZUwZwuAFIqW7asTZkyJcm4m266yZ0YfvrppyTjq1SpkqOb8Msvv7RixYrlaBmQcevXr7edO3faZ599lmR8wYKcEoBI3nrrLevdu7e7Aejfv7/Vrl3bBRV6Ely/fn176aWXrEePHpnaeHpQsGLFiqhu+JxYZ27y/fffW6lSpTI1nW5g//nnnywtN+haiwceeMCuuuoqK1eunOUGCuB/+eUX9zvL6I16agFEZpeZnRITE61Vq1au3I8++qgr23vvvWcdOnSwCRMmuHOOr0CBAnbbbbfZHXfcYXfffXdM70vuJGKQDiBF3uGKFy/u/k0+PqfVrVs3p4uATCpUqFDMHU9ALPr222/tiiuusH/961/26quvWr58+dx41V6oqcnll1/uPq9Vq5a1bNkyp4uLABx33HGBTpfZ6YNqTvP777+74CK30D1P0Nen7FhmVj322GO2bNkymzdvXqgmsUWLFrZhwwYXSHTt2tWOOeaY0PR6gNGvXz978cUXbcCAARaraBaVi/lt+f/44w+75pprrEmTJjZ+/Hj3RFo/oOeffz7FPKpu07SRLp468TRt2tSaNWtmt956q2sCkJm2/365Vq1aZVdeeaVbpi68ftMBPS3TulTeCy+8MGL1pcrpN9Vp1KiRnXPOOfbQQw/Znj17UjyRefbZZ105tF4199m+fbv17Nkz4ok0s98zkvSWMbwpk7aDqj07d+7sqm8jyWwZ9QRVZZk/f36mvg+AyO69915Xq/fkk0+GAguf/tZ4fT548ODQeP2GdR5KTudo/U7984TOx2reqvNWeBNF/S133XWXO7+p6YjKoTb7Z5xxhrspOXToUJJlB7XOSDJSDn/a/fv32/333+9umnS+9L355pvWpUsXF5ydddZZ9uCDD7omK5HoxkvfSefNbt26udry5M4///wk52I1H9FTYK0/s8tMb9+I8On8Js0HDhywl19+OVSm66+//qjLnTNnjgtSdV3UNKodS958Sud27WPdfGrb33LLLe76fzR6Eq4bVC03tX4o6dkm/rSqGVA51PxL31P0nZ9++mk777zz3H7VPtBxd+TIkSTL0Hf6z3/+465vqkl44403MtQ/Qut55pln3D7X+nXz7S9DN9y6B0h+ff7ggw/SXKaO+/vuu89tUy1T9yVTp05NMo2WoXl1//L+++9bu3bt3L66+eab3X5Prk2bNq6MR6PWA2qtkryJon4fupebPHlykvGqrdC9jvZpTPOQK1xwwQVegQIFkowrXry4969//ctr27at9/7773szZ870XnrpJW/btm2edu3IkSNTLOfUU0/12rVrl2Tc888/75bdp08f74svvvBmz57tderUyatYsaL3+++/p1muatWqef/+979TlKtHjx5ex44dvY8++sibM2eO17x5c+/444/3Vq5c6db/wQcfuPGnn366V7lyZW/Pnj1JlrF69Wrvl19+ccPChQu9F1980atRo4Z3/vnnJ5mub9++XsGCBb0HH3zQ++6777xJkyZ5nTt39po1a+adddZZ2fo901vG8P00depU76uvvvKuvvpqL1++fN6bb76ZqTJGKs99993n9vvnn3/uHc0ll1ziFStWzGvVqpV30kkneeedd543duxYb9++fUedF8hLEhMT3W9Sv8O06Hyn6TS96PzTokWLFNM98MAD7ne6c+dO9/fatWu97t27e2XKlAmdTzQcOnTIfX755Ze737v+ffLJJ915Tr/VIkWKeJdddlmSZQe1zkgyUg5/2iuuuMJNM2/ePO/+++8PnbO1nYYOHep9++233iuvvOJVqlTJO+WUU7xdu3aFlqHyajlnn3229+GHH7rrRa9evdy8un6E07nR/w4//PCDO4/quqLzbriMLLN06dLef/7znwyN0/ZTGQoXLuxdddVVoTKtW7cuzWWMGTPGleHWW2/15s6d682aNcuVUdtw/fr1bhp9Ly33xhtvdNtT2/+ZZ57xGjVq5B2Nrr3nnntuxM8ysk00rfappp02bZr38ccfe6+//rq3d+9er02bNu469dxzz3nff/+9ux6WL1/eTe/btGmTV6tWLe+4447zJk+e7K6FutbdcsstbtlvvPFGaFqtW+O++eab0DjdJ7Ru3dodtzqutA00ncr/8ssve1u2bHHjNd+7774b2v7+bzLSMjWPto+u3boe67O77rrLXZ+HDRsWmk7HqebVZyrv119/7dahY1fX9uQqVark1a9f/6j7pmnTpm4/J6ftq/VpfyfXr18/d98T/nuJNQQXuTy4SEhI8P7888/QuCNHjmQouNC8OmFdd911SaY7cOCAV7duXRckZCa4KFGihLdx48bQOJ0YVaZ69ep5f/31V2j8kiVL3HidiI5mxowZbtrFixe7v5ctW+b+1kUq3CeffOJODOHBRXZ8z/SU0d8eugCH7yfp0KGDV6FChdANfUbKGKk8OnHrRLp79+6jlvPaa6912+2zzz5zJ0ld+BVs6MYklk9YQLTpt6zftG780uLfIOmclpEbff/3WK5cuYjL1Y2TzmcvvPBCkvFPPfWUW44eQPiCWmdWy+FPqxvN8GuTfx0YNGhQkmXohk7j9YDEp79Llizpbd68Ocm0eiClG8G0AiHRjZ+WoQdamVlmZoILn67LCqIiST79ihUr3LVdN4zhdCOt87z2k2jbaLnajsmvD2nR9LoR9ZeTXEa2iabVtV3XmvDl6/qRP39+b/78+UmWoYeL4Q+8/JviP/74I8l0Xbt2TVdwoWuWxim4Ss7fDu+8846bRgFOcpGW2b9/f3esLl26NMm02kf6Tr/++muS4CI8WBIFshq/aNGiJONXrFhx1IeWouVpPeH3ReEPCy+66KIU8zz22GPus59++smLVTSLyuXOPPNMq1atWujv5FX2R6OO46pmvPbaa1O0x1db4o8//jhT5VKVeIUKFUJ/q6oxf/78Vq9ePatcuXJo/EknneSaEygVXbhNmza5bCaqNlU1t6oj1ald/Gn9tHWXXXZZknnPPffcFB2dsuN7pqeMPlX9h+8nUZMxLcNvxpTVMpYvX96VIT0d7FVdrewUasqlzmT6HuqQ+t1339njjz+e7m0AxDv9Jv3fYVr8z/3pg5b8POc3+/zwww+zZX1ZLYfuRcOn1bXpo48+cv8f3klV1E9F567ky4h0Ltd5U81Ef/zxxySd09XBVefZE0880S1LnV4jnYvTu8xoUfOWw4cPpzjvFy1a1DUx8s/71atXd828dN4Oz3h1tONSTWvUbK1MmTKpTpORbaKOxrrWhO/Xt99+213LTzvttCTTduzY0YoUKRL6Dtr/rVu3TtGhWs2F0+Odd95xTZEiZTk72nZIjcqk5se6hoe7+uqrXZOu8PS4kjxpg9/UTE3FwtWrV8+OPfbYo65f/Sp0b3TjjTeGmgaqafTYsWPd/+vYSM7fl1u2bLFYRYfuXK5mzZpZmn/NmjWhk71u8v+vNsuNUztCZTBQ1gWd6DJCJ8LkndRLliyZYrxOTKVLl07yI1H2BJ2k1PlKN73HH3+8u2FWCj+1BfWzQPjtUZMvU5LfyAf9PdNbRl+NGjVSLMMf56eUza59EUmkrFBqo1qiRAnXFyS87TiQl1WtWtX9qw6WafE/z44MfrrxS/671/lU585opgLPSDk0rZ+IJPk2inTdUmf45DeyRztv6kZTD2jUBr1SpUouLbBu6lTGxYsXu7SrGT0Xa5nR5J/3lSxAN5nh530FEdu2bQtdF7R9/vvf/7p+LA0bNnT9GtQnL63EKtoHus4qhWlqMrJNIu07/zv4N+j+d9CgwMa/VmtZ6i+SnvVH8ueff7rgJkg6JhUYRToe/c/TKqvf2TpSv4v00H2E+neoj41+MxrUr+mRRx5xAYeO6+T8fanfXqwiuMjl9FQgOd3k6mQSKRWbTlbhTzD8g3PcuHGhi2h61nE0CiYyMt4/mfpPcnSy+uGHH1ynL1/yjmu6ERadfJNfxDQuO79nesvo27p1a6rj/LJl175ILx0z2o6xlgMcyEl6UKGbN3Vw1VPESOcwjVeHXN3Y+g829FvybwzDZebdDXqYoaeouvn0HTx40D2VDr/BCHKdWSlHaucqfxqVMXkQpgdMyZeRnvOmOvPqplWddfWQx7d06dKI3yE9y4wmf50TJ05Ms3ZBD4SeeOIJd9OpJ9s63pSq9LnnnrOFCxemmgVJx6tuUNM6BjKyTVLbr/qNqCyRKPj0r9lpretolMI3szfxqVHZI/1m/Aeeyb9/eu5hMkodvzUoCFNgoQemOn71W4tUS+Pvy+QPUWMJzaLiUOHChV3TI2UnCqe/9X6DcGoWI8rslNqL+jLa1CqrdKGS5Bef5FkT/B9d8qwWSrmnJxzZ+T3TW0bfN998k6K5xOeff+6qcv2q5JzeF8r/rdzsasIG4P9TykfdwKZ286SMdfo8PDWknnzqAYRuvsNvQHRTmJxu2JJnXAqnZXz99ddJxmk5uvlQs8bsWGdWypEaf5rk79fReUfvcFKTmXB6t1PyZiE6b6pmQlmNMnMuTs8ysyoj29Y/7+vBVGrn/eTLVrPjoUOHuifeehikVLNp0bVy0aJFqX6e1W2i76Csj9oHkcrv7xvtfzUDTv4AS+tKD61HD/TSegmhH/ykd/urTAsWLEjx1utZs2a5f5Mfk9mpcuXKrsmYAkllvlKtSHiWNZ/KqwcZFStWtFhFcBGnVB2sNvz+CUWRrpq61KlTJ8l0+uGoDaFSB4anXtONsNoiKrVqtCmFm26ilfJOFy1dHJXuLvkLn1QlrBtzfS/dGIueQCg1bvJq4qC/Z3rL6NOTCFV7+gGG2ha/8MIL1qdPn1D71ayWMb2paNV0Sxem8BO0Lgw6ZvSU5s4778zQtgDi3Q033OD6DyjNpdJt+ilO/bSYyjuvz/V79un3pBsWnSNEN29qQhnpBWo6X6nZY2o1n+q/NmbMmNBDE6X1Vll0g6HmNNmxzqyUIzVKwa0mNmq+5DeBUnnVvl3n0+TnHt08DRw4MHSjqPS5r732mmun7j9RVj8LGT16tDsP63ysYC/5g7SMLDOrtG39J89Ho34V2i7ajuH96nSM6RqulLqi7a4+B3qyLfqu/oO1E044Ic11qO+D9nPyh25BbZNhw4a5f3X98ptI+fcdum7pHQ6ia5uu0Uqh6/+GFBilFfiE03VLN95KmeunttcxrvL6286/9qtZXHrofkHBjtIF+82N1PdQTc/Up1V9KjOjTTpT0eocojL4wY0CeF3LdQzrdQLJt78+V81Vp06dLKbldI9yZC1bVPIsFT5ljFLqOWVBqFq1qnfCCSe4bAaRUtEePHjQZRNR6j5lDKpZs6b7VxkcwrMqZCRbVKRyKUvGDTfckGK8MpYkz2Qxbtw4l8HimGOOcYNSHS5YsCBFZqm///7bpVH1v6eyKim9nb5n+/bts/V7preM/vZQlhWtWxmilBXqpptuSpHpI71lzEoqWmUhGTVqlEsJqFSBSh+oDB46XvxMNwCSUlYcpf5s0KCB+03WqVPH/baVblLjk2fxCc/wo9+ZftPjx4+PmLlJqTJPO+00l1VOGfW0TJ3Dw9O6KptNw4YN3XlO5zul5Fy1alW2rDOSjJTDnzYSZRG89NJLvUKFCnlVqlRx5x6l40yeAUjlHThwoEt7q7Seuk7oeym7T/JMUaNHj3b7QtPoXHzNNde4lK5ahrIHZWaZWckWpayBKoeWr+0angEw0vT79+/3Bg8e7K4N+h7K0qR/lTJcGbb8rGU9e/Z043VdKFu2rFe7dm3v2Wef9Y5mx44d7lr18MMPp/gsI9vEnzaS3377zevSpYu7tmk5Ov60f/W9wo8rpaDVsaF16Nqj76hrdnqyRYkyJOkeRvdDWr6+lzIp+il7RdtXx5W2j7a/0rqmtUyl/lVKXx2T+s2obFdeeaW3ffv20DR+tqjkWaWUZljjtf0yk4r2yJEj3n//+1+3LXRNVjYu3b+oTJEonX2kcsSafPpPTgc4ODo9cVBUXb9+/SRPoNWWMVKHH5/aJ+pJh9rm6cmQniqovWxqHahUta+nF5o+vF1tatSER308wqukUyuXnurrCVry8WqupbaY4Vmk/CcSevqkF8woeleEryZPWpffhjO8zaa2j19uTaOq49Re0BPE90xvGcO3hz7X9HpSlLyfSEbKGKk82tca1OEuPRmjRE+R9AIhLSc7+3MA8US/G51z1GxBv/206MV1avajflQJCQmuLbc6IetcnryZo8Zr2XrirTc5q323MumoP4GuAbpcq4OpmlOm1SQiq+uMJCPl0LlLZUiro7E+V+2pzo3JMxX5WZ40XrUlesqt9ekcmtq5TedKnVs1j64nuu6tXr3anT/9p78ZWWak61V6x/nXBm0rlUPnej/xSGrTi7artp32hX/NTk6fabn6Tkc79sKp1kBNxbQNwvex1qFai1GjRh11m4Rvv9To++o7qGyp9SHRd1AmKm0HTaf1qmYlfF/peq5p1Ewo0rVJzeF0vdN2jZQpSvP711D9DrSuoy1TvwUtV9Mn/1y1fNo2av2hpuc+LV/3MLp/Cf++K1eudNs5PRmj/H2v/apjN639qlouHVuZzeQZLQQXiDtqu6s3hCqlqv+2TgDIjcJv6ikHMkvNbtR8TR3C1QwtUnCB2DZ//nzXfFpNvpRyOZaRLQq52gcffOCeMLRr18493deTKuUL15MV5ekGACCvUw3RkiVLspTVCDmrTp06ruYr+XtCYhEdupGrKa+2Oi+qGlFVmfrxqYpUmR78/NMAAOR1ukbGcvpSpE3JX3JDYCE0i0Jc8PsyKKBI3h8DAHKr9PRfyEvlQLDS048CyCiCCwAAAACBoFkUAAAAgNzZoVspyJTOS+nGov3mZwAIkjpH+qkL05PSGFnD9QMAYv+aF/XgQoFFau9YAIDcSLnT/Tz2yD5cPwAg5x3tmhf14MJ/QYr/AhWkz2uvvRaTm2rcuHEWq15//XWLRbVq1crpIiAgerGSHpb45zVkL64fABD717yoBxd+UygFFgQX6Ve0aFGLRam9zTUWxOoNH8d9/KGJZ3S3M9cPAIjdax6NhAEAAAAEguACAAAAQCAILgAAAAAEIup9LgAAAJB7HT582A4ePJjTxUDAChUqFEhfWoILAAAApOs9B3///bdt376drRWnypQpY5UrV85SohKCCwAAAByVH1hUrFjRihUrRqa8OAsc9+zZYxs3bnR/V6lSJdPLIrgAAADAUZtC+YFFuXLl2Fpx/NqDjRs3uv2c2SZSBBcAgEz5/fff7ZVXXnFPux5++OF0zbNo0SKbNm2aHTp0yDp27GitW7dm6wO5gN/HQjUWiF/F/m//an9nNrggWxQAIMMuv/xy69Chg82dO9eefvrpdM3z8ssvW8uWLV3Til27drn5H330UbY+kIvw0tD4li8LfS18BBcAgAz7z3/+YytWrLDu3buna3rVbvTt29eGDx9uzzzzjD3++OP2xBNP2ODBg12wAQCIDwQXAIAMa9WqleXPn/5LyJdffunaa19xxRWhcT179rQjR47Yxx9/zB4AgDhBnwsAQLb77bffrHDhwla9evXQuBIlSlilSpVcDUgk+/fvd4Nvx44d7CkgBtW++6OorWv1qAsyNP2UKVPcQw01xUSMBhevv/66jRgxwtasWWPHHXecPfTQQ3b++ednT+kAAHFBzaJKliyZYnypUqXcZ5GMHDnSNaMC4lW0bsozekMORK1Z1MyZM+3f//63DRgwwFavXm2XXXaZXXjhhS77BwAAqVFgkZiYmGL8tm3bIgYdMmjQIDePP6xbt44NDCDdvvrqK7vooots9+7drqOyBt3Dvvnmm1a+fHmXjKJmzZouK9LKlSvtqaeesgYNGiRZxqxZs1J0cl6wYIG1a9fOZVbS+yCuvvpq27JlC3smM8GFsnpccMEFds0111iFChXsrrvuslNOOcV1zAMAIDUNGzZ06Wd1Afdt3brV5VPXZ5EkJCS4mo3wAQDS64wzzrDJkydb8eLF3UviNPgZ6hQMfPjhhy7jnd7hUa9evXQ38VRgcemll9pff/3lAg31J1MfMmQwuNAOmTdvnp199tlJxmsDazwAAOGGDh3qLt7+RV5P+MaPHx/6/LnnnnNP/jp16sSGAxB1OgfVqlUrQ/OMHj3anbNuvPFGK126tFWrVs3VgKiGQ10GkIE+Fzt37nTVSnpjXzjVYKSVRpAOeQAQf1566SVbvHixLV261A4cOGD9+vVz4++44w6rUaNG6MKtzzp37uw6c0+cONEuueQSW7ZsmauVmDFjhr3wwgtWpkyZHP42APIaNcf0z1UZoZoKdQd49913Q7UhGvwXi9bKYLASj7KcLUqpCP2NGgkd8gAg/ujBUu3atd3QpUuX0HgFDb4HHnggSZMnvZFbmaHUf09NpB577DE79thjo152ANADj/RQuuzkf+this5fyGJwoQhP1debNm1KMl7tZZVKMDXqkHf77bcnSSWYmUgRABA71P/uaK6//voU46pWrWq9e/fOplIBQFKFChVKESCkpmzZsi7JRLjkqbKbNm3qHpBomRl5109eku6top7yLVu2dC9CCjd79mz3MqXU0CEPAAAAOUHNlPbu3WsLFy486rSnn366SzShJp1Kka1sU2qBE+7OO+90GVP18ER9LJTJTvfC6XngkldkKORSDcS0adPcuy7UB+PJJ590O6tv377ZV0IAAAAgExo1amT9+/d3zTL9VLSpqVOnjk2YMMFGjRpllStXtsGDB4f6k/mUqlZBhzJFnXTSSa5pqAIQBR34n3xeWh0mIlCHPLWjXbt2rXuJnjaocginl5pFqXe9Ij3SCmas82QsGjNmjMUqvZUzFulEhPjA+YztDeSVl+jt27fP/vjjD9dPqkiRIoGUC7Enrf2c3mtehjt06x0XGgAAAAAgHD1RAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAgIA8++yzdv/994f+HjNmjI0aNSpLywxiGdGS4Td0AwAAAIjsl19+sdWrV4f+/umnn2zXrl3p3lyjR4+2I0eO2J133pnpZeQkggsAAABkXr580dt6nme5Tf/+/e3QoUPpnn7p0qUpps/oMnISwQUAAADi0pdffmnjxo2ze+65xyZOnGhr1661li1bWr9+/SwhISHJNEOGDLEnnnjC1q9fby+88IJVqVLFfv31Vxs/frz98ccfVrNmTbvuuuvs5JNPTrKOGTNm2KRJk6xw4cLWvn37FGX49NNPbd++fXbKKaeExv3222+u+dSqVausQYMGdvvtt1vFihXdejW953nWsWPHUE1GpGXMmzfPfadNmzZZ/fr1rW/fvlatWrXQ52pGVaRIEatVq5Z99NFHtmfPHrvooovs0ksvtexEnwsAAADEpb/++ssmT55snTt3djfgXbt2dcHCVVddlWKaSy65xE499VS79dZbrXTp0vb1119bq1atrGjRom768uXL2xlnnOGCEd+0adPcMuvVq2edOnVyN/sawqlJ0+LFi0N/z5kzx5o0aWKbN2+2Xr162THHHOPWLW3atLGGDRvaCSec4AIgDQoYki/j448/trZt27p5L7vsMlu2bJkru5bp0/T33XefTZgwwTp06ODWeeWVV9p7771n2YmaizBffPGFxaqrr746p4uQ6xx77LEWi7p162axasqUKTldBAAAAnXw4EF75plnXIAhTZs2dTfad999t/vXn0a1D6rV8N1yyy02cOBAu+uuu9zfF198sWuaNGzYMPv888/duEGDBrlahwceeCB0ja9Vq1aa5fnPf/5jPXr0SBKE3Hjjje5fBUAKJrQev+YiEvXHuPnmm+2RRx5xf3fv3t0FJaqtePTRR0PTVa5c2aZOnWoFChQINbl6++23Q8FMdiC4AAAAQNzKnz9/kht1NS3SDfx3330XCi7URKpFixahaVQDoCf/qrVQTYOaKWnYsGGDG2Tnzp2uxkCBi69o0aLWrl0727t3b8SybNy40dVCqKlTuFKlSqX7+6hj988//2xjx44NjVPw0KVLF/edwuk7+YGF/+DVD4yyC8EFAAAA4pZu+AsWLJjiZn7btm2hv0uUKGH5wjqmJyYmun//9a9/uT4R4fxl+fMnDwxKlSqVanDhZ3wqW7Zspr+Pv1413Qqnv7du3ZpknPqBhNN3VCaq7ERwAQAAgLi1e/du++eff6xSpUru7wMHDti6deusdu3aqc5TtWpVd2OuGo3Umiep9qNQoUKuU3bjxo1D41euXGklS5ZMc7mq8TjttNMiThMe5KS2Xi1jxYoV1qxZsySdxGOhSTgdugEAABDX/D4R8thjj7nah/PPPz/N2g51fn7ooYdcsOBTUPL666+7/1dzo549e7omTsrEJHPmzEmz2ZGyN11++eU2cuTIUPMqNbd65ZVXQtNUqFDB/v777zSbeakTt9arpll+X4p33303SUf1nEJwAQAAgLilWoTff//ddZZWfwsFGkoDm7xZUXLq06DsTSeddJLru6B/zznnnCS1EupArSZUdevWdZ3Br7rqKpdR6mjLVVOr448/3mWjUgdw9cPwqbP3/Pnz3fJUa6L+FcmpI7dqTbTe008/3U177bXXumZcOY1mUQAAAIjbF9upCdH06dNdgKH3XChIKFeuXOhzpXRVBqXkihcv7moplKpW77vQeygUoIR3kFYzpyVLltiCBQvceho2bOjezh3e5yL5C/AUnCg7o96dsWbNGhdoKKuTTyllNV5Np1QzoWZQyZeh2o1vvvnGBSXqJO5nmQqnTFbJ+5pcccUVLmVudiK4AAAAQNyrU6eOG5LTjX34zX1yepmehtToBj48hW2DZB3ATzzxxIjzqX9Ean0k1OG7devWob/LlCkTcbpGjRqlWq7wF+759D4ODdmJZlEAAAAAAkFwAQAAgLiUWpMnZB+aRQEAACAuHa3JE4JHzQUAAACAQBBcAAAAIF30TgbELy+A/UtwAQAAgDTpnQrivywO8WnP/+1ff39Hpc/FkSNHbMaMGbZw4UK78MIL00yBBQAAgNxP73ZQOlS9U0GKFStm+fLly+liIcAaCwUW2r/az+Hv8sjW4OLTTz+1G2+80Y477jj75JNPrHbt2gQXAAAAeYDfMdoPMBB/ypQpk+UO8BkKLvQ2w1mzZrkXfhCtAgAA5B2699PL5PSm6oMHD+Z0cRAwNYXKSo1FpoKLpk2bZnmFAAAAyL10AxrETSjiU7a/52L//v1u8O3YsSO7VwkAAAAgB2R7tqiRI0da6dKlQ0ONGjWye5UAAAAA4jG4GDRokCUmJoaGdevWZfcqAQAAAMRjs6iEhAQ3AAAAAIhvvEQPAAAAQPRrLlavXm2vvvpq6O+pU6e6cU2aNLELLrggmBIBAAAAiP/g4vDhw7Zv3z73//fee6/7V3+T6xgAAABAhoKLunXr2ogRI9hqAAAAAFKgzwUAAACAQBBcAAAAAMgdqWgBAAAApCJfPosaz8v2VVBzAQAAACAQBBcAgAw7cOCADRkyxE466SQ74YQTrH///rZr164051m1apVdffXVbp6GDRtaz5497ccff2TrA0AcIbgAAGTYzTffbC+//LKNGTPGXnjhBZs5c6YLFlKzf/9+a9u2rW3evNleeeUVe/vtt61AgQKhcQCA+ECfCwBAhvz55582ceJEe//9961du3Zu3LPPPmtt2rSxhQsXWtOmTVPMs3LlSjff5MmTrXHjxm7cqFGj7PXXX7clS5aElgMAyN2ouQAAZMjcuXPN8zzr0KFDaFzr1q2tZMmSNmfOnFTfk3Tsscfae++9Z0eOHHHzv/XWW1axYkVr0qQJewAA4gQ1FwCADFENRIkSJax48eKhcfny5bMKFSrY+vXrI85TpEgRmz17tp1//vn25JNPWv78+a1s2bL22Wef2THHHJNqUyoNvh07drCnACDGUXMBAMgQ1TwULJjy2VShQoXs8OHDEefZu3evdevWzdVgqHbj66+/tjPPPNON27p1a8R5Ro4caaVLlw4NNWrUYE8BQIwjuAAAZIhqKBITE+3QoUNJxqtjtj6LRH0tli5d6jpzq0+GMkap34bmmTRpUsR5Bg0a5NbjD+vWrWNPAUCMI7gAAGRI8+bNXZ+JefPmhcYtX77ctmzZ4j6LRM2blB0qvCmVajrUXGrfvn0R50lISLBSpUolGQAAsY0+F2GUEjFWnXXWWRaLypQpY7HqpZdeslg0ZcoUi1Xbt2+3WBTLx1le1KhRI9ekafDgwfbBBx+4IGHgwIHu3RXh51HVUFx66aWuBkLnMDWluu++++yBBx5wfS6UxlY1F+EdwwEAuRs1FwCADHvzzTetcOHCrhmUOmT/888/NnXqVFc74duwYYNrziR16tSxd955x6WvVVYpDWPHjnXvymjWrBl7AADiBDUXAIAMq1Klis2aNct27tzpOnFHql1atGhRkmZQnTt3dsOePXtcp3BlnAIAxBeCCwBApqkGIq0AJJJixYqxxQEgTtEsCgAAAEAgCC4AAAAABILgAgAAAEAgCC4AAAAABILgAgAAAEAgCC4AAAAABILgAgAAAEAgCC4AAAAABILgAgAAAEAgCC4AAAAABILgAgAAAED0g4slS5bY5ZdfbtWrV7dKlSpZ586d3TgAAAAAyFBwMXDgQBdQfPvtt7Z48WKrUKGCnXPOObZhwwa2JAAAAJDHZSi4mDFjhvXq1cvVXFSpUsXGjx9vO3bssE8//TT7SggAAAAg/vtcbN++3Q4fPmwlS5YMrkQAAAAAcqWCWZm5f//+Vq1aNTvvvPNSnWb//v1u8KmmAwAAAED8yXTNxdChQ23atGn27rvvWvHixVOdbuTIkVa6dOnQUKNGjcyuEgAAAEC8BRcjRoyw0aNH2/Tp061FixZpTjto0CBLTEwMDevWrctsWQEAAADEU7OoBx980NVGfPTRR3bmmWcedfqEhAQ3AAAAAIhvGQouHn74YRdYqMbirLPOyr5SAQAAAIjvZlHDhg2zPXv2WLt27axgwYKh4f7778++EgIAAACIv5qLXbt2med5Kcbnz5+ljLYAAAAA8lpwUaBAgewrCQAAAIBcjSoHAAAAAIEguAAAAAAQCIILAAAAAIEguAAAAAAQCIILAAAAAIEguAAAAAAQCIILAAAAAIEguAAAAAAQCIILAAAAAIEguAAAAAAQCIILAAAAAIEguAAAAAAQiILBLAZ51eLFiy1W9evXz2LRsGHDLFaVKVMmp4sAAAByMWouAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAACZ4nme/fzzz7ZkyRI7fPhwuufbuXOnLVy40LZu3cqWB4A4Q3ABAMiw5cuXW4MGDaxdu3bWuXNnq127ts2fPz/NeY4cOWIDBw60SpUq2bXXXmtNmza1QYMGsfUBII4QXAAAMlxj0aNHD2vYsKFt2LDB1q1bZ+edd551797d9u/fn+p89957r7344ov2/fff26JFi+yPP/6wmjVrsvUBIC8HF//884+9+uqrNmbMGJs+fXqGqsIBALnfggUL7Mcff7TBgwdb/vz/u4wMGTLEBRmffvppxHnUBErXDU134oknunH58uWzm266KaplBwDEUHDx3HPP2ZlnnmmfffaZe+LUt29fa9y4sW3ZsiX7SggAiCmqdVBQ0aRJk9C4WrVqWcWKFd1nkXz99de2b98+69Kli61fv95Nt2PHjjTXo1oQTRM+AADiKLhQ+1h13lO19tixY12HPD2pmjRpUvaVEAAQU1QLUaZMmVCtha9cuXKpdtJW8ylN//jjj1vz5s2td+/eru/FPffck+p6Ro4caaVLlw4NNWrUCPy7AAByMLho1qyZFSxYMPS3/r9AgQKWkJAQcLEAALGqUKFCrhYiub1791rhwoVTnUcdujdv3mxr1qxxGaZmzpxpjzzyiL333nsR51Fn78TExNCgh1kAgNj2/yOFdNq0aZM9++yztnv3bps1a5Z17drVZf1Iq1o7vIMf1doAkLupCdSePXts+/btrgZDDh06ZBs3bky1g7ayScl1110XekjVpk0b1/9i7ty5dskll6SYRw+ueHgFAHHeoVtZQvTESnnKt23b5qrAIz3B8lGtDQDxpW3btq4mYtq0aaFx6sitgKN9+/ahcUpNq1oKOf30061UqVKuv4Xv4MGDLiCpUKFClL8BACBmai7UYW/EiBHu/1V7cfLJJ9uwYcNcFpDUqrVvv/32JDUXtJsFgNyrfPnyNmDAAOvXr5+rsVDtgt5fcc0111j9+vVD06lmW30rRo0aZUWLFrUHHnjA7rzzTjtw4IBVqVLFJkyY4DIOaj4AQB4NLsIVL17cPY1avHhxqtNQrQ0A8efBBx+0OnXq2Pvvv+8CDAUbt9xyS5JpWrRoEWoOJbfddptVq1bNXnvtNVfL0ahRI3viiSdcoAEAyIPBhVIHhqce3LVrl0sveP7552dH2QAAMUrvqFD/CQ2pmTp1aopx6lsRqX8FACAPBhdKGag+F6eccorLCqILh1IPDh06NPtKCAAAACD+gouPP/7YZfX47rvvXGc+tZdt166de4IFAAAAIG/LcJ8LpQ7UAAAAAABZSkULAAAAAJEQXAAAAAAIBMEFAAAAgEAQXAAAAAAguAAAAAAQO6i5AAAAABAIggsAAAAAgSC4AAAAABAIggsAAAAAgSC4AAAAABAIggsAAAAAgSC4AAAAABCIgsEsBtltypQpMbmRx4wZY7Hqiy++sFjUu3dvi1Wxus0AAEDuQM0FAAAAgEAQXAAAAAAIBMEFAAAAgEAQXAAAAAAIBMEFAAAAgEAQXAAAAAAIBMEFAAAAgEAQXAAAAAAIBMEFAAAAgEAQXAAAAAAIBMEFAAAAgEAQXAAAAAAIBMEFAAAAgEAQXAAAAADI2eBi3LhxVrBgQevRo0cwJQEAAACQ94KLH3/80UaNGmVNmjSxw4cPB18qAAAAAPEfXOzevdt69uxpTz/9tFWqVCl7SgUAAAAg/oOLW2+91c466yzr0qVL9pQIAAAAQK5UMCMTv/HGGzZv3jxbuHBhuufZv3+/G3w7duzIWAkBAAAAxFfNxerVq12txWuvvWbFihVL9wpGjhxppUuXDg01atTIbFkBAAAAxEPNxeLFi23Lli3WokWL0LgjR478byEFC9qqVausVq1aKeYbNGiQ3X777UlqLggwAAAAgDwcXHTr1s0OHjyYYlyRIkXsrbfecgFGJAkJCW4AAAAAEN/SHVzky5cvRQChcZHGAwAAAMh7eEM3AAAAgEBkqcph2rRpwZQCAAAAQN4OLvLnp+IDAAAAwP8QHQAAAAAIBMEFAAAAgEAQXAAAAAAIBMEFAAAAgEAQXAAAAAAIBG+/AwBkyqJFi1xK8kOHDlnHjh2tdevW6Z73xRdftCVLltjNN99sxx9/PHsAAOIENRcAgAx7+eWXrWXLlvb333/brl27rEOHDvboo4+ma97Zs2fboEGDbOzYsbZ27Vq2PgDEEWouAAAZsmfPHuvbt68NHz7c7r77bjfuxBNPtFtuucWuuOIKq1y5cqrzbtq0ya6++mobN26cXXLJJWx5AIgz1FwAADLkyy+/tO3bt7tAwtezZ087cuSIffzxx6nO53me9e7d2/r06WPNmzdnqwNAHKLmAgCQIb/99psVLlzYqlevHhpXokQJq1Spkq1YsSLV+R577DHbsWOHq+3466+/jrqe/fv3u8GneQEAsY2aCwBAhptFlSxZMsX4UqVKuc8iWbBggY0aNcpeeeUVK1CgQLrWM3LkSCtdunRoqFGjBnsKAGIcNRcAgAxRYJGYmJhi/LZt2yIGHXL//fe74GDMmDHub3UCl2eeecZWrVplN9xwQ4p51On79ttvT1JzQYABALGN4CKXKFOmjMWiYcOGWazq16+fxaIpU6bkdBGALGnYsKFLP7ty5UqrV6+eG7d161bbuHGj+yySa665xlavXh362w9O1JRKQyQJCQluAADkHgQXAIAMOeOMM6xKlSo2fvz4UPrZ5557zooVK2adOnUKTTd06FDXcbtz58524YUXJlnGn3/+6R5OXHzxxda+fXv2AADECYILAECGqDP3xIkTXSrZZcuWudqFGTNm2AsvvJCkllUBx4EDB1xwAQDIGwguAAAZpjdyKzPUzJkzXRMpZYI69thjk0zzwAMPpNpMSkHI448/bvXr12frA0AcIbgAAGRK1apV3XsrUnP99den+plS18ZqvygAQOaRihYAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABA9N/Q/dVXX9kXX3yRZFyRIkVswIABwZQGAAAAQN6ouVBgMX78eNu3b19o2L9/f/aVDgAAAEB81lxI9erVbcSIEdlTGgAAAAB5J7jYunWrjR071jWHOu2006xp06bZUzIAAAAA8d2hO1++fPbbb7/ZnDlzrFWrVtanT580p1ezqR07diQZAAAAAOTx4KJ79+62bNkye/rpp+21115zfTAmTpxob731VqrzjBw50kqXLh0aatSoEUS5AQAAAOTm4KJBgwZWoECB0N8tW7Z0zaI+//zzVOcZNGiQJSYmhoZ169ZlrcQAAAAA4qPPRXL58+e3Xbt2pfp5QkKCGwAAAADEtwzVXCxcuDDF3z/88IO1bds26HIBAAAAiOeai6FDh9qBAwesSZMmtnnzZnvzzTft0ksvtd69e2dfCQEAAADEX3Dx4Ycf2ty5c+27776zWrVq2U033WTNmjXLvtIBAAAAiN8+F23atHEDAAAAAGTpPRcAAAAAEAnBBQAAAIBAEFwAAAAACATBBQAAAIBAEFwAAAAACATBBQAAAIBAEFwAAAAACATBBQAAAIBAEFwAAAAACATBBQAAAIBAEFwAAAAACATBBQAAAIBAFAxmMchuX3zxRUxu5ClTplisGjt2rMWiyZMn53QRAAAAsgU1FwAAAAACQXABAAAAIBAEFwAAAAACQXABAAAAIBAEFwAAAAACQXABAAAAIBAEFwAAAAACQXABAAAAIBAEFwAAAAACQXABAAAAIBAEFwAAAAACQXABAAAAIBAEFwAAAAACQXABAMiwAwcO2JAhQ+ykk06yE044wfr372+7du1Kc54ZM2bYxRdfbA0aNLA2bdrYU089ZYcOHWLrA0AcKZjRGf766y+79957bfr06ZYvXz677LLLbMSIEVa0aNHsKSEAIObcfPPN9umnn9rEiROtSJEi1qdPH1uxYoV9+OGHEafX+HHjxtn1119vDRs2tJ9//tluvPFGW7lypY0ZMybq5QcAxEBwsX37dmvdurW7MHz11VdWoUIFe/nll93TqIsuuiibiggAiCV//vmnCyref/99a9eunRv37LPPutqIhQsXWtOmTVPM06lTJ+vcuXPo7/r169uaNWvsvvvus8cff9w9rAIA5LHgYtSoUbZnzx57++23rVixYm7crbfeml1lAwDEoLlz55rnedahQ4fQOD14KlmypM2ZMydicFGgQIEU4w4ePGgFCxYksACAvBpcTJ482dVQ+IEFACDvUc1FiRIlrHjx4qFxqnlQbfb69evTtYyNGze6GotevXqlOs3+/fvd4NuxY0cWSw4AiKkO3b///ru7eHTt2tU9oapbt64NHDjQ1WakRhcGXRDCBwBA7nXkyBFX45BcoUKF7PDhw0edXx2/u3XrZlWrVrVHHnkk1elGjhxppUuXDg01atTIctkBADEUXOiC8vDDD1vPnj3dk6tXX33VXn/9dZclJDVcHAAgvughU2JiYopMT5s3b3afpWX37t12wQUX2N69e23mzJlJaj+SGzRokFuPP6xbty6w7wAAiIHgonLlynbuuee6DFF6inT66adbv379XB+M1HBxAID40rx5c9fnYt68eaFxy5cvty1btrjPUqNabgUWSg7y2WefWbly5dJcT0JCgpUqVSrJAACIo+BCHfby5086y9EyfHBxAID40qhRIzvzzDNt8ODBrkZBQYOayCqTYNu2bUPTqWO3aq9FNRXKFqXAYvbs2UcNLAAAeSC4uOOOO1w1ttIPqi/FokWL7IknnnDNpAAAecebb75phQsXds2gjjnmGPvnn39s6tSpSbJCbdiwwQUf8s4779jnn3/umjadcsopVr169dCwadOmHPwmAIAcyxbVokULe+utt1xTpx49erhmUsr0MXz48EALBQCIbVWqVLFZs2bZzp07XSfuMmXKpJhGD6D8PhXdu3e3c845J+KyqMUAgDz8hm5litIAAIAyB6YVgPiUwpw05gAQ/zLULAoAAAAAUkNwAQAAACAQBBcAAAAAAkFwAQAAACAQBBcAAAAAAkFwAQAAACAQBBcAAAAAAkFwAQAAACAQBBcAAAAAAkFwAQAAACAQBBcAAAAAAkFwAQAAACAQBBcAAAAAAlEwmMUgu02ZMiUmN3Kslks+//xzi0Vt27bN6SIAAABkC2ouAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASC4AIAAABAIAguAAAAAASiYEYmHj9+vG3evDnF+Lp161qvXr2CKREAAACA+K+52L9/v+3bty807Nixw4YMGWLff/999pUQAAAAQPzVXPTt2zfJ32+//bb797rrrgu2VAAAAADyVp+LCRMmWOvWra1hw4bBlQgAAABA/NdchFu7dq3NmjXLJk6ceNSmVBp8akoFAAAAIP5kOrh48cUXrWTJknbppZemOd3IkSNt+PDhmV0NAABAXFr9cOforGiUF531AJltFuV5ngsuLr/8citWrFia0w4aNMgSExNDw7p169jwAAAAQBzKVM2FmkOtWbPGrr/++qNOm5CQ4AYAAAAA8S1/ZjtyN2vWzBo3bhx8iQAAAADkjeBi69atNmXKlHTVWgAAAADIOzIcXGzYsMEGDBjAG7kBAAAAZK3PRaNGjWzEiBEZnQ0AgJyXL1901uORnQdA3pSll+gBAAAAgI/gAgAAAEAgCC4AAAAABILgAgAAAEAgCC4AAAAABILgAgAAAEAgCC4AAAAA5Mx7LgAAEM/zbNmyZXbo0CH3DqQCBQpkyzxxh3dtAIhjBBcAgAxbvny5devWzRITE61QoUJu3HvvvWfNmzcPdB7EqWgFWGm90JAgD8gWNIsCAGSIah969OhhDRs2tA0bNti6devsvPPOs+7du9v+/fsDmwcAkPsQXAAAMmTBggX2448/2uDBgy1//v9dRoYMGeIChk8//TSweQAgKlSLFY0hj4h6syg9vZIdO3ZEe9W5Wqw+2Tty5IjFqt27d1ss4tiPH/6+9M9recWiRYtcgNCkSZPQuFq1alnFihXdZ507dw5kHp33ws99ak6Va35DsVDGWChDLMjp7ZDT64+VMsBiYj9koQzpveZFPbjYuXOn+7dGjRrRXjXymEg3K0B2nddKly6dZzbu1q1brUyZMqEaCF+5cuXcZ0HNM3LkSBs+fHiK8bni+hELx0MslCEW5PR2yOn1x0oZYDGxHwIow9GueVEPLqpWreqqwUuWLGn5slhFpAhKFxktr1SpUoGVMZ6xzdhmHGfB0dMbnWR1XstL1Bl73759Kcbv3bvXChcuHNg8gwYNsttvvz1JTakCEQUkWb1+5KZzJmVgG8TKsZDT66cMObsv0nvNi3pwoadW1atXD3SZ2qgEF2yz7MZxxjaLJC/VWIQ3Z9qzZ49t377d1UaIUstu3LjRatasGdg8CQkJbgjnz5sXf/+UgW0QK8dCTq+fMuTcvkjPNY8O3QCADGnbtq2riZg2bVponDplK3ho3759aNz8+fNtzZo1GZoHAJC78Z4LAECGlC9f3gYMGGD9+vVztQ+qXRg4cKBdc801Vr9+/dB0Xbt2td69e9uoUaPSPQ8AIHfL1cGFLk733XdfimpzsM04znIWv8349+CDD1qdOnXs/fffd8GCAodbbrklyTQtWrSw2rVrZ2ieWBMLxzJlYBvEyrGQ0+unDLG1L1KTz8trORQBAAAAZAv6XAAAAAAIBMEFAAAAgEAQXAAAAADI2x261Rnwp59+ci9fOuGEE6L2QqXcLDEx0X7//XerVq2aVaxYMaeLk6ssX77cNm/ebM2aNbMiRYrkdHFinl50tnr1ajv++OOtRIkSOV0cINP0gqp//vnHHcs5lddf17pdu3ZZy5Ytc2T9f//9txvUGT+ntoFSGusaduyxx7qX8OYUndf+/PNPa9SoUdTeuaJ9v3jx4hTjTznllKhvC3XT1fWwQIEC7jcRLaltA1G2uQoVKkStLNu2bXPHQfHixd1vomDBglHfB+vWrbNNmza5fZCTv4dUebnQV1995VWpUsWrWbOmV6FCBa9hw4beypUrc7pYMevXX3/1unXr5pUtW9Zr3LixV6JECa9z587e1q1bc7poucJPP/3kFS9eXIkPvBUrVuR0cWLanj17vN69e3tFixb1Tj31VK9GjRrek08+mdPFAjJs79693sUXX+yO5QYNGrh/n3jiiahuyUmTJnlNmzZ15+7SpUt70TZ79mzvtNNO8ypXruydcsopbhv07dvXO3LkSNTKMGPGDK9Ro0Ze3bp13b8qw4ABA6JaBt8///zjVa1a1V0LPv7446it9/vvv3frbNmypde6devQ8PPPP3vRNHPmTK9WrVru3kvHQ6tWrbx169ZFZd3Lly9P8t01HH/88W67fPLJJ1Epw+HDh70bb7zRHYO6l9L1TcOsWbO8aFm+fLm7tureV/ugZMmSUT8vpUeuCy527drlTnS33Xab+/vQoUPeeeed506AiGz69OnelClTQifjTZs2efXr1/euvPJKNlk6bpZ1QbvrrrsILtKhZ8+e3nHHHRe64Ozfv9977rnnOM6Q69x9991e9erVvQ0bNri/J0+e7M4B3377bdTKcM8993gLFixwAXpOBBf67Wr9vkWLFrkHLU8//XTUyjBhwgRv1apVob+1/fPly+f2RzTp+tmxY0dv4MCBORZcbNu2zcspS5Ys8QoXLuw9/PDDScr13Xff5ViZ+vTp436jug+MhrffftvLnz+/t3jx4tAxcc0117iAM1qaNGniXXDBBd6+ffvc3/p9JiQkeHPmzPFiSa4LLvydqycIvi+++ML98JYuXZqjZctNBg8e7B177LE5XYyYd/3117snFXPnziW4OAo9RdPvcNq0adHZOUA2qlSpkjds2LAk4/Sg4YYbboj6ds+p4CKS9u3be7169cqx9euGTrXvTz31VFTXq5vqDh06uGAzp4IL/asATw9Zo+3SSy91T8xjxe7du71SpUp5Q4cOjdo6FVSrpiC81uz555/3ihQp4mo1spuCSx0H77//fpLxZ555Zsw9LM51HboXLVpkNWrUSNJnoHnz5qHPkD7ff/+91atXj82Vhnfffdfmzp1ro0ePZjulw2effeb6QJ133nmub8+PP/5oe/bsYdsh19mwYYPrZ3HqqacmGa9rTV6+zuzdu9f1/4j2tWPHjh321Vdf2ccff2xXXHGFezFjr169orb++fPn2+OPP24vvfRSjvbvvPjii933Llu2bOhN99E8v3fu3Nmd03/44QfX7yQnvfPOO64fxjXXXBO1dWrbq4/FddddZzNnzrTXX3/dRo0aZSNHjrT8+bP/drp48eLuGrt+/frQOFUS/PXXX26fxJKCubGjaLly5ZKMK1q0qBv0GY5OJ8hPP/3UZs+ezeZKhTpr3XzzzTZjxgwrVqwY2ymdN2Tly5e3q666yr777ju33dQJUyfeW2+9lW2IXMO/liS/1ujvvHyd6d+/vx08eNBuuummqK5X55G7777bbXvdWOmccswxx0QtsNFN5bhx46xq1aquY3u0KZiYNWuWtWvXLhTs6P91PA4ZMiTb13/gwIFQkg6/8/Qff/xhJ554or355ptWvXp1i7YJEybYueeea7Vq1YrqftC1bODAgbZgwQLbsmWLHXfccdalS5eorL9QoULuvkRv5VYnciU3eO2111zH7lhLNJPrai60cfft25dknCI3HfyK6JC2Dz74wG644QZ76qmn7KyzzmJzpaJPnz7u5K2nNHpitnTpUjdeTwdWrVrFdkvlt6kAQ08VdeH5+eef7fnnn7e+ffu6EzGQm45lSX6t0ZP7vHqdGT58uL366qs2ZcoUq1KlSlTXfdJJJ7nz8LJly9wT4zvvvNPdXEaDghoFFbqhVhl0Yy86v6kWJxrq1q0bCiz8GrRrr73W3dhHgzJDyfTp0+3rr7+2hQsXuoBv//79UQ805bfffnOtCq6//vqornfSpEl22223uVqcJUuW2Nq1a92xefbZZ7tzQzSMHj3aHn30UVcG/X/jxo3dsaAH7LEk1wUXilJVBaSAwqe/Dx8+bDVr1szRssW6jz76yC699FJ3YObECSE30YVEqd50YdHwzDPPuPH//e9/bfLkyTldvJikoEIUvPr0xE9p8nRRBnILNb1VM4fw5geiv/PidWbEiBHu3KdryBlnnJGjZWnRooWdeeaZrolUNOj8pfsN/1rw4IMPuvEvvvhi1AKcSCpVqpTi+MzO4EK/iU6dOoWOf6Ukvuyyy9xNfrRNnDjRff9o1Rj4PvzwQ3f8KwWw6ByheyndK0SruWT+/Pnt6quvds3CFGjffvvtLthTauRYkuuaRXXo0ME9tdABrROMTJ061VUJtWnTJqeLF7N0Ir7kkkvskUceoYlKOqiqMZxujnV86UkRfVUia9++feiGTNW1fj7w3bt3RzUHOZBVatLXqlUrmzZtmmvjLzqO1TRl2LBheWoDP/TQQ64ZkgKLnKjt1nZXW3OfHiSqeY5//c9uDz/8cJK/1SxKNTd6SNexY8cc2Qaips3RvKFUXzrVSIdTv4ton9vVz0Q1CL179w7VMEaLvusvv/zigk2/740CC/+zaNi7d2+SWgrVoM2ZMydqtVhxG1woYtTT0H//+9/upKcOPWr/ds899+TYy31inQ68iy66yHUGa9q0aegpsm4EdQEFgqAnWmoCpSpaNaHQxVDVtgrGLrzwQjYyct3Tej3MGjRokJ1++un25JNPukQiajIZLbqRUbtuJUjQTbV/7m7SpEmKm83s8MQTT9i9997rtoXaePvrL126tGsOEg2nnXaa67Sr9e3cudPVGOgGX/0/8godg7qpVtMo7Qc1T/vmm29cn8Bo0XGgBAd33HGHCzSUsEP9UPS7iCYFuUq2oE7V0aZaedWaKLDRfejGjRtd/wcFmdF66Dhx4kTXPFCd69UMWQ87VJbu3btbLMmnlFGWy6h/hQ5oVQmp/aueyGtnI/WDUUNyCQkJrt0ejk59LlT9+dZbb7k3nCOyI0eOuGNNtYk6tehipJuAaL3JFgiS2pc//fTT7mZGN7dqFlO5cuWobWQ9NNPDoUhJOaJxMzNgwAD79ttvU4xXcBOtm0rdwKmPoPpt6YntySef7M7F4Rkjo0kdm7t27eoenKiJVjQosHzllVdcCwTVYjRo0MC1QIhmZ2ZRf0PV2KxYscL1Q7nyyitdAB5NenClGhP158sJurFXUKVtoCZzatGgoCNaHao9z3PN8dT3Sfdwemis5mk5mcUsboILAAAAALEn13XoBgAAABCbCC4AAAAABILgAgAAAEAgCC4AAAAABILgAgAAAEAgCC4AAAAABILgAgAAAEAgCC4AAADMbPPmzfbmm2+6F4Jm5zw5sUwgWniJHgAAiFuJiYnu7daiNxmXKFHCatasaSeccIIVLFgwybRfffWVe+vy3r170/3W5eTz6K3is2fPth49emT6zcmZKQcQK5L+qgAAAOLIunXrrFevXnbuueda2bJlbc+ePfbzzz/bzp07bcCAAW7In/9/DTkqVKjggoICBQqke/nJ51m2bJlbX/fu3VMEL0BewFEPAADi3oMPPmjNmjUL/f3hhx9az549bdu2bTZy5Eg3rly5cnbhhRemCC4WLlxoGzZscLUdmmbGjBl2ySWXWKFChZLMo1oS1VrI22+/7YKWunXr2mmnnZZq86f58+db8eLFrWXLlpaQkBBxul27drnySuHChd0yTz755BQ1I5pOyzt48KCdeuqpVr58+XR9BgSJ4AIAAOQ5nTt3tqFDh9qQIUPsjjvucDfby5cvd7UOChb85khXXnmlTZ061Vq3bm2//vqrNWjQwDWzUlBSpkyZJPOoNkRNmkTz6Ob/nHPOiRhcPProo279TZo0cQHD1q1bbdq0aVarVq0U0+7evdumTJni/n///v0uSDjuuONs+vTpVqxYMTd+wYIF1rFjR6tXr577Lqqduf/++1350/oMCBrBBQAAyJO6du1qAwcOtG+++ca6dOmS4vMPPvjA1UCo5uLEE090N/YKFlJTvXp1FzB8/vnn9tprr6XaLGrmzJl21113ueBAN/2iwEV9LCKpVKmS6+Dt27dvn7Vq1cqefPJJV34ZPXq0devWzSZMmBCaRuU42mdA0AguAABAnlS5cmX376ZNmyJ+/u6779r555/vAgtRs6XbbrvN5s2bl6X1Tpo0ydq1axcKLKR+/fppzuN5ni1atMjWrl3rgoMaNWq4Ggxf0aJFbc2aNbZ9+3ZXo6Kal06dOh31MyBopKIFAAB5kpoxifo8pNYZvHbt2knGJf87MxQgHH/88eme/u+//7aTTjrJ1T4899xzronUqlWrXGYq3/Dhw10fj6pVq9qZZ57p+pHs2LHjqJ8BQSO4AAAAeZKaQ0njxo0jfn7MMce4p/3h1Nciq1R7sGXLlnRP/8gjj7hMV6p9UFMqNZFq27atq83wqSZDza3Wr19v/fv3dwFI+/btj/oZEDSCCwAAkOcoSNATffWhSK1Jkjpxf/LJJ66vhU8dtdOi92iImi6lRmlx1Sk8vDnW4cOHUw1cVHOhDtx+ylwt+6OPPkoyjQIHURBy0UUX2bBhw+yHH35w2aHS+gwIGn0uAABA3NOT+5UrV7pO08qWpA7Xysykf1Nzww03uE7Tesp/xRVX2NKlS+29995zn6X2gjw1dypZsqQNGjTIdbpWhqbk2aL69Olj77zzjrVo0cJuvvlmly3qjTfesLFjx1rz5s1TLFOZqK666irXJKtixYo2ceJEV6NSrVq10DSqkdAbvVWjoY7k48aNc/MpXW5anwFB4w3dAAAgbv3555/uRXl+QKDUrXpD91lnneWG8CBBGZvuu+8+e+WVV0I33urXoABD77lo2LChCxYuvvhiV5uhG/VI83z//fcuaNG8uqFXMJGcag1effVVl7pWzaQuu+wy9/6J1MqhzFV614WChLPPPtuNV5CkWghRE6nJkye7LFCHDh1ygYuWqcAlrc+AoBFcAAAApELvn1DfC58Clc8++8xlbgKQEs2iAAAAUqHmSI0aNXJ9Hr799ltX26AmTAAio+YCAAAgFYmJifbCCy/YsmXLXCrXHj16uGADQGQEFwAAAAACQSpaAAAAAIEguAAAAAAQCIILAAAAAIEguAAAAAAQCIILAAAAAIEguAAAAAAQCIILAAAAAIEguAAAAAAQCIILAAAAABaE/wfYXs2Wu+wAUAAAAABJRU5ErkJggg==", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ - "# Your code here" + "\n", + "# \"Worst\" = lowest probability assigned to the TRUE class. Index the predicted\n", + "# probability matrix with (row, true label), sort ascending, and plot the first 5.\n", + "#######\n", + "probs = model.forward(X_test)\n", + "true_class_probs = probs[np.arange(len(y_test)), y_test]\n", + "worst_indices = np.argsort(true_class_probs)[:5]\n", + "\n", + "for idx in worst_indices:\n", + " print(f\"sample {idx}: p(true class {y_test[idx]}) = {true_class_probs[idx]:.4f}\")\n", + " plot_prediction(model, sample_idx=idx)" ] }, { @@ -803,13 +1141,77 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 35, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "hidden=(10,), lr=0.001: test acc = 0.896\n", + "hidden=(10,), lr=0.01: test acc = 0.919\n", + "hidden=(32,), lr=0.01: test acc = 0.970\n", + "hidden=(64,), lr=0.01: test acc = 0.974\n", + "hidden=(64,), lr=0.1: test acc = 0.611\n", + "hidden=(64, 32), lr=0.01: test acc = 0.963\n" + ] + } + ], "source": [ - "# Your code here" + "#####\n", + "# Generalised MLP supporting any number of sigmoid hidden layers (hidden_sizes=(64, 32)\n", + "# gives the requested second hidden layer). Inherits loss/predict/accuracy from NeuralNet\n", + "# since those only rely on forward() and output_size.\n", + "#######\n", + "class DeepNeuralNet(NeuralNet):\n", + " def __init__(self, input_size, hidden_sizes, output_size):\n", + " sizes = [input_size, *hidden_sizes, output_size]\n", + " self.Ws = [np.random.uniform(-0.1, 0.1, size=(i, o)) for i, o in zip(sizes[:-1], sizes[1:])]\n", + " self.bs = [np.random.uniform(-0.1, 0.1, size=o) for o in sizes[1:]]\n", + " self.output_size = output_size\n", + "\n", + " def forward(self, X):\n", + " ######\n", + " # Cache pre-activations Zs and activations Hs (Hs[0] is the input) for backprop.\n", + " #######\n", + " self.Zs, self.Hs = [], [X]\n", + " for W, b in zip(self.Ws[:-1], self.bs[:-1]):\n", + " self.Zs.append(np.dot(self.Hs[-1], W) + b)\n", + " self.Hs.append(sigmoid(self.Zs[-1]))\n", + " return softmax(np.dot(self.Hs[-1], self.Ws[-1]) + self.bs[-1])\n", + "\n", + " def train(self, x, y, learning_rate):\n", + " ######\n", + " # Backprop from the output layer down: grad_W = H_prev^T @ error, then push the\n", + " # error back through W (before updating it) and multiply by dsigmoid(Z).\n", + " #######\n", + " x = x[np.newaxis, :]\n", + " error = self.forward(x) - one_hot(self.output_size, [y])\n", + " for l in reversed(range(len(self.Ws))):\n", + " grad_W = np.dot(self.Hs[l].T, error)\n", + " grad_b = np.sum(error, axis=0)\n", + " if l > 0:\n", + " error = np.dot(error, self.Ws[l].T) * dsigmoid(self.Zs[l - 1])\n", + " self.Ws[l] -= learning_rate * grad_W\n", + " self.bs[l] -= learning_rate * grad_b\n", + "\n", + "######\n", + "# Train each (hidden sizes, learning rate) config for 15 epochs of per-sample SGD\n", + "# and report test accuracy.\n", + "#######\n", + "def fit_eval(net, lr, epochs=15):\n", + " for _ in range(epochs):\n", + " for x, y in zip(X_train, y_train):\n", + " net.train(x, y, lr)\n", + " return net.accuracy(X_test, y_test)\n", + "\n", + "np.random.seed(0)\n", + "for hidden, lr in [((10,), 0.001), ((10,), 0.01), ((32,), 0.01),\n", + " ((64,), 0.01), ((64,), 0.1), ((64, 32), 0.01)]:\n", + " acc = fit_eval(DeepNeuralNet(n_features, hidden, n_classes), lr)\n", + " print(f\"hidden={hidden}, lr={lr}: test acc = {acc:.3f}\")" ] }, { @@ -822,7 +1224,7 @@ ], "metadata": { "kernelspec": { - "display_name": ".venv", + "display_name": "deep-learning-env (3.11.14)", "language": "python", "name": "python3" }, @@ -836,7 +1238,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.12.12" + "version": "3.11.14" } }, "nbformat": 4, diff --git a/01_materials/labs/lab_3.ipynb b/01_materials/labs/lab_3.ipynb index 0f8c7ef6a..a629d5a99 100644 --- a/01_materials/labs/lab_3.ipynb +++ b/01_materials/labs/lab_3.ipynb @@ -15,9 +15,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "GPUs disabled, using CPU.\n" + ] + } + ], "source": [ "## Tensorflow GPU disabled by default. Comment the following lines to enable GPU if you have a working CUDA installation.\n", "import tensorflow as tf\n", @@ -38,7 +46,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -78,9 +86,141 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
user_iditem_idratingtimestamp
01962423881250949
11863023891717742
2223771878887116
3244512880606923
41663461886397596
...............
999958804763880175444
999967162045879795543
9999727610901874795795
99998132252882399156
99999122033879959583
\n", + "

100000 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " user_id item_id rating timestamp\n", + "0 196 242 3 881250949\n", + "1 186 302 3 891717742\n", + "2 22 377 1 878887116\n", + "3 244 51 2 880606923\n", + "4 166 346 1 886397596\n", + "... ... ... ... ...\n", + "99995 880 476 3 880175444\n", + "99996 716 204 5 879795543\n", + "99997 276 1090 1 874795795\n", + "99998 13 225 2 882399156\n", + "99999 12 203 3 879959583\n", + "\n", + "[100000 rows x 4 columns]" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "import pandas as pd\n", "\n", @@ -102,9 +242,166 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
item_idtitlerelease_datevideo_release_dateimdb_url
01Toy Story (1995)01-Jan-1995NaNhttp://us.imdb.com/M/title-exact?Toy%20Story%2...
12GoldenEye (1995)01-Jan-1995NaNhttp://us.imdb.com/M/title-exact?GoldenEye%20(...
23Four Rooms (1995)01-Jan-1995NaNhttp://us.imdb.com/M/title-exact?Four%20Rooms%...
34Get Shorty (1995)01-Jan-1995NaNhttp://us.imdb.com/M/title-exact?Get%20Shorty%...
45Copycat (1995)01-Jan-1995NaNhttp://us.imdb.com/M/title-exact?Copycat%20(1995)
..................
16771678Mat' i syn (1997)06-Feb-1998NaNhttp://us.imdb.com/M/title-exact?Mat%27+i+syn+...
16781679B. Monkey (1998)06-Feb-1998NaNhttp://us.imdb.com/M/title-exact?B%2E+Monkey+(...
16791680Sliding Doors (1998)01-Jan-1998NaNhttp://us.imdb.com/Title?Sliding+Doors+(1998)
16801681You So Crazy (1994)01-Jan-1994NaNhttp://us.imdb.com/M/title-exact?You%20So%20Cr...
16811682Scream of Stone (Schrei aus Stein) (1991)08-Mar-1996NaNhttp://us.imdb.com/M/title-exact?Schrei%20aus%...
\n", + "

1682 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " item_id title release_date \\\n", + "0 1 Toy Story (1995) 01-Jan-1995 \n", + "1 2 GoldenEye (1995) 01-Jan-1995 \n", + "2 3 Four Rooms (1995) 01-Jan-1995 \n", + "3 4 Get Shorty (1995) 01-Jan-1995 \n", + "4 5 Copycat (1995) 01-Jan-1995 \n", + "... ... ... ... \n", + "1677 1678 Mat' i syn (1997) 06-Feb-1998 \n", + "1678 1679 B. Monkey (1998) 06-Feb-1998 \n", + "1679 1680 Sliding Doors (1998) 01-Jan-1998 \n", + "1680 1681 You So Crazy (1994) 01-Jan-1994 \n", + "1681 1682 Scream of Stone (Schrei aus Stein) (1991) 08-Mar-1996 \n", + "\n", + " video_release_date imdb_url \n", + "0 NaN http://us.imdb.com/M/title-exact?Toy%20Story%2... \n", + "1 NaN http://us.imdb.com/M/title-exact?GoldenEye%20(... \n", + "2 NaN http://us.imdb.com/M/title-exact?Four%20Rooms%... \n", + "3 NaN http://us.imdb.com/M/title-exact?Get%20Shorty%... \n", + "4 NaN http://us.imdb.com/M/title-exact?Copycat%20(1995) \n", + "... ... ... \n", + "1677 NaN http://us.imdb.com/M/title-exact?Mat%27+i+syn+... \n", + "1678 NaN http://us.imdb.com/M/title-exact?B%2E+Monkey+(... \n", + "1679 NaN http://us.imdb.com/Title?Sliding+Doors+(1998) \n", + "1680 NaN http://us.imdb.com/M/title-exact?You%20So%20Cr... \n", + "1681 NaN http://us.imdb.com/M/title-exact?Schrei%20aus%... \n", + "\n", + "[1682 rows x 5 columns]" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "columns_to_keep = ['item_id', 'title', 'release_date', 'video_release_date', 'imdb_url']\n", "items = pd.read_csv(ML_100K_FOLDER / \"u.item\", sep='|', names=columns_to_keep,\n", @@ -123,7 +420,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -140,7 +437,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ @@ -149,9 +446,134 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
item_idtitlerelease_datevideo_release_dateimdb_urlrelease_yearuser_idratingtimestamp
01Toy Story (1995)1995-01-01NaNhttp://us.imdb.com/M/title-exact?Toy%20Story%2...1995.03084887736532
11Toy Story (1995)1995-01-01NaNhttp://us.imdb.com/M/title-exact?Toy%20Story%2...1995.02875875334088
21Toy Story (1995)1995-01-01NaNhttp://us.imdb.com/M/title-exact?Toy%20Story%2...1995.01484877019411
31Toy Story (1995)1995-01-01NaNhttp://us.imdb.com/M/title-exact?Toy%20Story%2...1995.02804891700426
41Toy Story (1995)1995-01-01NaNhttp://us.imdb.com/M/title-exact?Toy%20Story%2...1995.0663883601324
\n", + "
" + ], + "text/plain": [ + " item_id title release_date video_release_date \\\n", + "0 1 Toy Story (1995) 1995-01-01 NaN \n", + "1 1 Toy Story (1995) 1995-01-01 NaN \n", + "2 1 Toy Story (1995) 1995-01-01 NaN \n", + "3 1 Toy Story (1995) 1995-01-01 NaN \n", + "4 1 Toy Story (1995) 1995-01-01 NaN \n", + "\n", + " imdb_url release_year user_id \\\n", + "0 http://us.imdb.com/M/title-exact?Toy%20Story%2... 1995.0 308 \n", + "1 http://us.imdb.com/M/title-exact?Toy%20Story%2... 1995.0 287 \n", + "2 http://us.imdb.com/M/title-exact?Toy%20Story%2... 1995.0 148 \n", + "3 http://us.imdb.com/M/title-exact?Toy%20Story%2... 1995.0 280 \n", + "4 http://us.imdb.com/M/title-exact?Toy%20Story%2... 1995.0 66 \n", + "\n", + " rating timestamp \n", + "0 4 887736532 \n", + "1 5 875334088 \n", + "2 4 877019411 \n", + "3 4 891700426 \n", + "4 3 883601324 " + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "all_ratings.head()" ] @@ -167,9 +589,151 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
item_idrelease_datevideo_release_daterelease_yearuser_idratingtimestamp
count100000.000000999910.099991.000000100000.00000100000.0000001.000000e+05
mean425.5301301988-02-09 00:43:11.369223NaN1987.956216462.484753.5298608.835289e+08
min1.0000001922-01-01 00:00:00NaN1922.0000001.000001.0000008.747247e+08
25%175.0000001986-01-01 00:00:00NaN1986.000000254.000003.0000008.794487e+08
50%322.0000001994-01-01 00:00:00NaN1994.000000447.000004.0000008.828269e+08
75%631.0000001996-09-28 00:00:00NaN1996.000000682.000004.0000008.882600e+08
max1682.0000001998-10-23 00:00:00NaN1998.000000943.000005.0000008.932866e+08
std330.798356NaNNaN14.155523266.614421.1256745.343856e+06
\n", + "
" + ], + "text/plain": [ + " item_id release_date video_release_date \\\n", + "count 100000.000000 99991 0.0 \n", + "mean 425.530130 1988-02-09 00:43:11.369223 NaN \n", + "min 1.000000 1922-01-01 00:00:00 NaN \n", + "25% 175.000000 1986-01-01 00:00:00 NaN \n", + "50% 322.000000 1994-01-01 00:00:00 NaN \n", + "75% 631.000000 1996-09-28 00:00:00 NaN \n", + "max 1682.000000 1998-10-23 00:00:00 NaN \n", + "std 330.798356 NaN NaN \n", + "\n", + " release_year user_id rating timestamp \n", + "count 99991.000000 100000.00000 100000.000000 1.000000e+05 \n", + "mean 1987.956216 462.48475 3.529860 8.835289e+08 \n", + "min 1922.000000 1.00000 1.000000 8.747247e+08 \n", + "25% 1986.000000 254.00000 3.000000 8.794487e+08 \n", + "50% 1994.000000 447.00000 4.000000 8.828269e+08 \n", + "75% 1996.000000 682.00000 4.000000 8.882600e+08 \n", + "max 1998.000000 943.00000 5.000000 8.932866e+08 \n", + "std 14.155523 266.61442 1.125674 5.343856e+06 " + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "all_ratings.describe()" ] @@ -183,7 +747,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -193,36 +757,240 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "items['popularity'].plot.hist(bins=30);" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "np.int64(141)" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "(items['popularity'] == 1).sum() # Number of movies with only one rating" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "49 Star Wars (1977)\n", + "257 Contact (1997)\n", + "99 Fargo (1996)\n", + "180 Return of the Jedi (1983)\n", + "293 Liar Liar (1997)\n", + "285 English Patient, The (1996)\n", + "287 Scream (1996)\n", + "0 Toy Story (1995)\n", + "299 Air Force One (1997)\n", + "120 Independence Day (ID4) (1996)\n", + "Name: title, dtype: str" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "items.nlargest(10, 'popularity')['title'] # Get the 10 most popular movies" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
item_idpopularityrelease_datevideo_release_daterelease_yearuser_idratingtimestamp
count100000.000000100000.000000999910.099991.000000100000.00000100000.0000001.000000e+05
mean425.530130168.0719001988-02-09 00:43:11.369223NaN1987.956216462.484753.5298608.835289e+08
min1.0000001.0000001922-01-01 00:00:00NaN1922.0000001.000001.0000008.747247e+08
25%175.00000071.0000001986-01-01 00:00:00NaN1986.000000254.000003.0000008.794487e+08
50%322.000000145.0000001994-01-01 00:00:00NaN1994.000000447.000004.0000008.828269e+08
75%631.000000239.0000001996-09-28 00:00:00NaN1996.000000682.000004.0000008.882600e+08
max1682.000000583.0000001998-10-23 00:00:00NaN1998.000000943.000005.0000008.932866e+08
std330.798356121.784558NaNNaN14.155523266.614421.1256745.343856e+06
\n", + "
" + ], + "text/plain": [ + " item_id popularity release_date \\\n", + "count 100000.000000 100000.000000 99991 \n", + "mean 425.530130 168.071900 1988-02-09 00:43:11.369223 \n", + "min 1.000000 1.000000 1922-01-01 00:00:00 \n", + "25% 175.000000 71.000000 1986-01-01 00:00:00 \n", + "50% 322.000000 145.000000 1994-01-01 00:00:00 \n", + "75% 631.000000 239.000000 1996-09-28 00:00:00 \n", + "max 1682.000000 583.000000 1998-10-23 00:00:00 \n", + "std 330.798356 121.784558 NaN \n", + "\n", + " video_release_date release_year user_id rating \\\n", + "count 0.0 99991.000000 100000.00000 100000.000000 \n", + "mean NaN 1987.956216 462.48475 3.529860 \n", + "min NaN 1922.000000 1.00000 1.000000 \n", + "25% NaN 1986.000000 254.00000 3.000000 \n", + "50% NaN 1994.000000 447.00000 4.000000 \n", + "75% NaN 1996.000000 682.00000 4.000000 \n", + "max NaN 1998.000000 943.00000 5.000000 \n", + "std NaN 14.155523 266.61442 1.125674 \n", + "\n", + " timestamp \n", + "count 1.000000e+05 \n", + "mean 8.835289e+08 \n", + "min 8.747247e+08 \n", + "25% 8.794487e+08 \n", + "50% 8.828269e+08 \n", + "75% 8.882600e+08 \n", + "max 8.932866e+08 \n", + "std 5.343856e+06 " + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "all_ratings = pd.merge(popularity, all_ratings)\n", "all_ratings.describe()" @@ -230,7 +998,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 14, "metadata": { "collapsed": false }, @@ -241,9 +1009,140 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
item_idpopularitytitlerelease_datevideo_release_dateimdb_urlrelease_yearuser_idratingtimestamp
01452Toy Story (1995)1995-01-01NaNhttp://us.imdb.com/M/title-exact?Toy%20Story%2...1995.03084887736532
11452Toy Story (1995)1995-01-01NaNhttp://us.imdb.com/M/title-exact?Toy%20Story%2...1995.02875875334088
21452Toy Story (1995)1995-01-01NaNhttp://us.imdb.com/M/title-exact?Toy%20Story%2...1995.01484877019411
31452Toy Story (1995)1995-01-01NaNhttp://us.imdb.com/M/title-exact?Toy%20Story%2...1995.02804891700426
41452Toy Story (1995)1995-01-01NaNhttp://us.imdb.com/M/title-exact?Toy%20Story%2...1995.0663883601324
\n", + "
" + ], + "text/plain": [ + " item_id popularity title release_date video_release_date \\\n", + "0 1 452 Toy Story (1995) 1995-01-01 NaN \n", + "1 1 452 Toy Story (1995) 1995-01-01 NaN \n", + "2 1 452 Toy Story (1995) 1995-01-01 NaN \n", + "3 1 452 Toy Story (1995) 1995-01-01 NaN \n", + "4 1 452 Toy Story (1995) 1995-01-01 NaN \n", + "\n", + " imdb_url release_year user_id \\\n", + "0 http://us.imdb.com/M/title-exact?Toy%20Story%2... 1995.0 308 \n", + "1 http://us.imdb.com/M/title-exact?Toy%20Story%2... 1995.0 287 \n", + "2 http://us.imdb.com/M/title-exact?Toy%20Story%2... 1995.0 148 \n", + "3 http://us.imdb.com/M/title-exact?Toy%20Story%2... 1995.0 280 \n", + "4 http://us.imdb.com/M/title-exact?Toy%20Story%2... 1995.0 66 \n", + "\n", + " rating timestamp \n", + "0 4 887736532 \n", + "1 5 875334088 \n", + "2 4 877019411 \n", + "3 4 891700426 \n", + "4 3 883601324 " + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "all_ratings.head()" ] @@ -263,13 +1162,88 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 16, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
item_idaverage_rating
013.878319
123.206107
233.033333
343.550239
453.302326
\n", + "
" + ], + "text/plain": [ + " item_id average_rating\n", + "0 1 3.878319\n", + "1 2 3.206107\n", + "2 3 3.033333\n", + "3 4 3.550239\n", + "4 5 3.302326" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "raise NotImplementedError(\"Please calculate the average rating for each movie\")" + "average_ratings = (\n", + " all_ratings.groupby(\"item_id\")[\"rating\"]\n", + " .mean()\n", + " .reset_index(name=\"average_rating\")\n", + ")\n", + "\n", + "average_ratings.head()" ] }, { @@ -281,7 +1255,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "metadata": {}, "outputs": [], "source": [ @@ -321,7 +1295,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 18, "metadata": {}, "outputs": [], "source": [ @@ -332,7 +1306,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 19, "metadata": {}, "outputs": [], "source": [ @@ -379,9 +1353,38 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 513us/step - loss: 2.6229 - val_loss: 1.0500\n", + "Epoch 2/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 492us/step - loss: 0.8521 - val_loss: 0.7947\n", + "Epoch 3/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 498us/step - loss: 0.7511 - val_loss: 0.7673\n", + "Epoch 4/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 495us/step - loss: 0.7226 - val_loss: 0.7524\n", + "Epoch 5/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 475us/step - loss: 0.7001 - val_loss: 0.7469\n", + "Epoch 6/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 524us/step - loss: 0.6796 - val_loss: 0.7408\n", + "Epoch 7/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 495us/step - loss: 0.6587 - val_loss: 0.7406\n", + "Epoch 8/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 487us/step - loss: 0.6372 - val_loss: 0.7411\n", + "Epoch 9/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 485us/step - loss: 0.6133 - val_loss: 0.7407\n", + "Epoch 10/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 496us/step - loss: 0.5888 - val_loss: 0.7399\n", + "CPU times: user 9.61 s, sys: 10 s, total: 19.6 s\n", + "Wall time: 5.92 s\n" + ] + } + ], "source": [ "%%time\n", "\n", @@ -393,9 +1396,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "plt.plot(history.history['loss'], label='train')\n", "plt.plot(history.history['val_loss'], label='validation')\n", @@ -411,16 +1425,16 @@ "**Questions**:\n", "\n", "- Does it look like our model has overfit? Why or why not? \n", - "Your Answer: ____________\n", + "Your Answer: It shows a little sign of overfitting.\n", "- Suggest something we could do to prevent overfitting. \n", - "Your Answer: ____________\n", + "Your Answer: we could add a dropout perhaps\n", "\n", "Now that the model is trained, let's check out the quality of predictions:" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 22, "metadata": {}, "outputs": [], "source": [ @@ -435,9 +1449,29 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 23, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m625/625\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 230us/step\n", + "Final test MSE: 0.905\n", + "Final test MAE: 0.733\n" + ] + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYEAAAF4CAYAAACyxEX1AAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjExLjIsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvgI3uAAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAeYNJREFUeJztvQm8pFV55/9796q7dtPs2iiIYgRUNHEJwRXiEscIgkj2cRijUcfEmajM/I2DUTsfjYqj6AQyOuoY4zYhjkbRMEaD+4IixomKLA2ySEPfrare9fw/v+ec997qS2+3+laft6rO10/53ve8D93nVled55xn9ZRSCg6Hw+GYSHzbE3A4HA6HPZwScDgcjgnGKQGHw+GYYJwScDgcjgnGKQGHw+GYYJwScDgcjgnGKQGHw+GYYJwScDgcjglmJJVAWZa44YYb8LOf/cz2VBwOh2OkCTFi/O///b/xspe9DFNTU/I69thj8ZGPfARHHnmk7ak5HA7HyDFSSuDLX/4yLrjgAlx55ZV40YteJGP/9E//hLvuusspAYfD4RgAb5RqBz3taU9DFEW4+uqrbU/F4XA4xoKROQmkaYprr70Wb3/727G0tIQf//jHOP7443Hccccd8L/jq6aqKtx7773Ytm0bPM87DDN3OByO4cK9PNdFrom+74+nErjnnnuQ5zmuv/56nHLKKeIL+OlPf4onPvGJ+Ju/+RtZ1PfGjh07cOmllx72+TocDsfhZufOnXjgAx84nuagu+++G8cccwwe/OAH4xvf+AaOPvpo7Nq1S5TAmWeeife///0HdRJYWFjACSecIG/W3NzcYfwNHI7JoSgrVArwPexx4uZyU4+HQTOCE6tKoagUOMtKKXBF5KLIe07d9zy5D30PPifeQBYXF7F9+3bs3r0b8/Pz43kSYPTP9PQ0zjvvPFEAhLt/Ooo/+tGP7vO/S5JEXuuhAnBKwOEY3qIa7GfBLCvViEVVKSVzodKiGtiX0qIaoNLi79RkM/Igc2uGKj4IaOc655xzcPvtt+8xftttt+Goo46yNi+Hw4F1i6aSxXR/8Lnedds3RJSlEgWwtwWe9xznc8qNIyNzEiBveMMbxPTz+te/Xq40C9Ef8LGPfcz21BwOh4Hr+oF2+FxceWKwTVUplGrt1FIrJV5qfcC58jFPDJQPguaeBAZhZE4C5PTTT8dXv/pV2f2/5S1vwU033YQvfelLOPfcc21PzeFwmMXzYJd2ytk+CHhcz9WaUtKmIW3O4rVe+OWE0KcYxomRcQxvpgOFjhM6iJ1PwDFq7Gun2qT5cfE8GFs/F9cwsGtjL8sKaVHJvA/kE+B4EvoIGuLQ3qx1baTMQQ7HJMNFc+/RKwc2vxxOZNOszO55H+jnsI5PP4AC8gqIQ54GtEKoKj7TMoHvIysUYr9Z7/Nm4ZSAwzFiIZf9C5HsvCsFX+noFdvU9nOJDtrPesnfhdFBtk8xisrIBwKlkGYlyqrUTuCKi78+AQR+gDAAPDqID6DcRhGnBByOkTgBcFG6/+Ij0St9Tssm7FQ5Byolzml/eQJNmKvneeD/8lLJq7az8aQlfmv+HkqHj0aWTVfDwikBh2OMQi5p2mjCQsVTSW2+4rXffNWE/IAapbQCzYpKwtBp+uG1ni/NQqXy5HkSalNcA97eTcUpAYej4YxSyOXe7O3NdmRXyIsSMR2+vr+Hz4VQIYSeNg9RLok49wDjhFMCDseYhVw2aI1dXfCbNKf7ZQwr7U/Zv9LydFbxGAZTOiXgcDQYrj8Hu37W5pYmwWgbfV2LttlolcthohSdvTojWN+r+82XSoDPa9lxwykBh6PhjFLIZT9FUaGoKllQqQq4pnJhDfni/zUAz9MOd1rbGB1U0QmsvNX5eh79MQpxVNcNwtjRjH8Jh8Oxn5BLT0eq7AcdcdOc6JVeVqBXUAHQ4bqmAHjPcT5vjhIAsrxAYU4BNAuJYjB+GI7zuYSMNuPt3VScEnA4Go6EXJow0PU26boKZlNCLtdOAHpx4bWX1Qv/nuOUs43v+2II6uYKrSjQIa3QyotX3nOcz72GmbI2C2cOckxMSYNRZlRCLrl40gRUFAWXUAQeC6758M1noj4J+KhQ+CH8yu7Cqhh+63uIA2C5m6OSZDEfTBlg/oUoglzJc8q5ZDGHY8RLGowyoxBySbKsEgVA5cRTCuvz1I5WzpTjReWLHEMz7ePJ/7OGkFcV8INQQkI537IsoHwmiomHAOOIOwk4JqakwTjQ9JBLmngy+gE8ICu4c6bJRztaVUkJmq/4WVHIlJaPWZTHEhXNVXkpSms68bB7sYsiK7CcATMxEHrAlrkWaByiHJXWuFmEnBJwTFRJA8dw0c5fhUrCKteOhTy5VKZsM/+vLslge0FVqkRRlsiyAgvdEosLKyi9AJ0cSCPWFCqRqRDz7QB+HEIpcXFjnHBKwDFxJQ0cw4Pdt/TJUCEMw7WIJfPPXtfkyYtCnlE+tLwKpXmJ2+5ZwVJaorO0iCqMsVQAsyHgFxmWyxBLSYDtR80AiDBuOCXgmMiSBo7hwK5brMpZFh4S40jVrzUTFk+NqfIQBFreJkWhcN9Kilvv3o0e57XUQRVVyEugS2dw3kOCGPctKMxMRThyJkE0ZnrAKQHHxJY0cGw+YvZjxU2fIaGl2P49b60gG30EleJzyumIJ5uUZYa7F5fx84X7gLCFKs0QezFy+cACWZphBR2g6OHIxTZOOrIFIMY4MV7GLcdhZdRLGowi9c5awkQb0qi9n7oSpyc1+PVJoKxYpK2SK++lm5gfrFbstMlKt4ebf3EvVvIcrAjRKysspj3c1+vJlfcc53OR6/YwbriTgGMiSxqMIroHLhfSOkO4znjVxc+aAs09Ui6CtXaqUk4C0kRGyvVXUD6Tstisxf4etNNL8YuFJXSyAl5UYLnbgxdV6LHEND/beQbEU/Jc5Hopxg2nBBwT00VqlKGzlb17mcyEvs5XEnLJWjyB14gwXMkN8Y0iKCt0sxJMG0tzIIm44ChMhRUiUVz2T4e9LMOuTheMZO0uL6FzXwk/6SLjPSOdUqAXLCEoc+zq5CI/bjgl4JiYLlKjmuHMEwCbmjCSpk7IY9w9FYEUODO7bkbb2H6fZWMAD4udDHnlocxzSb6iScVjTf6Su+0QqV/g6Lm29fc7L0r0uiW4wVdBiXvvAYIWkJZAEgBlDzgi7sErgVai5ccNpwQch/4hGpGSBqOY4SwJd6UpuObpLFyWYahhGYa8YmvEUp5Fnm91YeX7masKvbxCrhR63QKlr0CrSjcGgqpEyy9Qep7I2XZphD4jhIDbbgNas8CuHGjnAMvb0fDT5e90L9BbAh78IC0/bjgl4JiokgajluHMOTGOneXLktC/X8gl39849JDmWk6crhbfc5qremmBlW6KXu6h4kkgpI+A4ZbcSefIqhCtSKGXRphNgj2U2uGfb4VeB7gLwNwScC+AKZ4QTEZAh5/tJWARwLGdtf4I44RTAo6JzXDeVwx7kzKcWXeHpqAo9Pd7emETdMq1St0r1+Z87+uk6KUVj4jGj1FI3H3FuHulECeQ55Q7YjqyGndfFAW6XeA+fjYYLWSumQkE7ZpFcoE/d7X8uOGUgGNizCv9Gc77nW/DMpyptPRL7fv0InOGdbKiwO6lFJ1eBj+IkGU5V350K6DN1bUqUHkFqjJHsARkW1toIbE235U0xX3LZu5mjGYgTrWOA6rHKUf5ccMpAceEmVf0Yrrf+YoisL/498+Xp5O9vYd1faa6VINtG3tVlFhKM6RlISeTtLOCKoi0EmBzmTJHghAxvcSplrfJYqeDXebneudf/8t768Z3GflxwykBx8QUkOMCKY1ZcGBzEMeb0E5Qwi1NLgYpS71oroWIsvRCoOdrwjNtklUlOt0Ui50Ume+j0+miCsvVaBvW4pnyI8RVhTmViLzV+XZTsff7fYthue4amueLRn7ccErAMUEF5PTiTmV0QHOQLnNpvYY83y/Wss8k5r5AnjPqnjH4YnIHCzJEkVYAcWA3MkjmWyksZBluX9iNKJmGVxaIwni1l0BWFkg7KfJ0BQ8It4q8TVJV6KJ2Zqe/N+px38iPG04JOCaugBxNJ4y2YbFjWTTNSUDMQfyZvaVsHwEMzLaNwgC7OxkyLvweHb+h3vGzHj+jcYpCOl9NS9y93aOA5AH0OljqppiLW8jSAp5KJTqI4ZUqKxCHpTynHOVtMtuaQoQFCQk9EJGRHzecEnBMUAE5moCwuiDVZp89SzDocMZI1lL7ikCUkzG5SXcrlmFgD9zV9odKxivG3Ff2y3MweibtZShRIk1zdNIUofKkgUxM30WWQoWJft7LrEfbFAUzmg9S1siPG04JOCaogJxZJBVNK9ijwiUXVVUxHJOLKucaNMIcRB9AWhSYTgLxAyx3ldTiTzMgiYHIYwcsD4EfiFxSelLH39p8K4UOKpSFQqcoUOTUuFppFVQCeSXj8pxylk+I06EnOQEHQ27kxw2nBBwTVUBu1ZEt3ta9OLLpLzCZz02BTc+lBk+lazW1g0BOMjytMDmrk1UIfYWpxP7XOWcJC5qA6FsxDmwUqTiGwTIMlY62YZcxylHeJncvd4YqPwrY/9RsgBtvvBF33HHHHmPT09M444wzrM1pkhm1AnISHWTMP8y+1ZE2puftaqSNL5m3ZQPCLQmnyBIMaUEvBn8HduMykSvyf544V1OJvmJ9IVjt1MUCcTl3+HxTFevyAF7J0wtQhvQJANFsKc8pR3mb5MxiG6L8KDBSSuCtb30rPvGJT+DhD3/46thJJ52ED37wg1bnNcn0F5CrHa217V/CL6EVhe3wUI12YjC7Ns1KbUdXugm6X5pibCUQ8chveuHahj1wM66gfI9Zklk0Fp3bLHimO6X7bH6uKmQ5FVdo9WvN9zNSnpRi8MquZNmyhDSrcrLRfNEDguUuVApsneJnxe7n4u5dw5UfBUZKCZCnPOUpoggczYFJTEVRyYlAzC0mnI67a54AmpQoxmWdu1A6f+kbEJ+AMf2zLgwbpHPnylr3TTgJcMYsDichoaEvVSz5Dqc8zVBxQSEJQknMYsiobcUVxxG8OMDCEpAooLOsk8T4fjNwqbsMBNNAugwcf3wg8jap8uHKjwIjpwR6vR6++93vYn5+HieeeKL1zkQOk61q8gGCkOGgWgFI5I153gRFIKGqpZJdKU8DeaETw8RywWxWicn3kJUKyQH8HIeLiuWYFbDcKxBEClk3h/J9qcqZx4zLr5DBR5mXmJ0KRd4mRUlncC71+bMesFwAxRIri2ondq8Akp7oX5GjvE3u/cVw5UeBkVMCV199NW699VbceeedSJIEf/VXf4VnP/vZ+5RP01ReNYuLzPtzbLajlUsPk5ioACQctKpry5u6N43IGKZ2UiizHFkRSMw9s225QxUnZlliJaX/ksXjIy1vuQMrlSnr8/e6GdJFHle6CENm2koZHhRFCnQUkkhhfiqynjFcFgU63Rxc22mZkizbfK0gG5szbjFz13J2lUCWD1d+FLC/PdsAz3jGM3D77bfj+uuvFwfxRRddhAsuuEAcxvtix44dcmqoX9u3bz+sc56EjGGaUWgKIlzoGWFTL/jaRFTXtbFrqqBSYmMW5QVSfjkvFVbSAkudQq685zifU64JJwGarrpFLtfSK7HY6+HulRXcsbIiV95zvF/OJnSqd7rs3QuwHS/XzDojl1fec5zPKUd5m9yVDld+FBgpJXDuuefi6KOPlp+5g+MCH0URPvWpT+3zv7nkkkuwsLCw+tq5c+dhnPH4I4sq9MKvG6BX4h/gta6/w+eUs4105jIJTSu9Ujc9933EEZu16Fr9HOdz6dzVgDlz6ez1CuzudrGcFzrb2YRf8sp7jvM55Wz7BNIyx/KyLrgmygAAi3QumeuKGedzylHeJtWQ5UeBkTMH9UNFsG3bNjkd7AuajPhyDKnxuVnoufDTgUlzkAkJF9MEE68Yk18XkZP4fEtwPhL/7/m64J2Yrjgv7bQkOn9A1+63bVohbCzfyXIsdHuIEj3nmB3G6H/xdNRNkRfI0x7ms5bI2yTr9LCwoM1AoTH/8AWjAGAUAtUV5Shvk+Uhy48CI6MEuEujU7jdbq+O/eQnP8Ett9yC0047zercJhWdfauP9HSmSkkD319dVEsqBi5alSc7bdvWFSqqjN23mLPge+gVSvwAnCMTr7iotiJPyi9QjvI2Y+5hCq7tXulJtBLf615eoFP1Vssw+GVB94U8pxzlbcKd/VKhO3Tti7vNdb6wfxLoDFl+FBgZJZDnOR772Mfi4osvxqmnnirO4Te/+c14zGMeI74Bx+FH6vDQFp2XpkjcWp0baYIu9kaFblmhHVHe7taau3w/8NDLqtWdP6OWdM0gXTaCiVm8tmLf6qmlpsyKVVt/igJ5kYnBh0pAynbwvigQ1j4B9iK2SF6V0qXrYLjPyNtkYcjyo0ADDrwHRxzHuOaaa3DPPffgsssuwxe/+EW8+tWvxle+8hVn7rEGzUG6CTqdqoRmFva5rfsLcJzPKWfbXq2VFPvcMgFL17NhspJOcGO5CEZ/VDoWnxEsDTAAsz1jJyvQKXIUVYFM6Uzb3GTc8p7jfE45yttkcWEJuw9SdreRt8nuIcuPAiNzEiDHHXec7P4dzTHR5TkTrnTzlToUdLVaaF8zdMqplu3oIDpTaetneWZ/NWpprYqohyRiQhYjiJpR78hjqQXFbl09tLwAWZHD93wxYQUFQy1zSR/upT1sjdoib5PdC9lQ5Tebcsjyo8BIKQFHs2D0TG4cw1KRwYSA1sli1Aas2s/nlKO8XRu7Arsasvia7nqmcxfq0tLaaUz/BZOwtLx1qKjYMyDNUPghlpdX4CclaPWJQxZh62EmSFCkGaqp2PrxpVcNV36zifp6CR+s/LjhlIDjEGvd66JrUpLB1GXg97peRKWapM9ibTwx2H2zpU5N4CH2ub3WC5Aud6GVAF8thjVFIdgGzXZdGz1prWBX8gy+8rG0oBAkXfQU0GLrzhRQUQ9VkZksPdsZw8OVt20P9zF+OCXgGBgx/cgRgGUjTG9eLkymuJknbccUAikkZ788M3f9sR9gJc2RVx4CVaIdhaslDZgf0Ml9RL7CdMLs2wYoAZa2ZoJVt0QVrGB5RWfepqbURca4y6kVKXwnetfynFkiYpjym01smshvRH7ccErAMfiHJ2S8uif17GNdvUz3EaY5xaz3PCl0igpTTMjiVts6StcxChSWlwoUWYleLlUiECqFmdkIoU7FQhNgDkC3m0pJZpVAagb5LVN7R+n7NAe8lIoiFXmbbPSvtzxduBBRpwQchwA3+iwYV3QZ/cMEsQp+EOjIGumEqOvbq7JA0E6sV+XUpimgm+ayk17p9FAFgXQZY5ljX4rxR0h8oB0n1s1XpCwL3NNZBqsrTHnAfTT/LAOdCpjiSSAFtnhAp4TIUd4mPW+48ptNPmT5UcCdBByH2EvAk8xtQnNQodgyUMfd0xwkDuIgEDnb5hUJBWUlyKVUJ4r1CniMBuJOmlatvEBP9dAKPWydpRKwrwW6WYbeSoW8CyxUwO4SiFlugbkC5tWiSSWFyFHeJp37hivv2HycEnAcmk/AOFTZ/jxi1dDAX1UCLNvM+vwBPQIm+sboCyvQCbzcy7G03EPlhQgYu8QSEtIAWdzYSNMSea/Acq+N+Va0quBswazrbgHsWgK8DsCeJrOmFAN3pVz/4/v0SWZ2q5a3yXI6XHnH5uOUgOOQYMPwJI50GGihE650bX5aVkJEIRukK5GzTVUV2LXURaU8tFsRKuY4ME+A9Y3oww4CxFEkTljKHTcXWw8K7JW51NhhGYa41DV5cvPqGKfmTKlPBFsXtLxNXJOW0cMpAcfASEgoTwKyk/YQhyzBoBWBpA6YrDE2QafPwHYp6W6aYfdiD0mkewgw67ZuMlNK3X6FVgJJGKNc98j2HrWqbJD3uqIE7mGtnX3IrJhyBkcuaHmbuIJso4dTAo6BkaYxtPUHvnTlKivdX7hu4ygJWQxxVD5UoTOLbSI1dyQbWBcuS/NUegekxpHtqRJVN2RUqyS32T+7AGmWiwIgtaGnXuaLdeP3GHmbbFQF2VVZDuKUgGNguKhHEX0AeqfPOHsa1+u4e1l2Q5pTlMjZVgI0SdFxnWZd9NgFLc/gBbGUYChYQK7MsFL5aEEhiIJGmLAWO+keJZj3Rj2+YuRtstG+fa7Pn32cEnAcWvJV4KNTFuixnHTGkma+mFdiMa9UiGMPrchHzAghy9FBTGUQv8ByB0lrSlobMgtXKnLyNMBQVq/Crl4HR85PmcbtdinLTOz9B0Nm5G2y0Ra8Y9iyd+RwSsAxMLW5Z6Wn4+5VUcILdElp9jtnrf5CWh+WmG1F1k8C/NsLlFjOU3hxItVCoQo5CdAnwKSGKNDPtyARedsUNLMdpGxp5G2y0YhPFyFqH6cEHIcE+wmwBj+byTDEsvYH6AoRnsTf8znlEuk3Zg9pG8+df15gMU3hZxnCVijzFXNWlqGLAHmuTwgNqCSNKk2HKu9wOCXgGBju8LtZwaV/1RHMjl2BqSLKAmwyzsYyWSGNWkKLZUTFMcyQynYbpechLQuUeYZuCbRpKioLJCwn3W6LnH2PALuHmZrcG5J3OA4epwQcA8PKoMtZIQlVrBRaMAqI65UpvcMx1umhaYhyc2VotZQ0I2eyNMdUGCBFgC7LNBeFVBEVH3BVie+CHakpZzvShvRCzqa3QXmH4+BpQkUvx4jCDNxOT1us672qNJGp+w/3jVOO8jaJ2DtAVeK41goqEJ8GHda6I5pWZtK8XVUib5sg7w1V3uFwJwHH4HgKRVUhrHzpy8umMbV9XZrNs3y0FJnWcqulRS3B3T6V073Li4haM+LDiMIYLdNPIC9LLPZS5L1lHHPEvD4dWKazMlx5h8MpAcfgSBMTheVuhjCKZOWng1gadEkZ6QqF8lDkufQdtm1kT8JA/BaMZPJZLqJk5BL78kJKR6iylHE+l1aTDYgR7VbDlXc4nBJwDAw7inFxX+oUaPn0rOp04aoOuZT7Cr20xNZZFmOza31kVBAnl3haAbCMRKACdBXQZkhrlqEdlfKcciJvme7KcOUdDqcEHIcEG7aDPXB7JbwqRRBGqxnDZZFD+Yk8jxrgsJQ2mLT/RzEQ6eQ1NpQnLCUhvoGIu/9Yy1lWWqPYpMUxejgl4BgYCQn1PLTaCdKixOJiF7mXSunjdghEqsLclgiJNGjRsjYpWA+I5pKq0vWBshQRzVf0bQf6nuNVVZnOXfadAhsN+3dpAo6N4pSAY2DYH8CDh163h93s2q4qhGGMNksGBUCZ93DfUootLR9bpmet9xiWstGKrTBDLGYplnpMGO5Kw/kuC8gVQJKlmAtDkZMeybbZaO6XyxVzbBCnBBwDQ/NJLy+w1C3RjmPdVD6KkAdibUHJjX8QYambYQuzcG13FjM1gm79xT0ok0RaX8bTIZKC/ZKZG1BgV6eD3WmKR2w/3nYwk7CrO1x5h8O+0dMxsmR5jsVOT/oJtNuhmFHSLMNKlsmV9xznc8pR3iqej6VCm6siP0QQr5W9ln7JdBX4oTynnDQdsEyeDlfe4XAnAcfgqApFwTLRAXYv9dDt0icQSFVONhCPVIncCzEVBSKnDfL2yPIesrQnhfgLOrO7dGDrAnKsvsY+vn67lOeUo7xtaKoaprzD4ZSAY2Dykhm4HnYvr6DD7XSeIUzaupxlqJukUzFQIWyZnxZ5mxRliQ5rGE2xDWIBrvF0U1BpSdXTVDeb53PKUd42Gz072S904Rg1nBJwDAyLxHXSDMt5gTCMkFUKeZrrdo0l7e8KMTws5zniNBN5m4gDuKrQ7QJeXEqSGAOWlFECvM/KEioDolbViF2169TlGDZOCTgGpsxTZFkXWa+DIplGXhTwQl9n3NJaVBSy467SDrJEywMz1t7xkKUtOrle/NkNjRv9nCcaHSLK+6JSUCVEjvK22egM7M/YMWo4JeAYHM9Ht6iwWJSYjSvpy0u7P23sEgikFHxVYako0WbxOMuOVpavSEtgcTfQnoOcCJjUVpuD6BOIukB3EdJwnvK22ahByr4ByzFqOCXgGBhmBleeh6wscF+aIsxzRH5k6gYBeZ6jg1Tq9FOO8jaJk1g+8J0uELSBHqtIZDQBASpgE3qglevnoZG3jTMHOYaNUwKOganyHL00x2wUowcl9vS8yGUxjUNdkC2KFKb5PM1F3iYp213Sj8FIoN3AAoDZ1HQVY1gof6fd2jxEOcrb5rYhyzsc9gOhB2RhYQHXXnstbrrpJttTmViYVZsWmdih55M22lEE7p3pAOaV9xznc5GzHCJKH0VqdvlMDuASnyq92+ZVlnxmO/O+q+Vts9EZ2J+xY9QYSSWglMJv//Zv48lPfjLe+c532p7OxOL7bMrio0MHMH2rfiAlGdphKFfec5zPKUd5m/SyHCuLeqGcmu5rzt5nS+c47ylHedu4EFHHsBlJc9A73vEO6W972mmn2Z7KROODNfdjeGWKXSsrKLsriFpTYvvP6WjtdRCUHgI2mQ9jkbdJqUpxDHMWvY4us1P3Ha6vHOdzylHe4Rh3Ru4k8J3vfAdvf/vb8f73v996VcpJxw99abwShr5EAXXzDJ00ldo7vPKe46GRo7xNWMCOUZ+7WGMnBxZNvbX6tWjG+ZxytgveORyHg5E6CSwtLeGFL3whLr/8chx77LEH9d+kaSqvmsVFftUdmwFNPCGLyBUF4tY0puIIIV8KiJl8hUIKyvV6KyJHeZso5Ymtv8PoVjNGZzBJ+8wvndonwCYDlpFIqw3KOxxjexJ46Utfiqc//en4zd/8zYP+b3bs2IH5+fnV1/bt24c6x4mCiVVQiLwAURDIAsSewnlZmd7CrCYayHPpPmx5Z62yTBZ5mn32VWctNc9zI2+bjb5j7uziGFsl8KlPfQqf/vSncd5550lUEF8rKyv4+c9/Lj/vi0suuUQiierXzp07D+u8x5mKrdqVh5lWjKoopITESk9XEeWV9xznc8pR3ialV8kuX89979TjHSPvcIw7I2MOKopCHMFveMMbVsfuuOMOdDodUQRf+tKXEAT3jz5JkkRejs2HLWWqwEeXSWFKmgojDgOUFRD7rNpZYaUooLxK5ChvkxUWhTM/76s+aD0uEUJMeHA4xpyRUQI8AfDVz6Mf/Wg85SlPwWWXXWZtXpOMqpQ0a08LhSQJkAURCkYF0QzEnr1BJA7hNNVN3SlvE6qhrO+Dv7clvh7PjLzDMe6MjDnI0TyqMkdapMiLHqQ0kMfevQr0APDKe47zOeUob5PFlQ6Wzc/72uPX48tG3uEYd0bmJLA3zjjjDJx00km2pzG5eB6KokJWeQiqAisswlPlUnahpGWuKBFXhTynnNRttsh8K0EI7Rw+mC8G5R2OcWeklQBzBRz2YP+AEh46vQ5WWICnVIhaAZgYzCqieapwz3IHXt5FOT8t8jZh45uDdfVKprOzBjkmgJFWAg67BJ5CWeTwgghBHKK3DFTdrtTrrwI5FKA1y97DkchR3iZTG4ij94y8wzHuOCXgGJheL8NSrwcfJYJKyeLP4vzsJ1Dx5xIyzh8oR3mb9Mpi1TF8IKSEROmigxzjj3MMOwYmiUJEYYClpQpddhWTkFwfScuXK+85zueUo7xNcqgNmYMo73CMO+4k4BgY9hIuMgVWVyjZW6DLhbNCwXLMHOsC/lQuzylHeZt0FnpDlXc4JkYJfOITn9jnMyZmMWLn1FNPPZR5OUYAX5XwfIaFAllWYnkZUjeI0UFRABQrQDhbIlAwcnarcnay4co7Rg9/g32Zx9F0MpASeMlLXoJdu1hrEYhj3YIvM3VWpqenpZzDr/zKr+Azn/kMjjrqqM2cr6NJMCCoqNDtAUFL+wGoENhKmFfe06ye9bScdevKRj/t7pw89syyQdUG5ceNgRTb6173Opx11lm4/vrr0ROHXw/f//73ceaZZ+LNb34zfvrTn6LdbuM//af/tPkzdjSGwvfQQY40B1g1gm5U9u1l0VZeec9xPqcc5W3CfsLDlHeM/wLoY/wY6HdiKecPfOADOP3006WmP1+PfOQj8cEPflCePeQhD8F73/teXHPNNZs/Y0dj8PIcXqpQpEBnmX4BIPKBINRX3nOczylHeZvQVDVMecfoUQxZfhQY6MB76623yk5/PVNTU/KMPPCBD5Tibo7xpZeXWEghjl8/gnQUW1yClIpIqQSUHmc9IcpR3iYr3eHKO0aPYsjyY3sSoL3/Fa94xapfgNxzzz142cteJs/IP//zP+NJT3rS5s3U0ThYGrpKgbIEFHf73FUwWzjUV2mIYp5TznYpaSqnYco7Ro9syPJjexK48sor8bznPQ/HH388HvzgB0vj91tuuQUnnngirrrqKpH5yU9+Im0gHeNLVenSzJ0eoGK96CdtICi1EshT5glAHMeFkbdJpxquvGP0SEzviI3IjxsDKYGHP/zh+OEPf4jPfe5z+NGPfiQ+AY4985nPXK3p/8d//MebPVdHw+AOP18GWi1gZgr4xSKwuACkCkg8HQzEcZVpOcrbpKWGK+8YPbZtUAlQftwYOAiOi/1v/MZvyMsxmXiqgpcAnUXAW9F9BGZiHR7KZLHlFFhe0SeFuVktb5PZmeHKO0aPYMjyY60Ebr75Znzzm9/Evffeu9c8Asf4E0YRwhCIAzZll1JB6KXa9MMPFu85zueUo7xNkpnhyjtGj7khy4+tEmB46MUXX4y5uTls3br1fs+dEpgMSk/b/mnmkUxhJg+aDExaUiQglMrB+Agob5OoHK68Y/S4b8jyY6sE/ut//a9417ve5Rb7CWc68NHf1jk04Wb1q//DRTnK2+S+5eHKO0aPrQB2blB+3BhICTA09Pd+7/c2fzaOkaJbKrAckCz67B9gdv91ShjvpcEMDwSllreJqx3kWE+xwbfE5Qn0tXVkmQjHZNOOQnEMc5Vnvxgu9owKCs2V99JHhs8TLW+T3u7hyjtGj+khy48CA30rn/vc5+Kiiy7Cf/kv/wUnn3yyhIj285SnPGWz5udoMN00h8dSEbT3VzqRhhVDa18A7znO55SjvE1cnoDjUEM+t43hWziQEqgLw734xS/e63MmjznGn8D3pGw0s8SC2uzT5xjmfWAcwpSjvFU2+rF0H+OxZ2ZqY4kCIj9mDKQEcsuFwBzNQEFJlvBCBszS8Wu+JNQL9Bcvd/hZAZYy4Ggjb5OWP1x5x+gx45TAYEogZNC3Y+IpKyVlo1u0lc4ARRfISl1zJ/T1h4vjeVeXl6a8TZaz4co7Ro9iyPKjwEGv5p/+9Kfl+pznPGf1531BGcf4o9gxxtvTJ5AUupmMCvb0CVBO5C2yhR1BVjYo7xhr5nh8vWeD8pOqBM4//3y5soFM/fO+oIxj/FF+INnASaIbsMjGuQRS+gVKfc9xPpesYsaLWiQthyvvGD06xXDlx0oJ9C/sbpF3kIBmwQhY6gBRohf/qM8xzPuUxeNSYMs2I2+Rbe3hyjtGjyPaw5UfBQZyfbF89CDPHONFDAWfDWRYZ73UpaSpAPqvHOdzylHeJkvpcOUdo0cVDFd+bJUAewfsjaIocPvttx/qnBwjQqWUhH5yraS5hws/X7Si1D9znM8pR3mbtJLhyjtGj3CDh9NxjInZ0K/E/gF7+5lUVYWvf/3rOOmkkzZvdo5GozxPPkCRWeTrJb7eLEkRuVI/D428TVztIMd6yg3a+C3HNthXAv1RP+sjgKIoElOQ6yY2OXSzHF2zyPPLIdFBfbWDJDqo0M8pR3mbSAmLIco7Ro8gHK78KLChX4nmHnLsscfizjvvHNacHCNCVZRIe0DMnAA2k+lpBZD12RrbLaDIIHKUt8nS4nDlHaNHsEGDuOVCuENhIL3mFICDKFTSK2C5AuaUzhhm4hgVAXf/jCdjfhift8VcZLlp70b/etdjePzxhiw/Ahzy4YYlJMp1zWNbbDrrGHtCP5BWklzsZ+taQUwKU/rKZ7So8Lm0nLScJ7CghivvGD3ieLjyo8BAh5vl5WW88pWvxPHHH48kSdBut/d4DZubbroJP/jBD2QeDnsoLvQsHkcTUAHwX2NZAUvmumzG+ZxylLfJypDlHaNHKxqu/NgqgUsuuUQiga644gqpGPqFL3wBb3rTmzA/P48///M/x7D41Kc+hV/6pV/CM5/5TLzwhS/EMcccgz/7sz8b2t/n2D++58FvGRNQCdCETgXQf+U4n1OO8jbZqEfCJQyPP8lUMlT5sTUHXXXVVfj85z8vCzJ52tOehrPPPhunnXaaKIP/7//7/zAM6Iu4+uqrccIJJ8j9//2//xdPf/rT8aQnPUn+fsfhxfMDtALtA/DNoimJYyY8tD9fgHKUt8lG//YxzAtyrGM2iTGDVE6tB2LGyI8bA50EmBB2yimnyM+zs7PYvVu3YOKCPMyOY+xfUCsActZZZ0lFU5egZu/Dw52+mH3MWB0E2h8mumzkbAdWbPTrO35fd8d6wig+aF+vZ+THjYFOAjQB+b7+Sj/sYQ+TqqLsOfzlL38ZRxxxBIYJFc4NN9yAxcVFvO9978OjHvUoPP/5z9+nfJqm8qrhf+fYHFgVNO1q27nX94HK+6585/mccrariB7lbyziR+QdY01Bp9UQ5cdWCTzoQQ9a/fk1r3kNfud3fgdveMMbpJzEG9/4RgyTf/3Xf8VrX/ta3HPPPbj77rvxl3/5l5iZ4UFt7+zYsQOXXnrpUOc0qWRFhV5X11iv10vJDO5TAhznc8pR3iYthjAtbFDeMeZU4rNaMhuZvQWE1eOtMY0bHkgJ3Hzzzas/X3DBBWIa+uY3v4mHP/zh+LVf+zUMk8c//vG49tpr5ed/+qd/wjOe8QxMT0/jwgsv3KcT+1WvetUeJ4Ht27cPdY6TQidL5cvj9ykBfmGkwby5r58tGXmbsP/xMOUdekHZyF7ZdgJuESdIsCT2/tY+WgtsM2HOiZEfNwY68P7FX/zFHvePfOQjcfHFFw9dAayHDe0f97jH4bOf/ew+ZRjCOjc3t8fLsTn00h66AKb6Fv7QOFTDPoXA510jb5O8N1x5h3aeDlN+s5kJAlncGfmZmM9s29y3zX3/c8qPGwMpgde//vWrJSQOFyxQt76PARPVbr31VmzbRl3tONxUZr/PrwWzhWfNF6VtrrNmPFgnbws/Hq68Q/97bwTbjbpavoe26YLnGaW0te81U5dE5+c60PLjxkBKgM7Yr33tazic0Ln7y7/8y7jsssskPPVjH/sYnvWsZ6HT6eDlL3/5YZ2LQxMFgez4K/NBivbyqn2xUm3U8i6qlw9X3rFx845tc9DMli3YtkVvXLa01zYt9WvajPM55Sg/bgz0b/CCF7xAkrX+9E//FI94xCMQr8ulpplms2EmMhf/d7/73ZIrQD/AU5/6VHz0ox91JwFLTCWR7PY7xgm8bHID6tpBNAHVX6pZI28Tdjgbprxj47tK2wFYHjzMbAVmdwG1y2raAzIFxB6wW+lxfn4pR/lxYyAlwMWf/Mmf/Mk+Q0iHActUvPnNbx7Kn+3YOFPtaRy5Bdi1Wx+X+xPF6oiKzHzIKEd5m2zUgDl+wYDDhwHiN21Q3iZR4GGm5eHEYxQ6GdC5D8iV3siwlDg/u0fMA1MxRI7y48ZASoC2eIdjqtXC7Fagu3vN7s8zYdp37ZjTAeUob5NR26WOIqP2Hld+CM8P0ZrK0d7iI1uo4CdAr6L9H6hSYNvRPlRWiRzlx42BfiNm6Tocoe8hqLQC4PK+2BcSWn+5OU53PuUob5ONWnecNWj8HcPTUYht7RZ2784Rej62bK0QzQBMaQl9IF8GPM9HWVYiR/lxY/x+I8dhI00zdHo6BHTWB5a4ezIKoPYSzfu6yTzlKG+TjXokxrBg5NBhT+mNVN4TeYuoCvDDAFzbK1bEjQEv0psWz9f3rH7L55Sj/Lhh+zTmGGGysgCbhVEJMIeGzrMtJrSO11kzzueUo7zV+Q5Z3gHMxMOV32yiJEIrjuBHHubbU9IJrx35CCNfrrznOJ9TjvLjhjsJOAZmuSjQSfklATzulIwzVZxqZoeRhEDchshR3iajlsg0irB50DDlNxulFOIgxHw7QeH70jQmSBI5vdIcVFZdwPflOeWGFfRiE6cEHAPjFSWqkr2D9arPS20N4KmZ99J0zjynvE1GsZ/ABmveWT/ab+Ux8I4NylukqhSU8nDk9AxSz8fuXgDlebKRYSBQGAXY0oqRKCoAT+QnVgl84hOfOOg/9Pzzzx90Po4RIg4Cqa9zd77m4JMuYn1Zwt0cWMmB43gisJwsFmxwRW1CU/FpU3dpI/I2KcPhym82IRMeI6YMB5iOE1TsFxBFiEudIcyjynTSQpGlIkf5ceOg/wle8pKX7HG/a9cuudaJYlmmLags4eCUwGQQJzHCCNjVBcJch4OS3Ky1vJ/OAX5Stkda3iYbdeo1wQmYbFAJ2C5vFlfDld9sFOfg+fBRIedJlY2PGDaKOsytlPEAlciN3zlgA6dHlm6uX6973evwhCc8Adddd53U8+GLP3PMtXucHEIT3cFFf7dZ9MUEZK4dM54bOdu2x1FsKr7RRd22ElDhcOU3myQMkCQh8rJCSXu/ohnIlwWfV95znM8pR/lxY6AD7+WXX44Pf/jDePSjHw3P8+TFnznGZ47JIC0rpNVawTgZM3kBdYx9XVCOcpS3SZAMV34YjFpE00aTwi0nkYNFDQPlGQexD48jqkRWlXLlPcf5nHK2iyAOg4H0MCt3spbPejjGZ47JICsKZD1g3iSF0WwxZRRAvX4yTJRBdZSjvE2Sarjyw2Cj5gfb5orYH678ZuMzYIGVROMYGSqkZYGqyLHCj6qiNahAgkqeU24Mi4gOdhJgY5eXvexlYhqq4c8co0nIMRnkeQbmf0koaKSVARf9OXOdN+N8TjnK22Sja3oDdMDIlWHYaGkd26V4yqqSf+iyzNHJCgSBj6kowVySyJX3HOdzkaP8mDHQSeDKK6/E8573PDzgAQ/Agx/8YDkqsbXkQx/6UFx11VWbP0tHI1HwULDaokkKC/I9i8cFZjzOIXKUt0nQNg2PNyJvmVHLcp6ZGq78ZqOUh06eI0eAbVNTyBnuFkQISiCRetKziJIprHQ7Ikf5cWMgJcDm8mz2zpLO//Iv/yJjLCnNVo91A3rH+BNHIaYT4O4UiHraF9A2jmF+VXjPPkC8Hk1lYLnuSroyXPlhMGqOYX+2bYqIb0TeHmWZIytzMUslQYgwihEEkZSJSDygZH2sIETuM+M91yeCMWPgbyUXezZ14csxmSRhhOkZXWlxudCRQDws0+gTm4Jy7UKPUY7yNmEdmA2sT1reMhutu2q3TiuwJY4wh6782x+IOSNvEwUF5n/NJi2x+Zeeh0wpMIYhY+0gz4Pve/I8V6XIjxsDb9t37tyJt73tbeIHqPnCF77gykxPEEkSoxXpnX4dGiq9hM21DhXlPeUob5O5+eHKD4NR82PMxpHUjToYpL6UZSUAhAiDGJUy7WKqChGdxSwax4FKxwPxOeXsBzo3RAl8/etfx6mnnopPfvKTeM973rM6/pnPfAZXXHHFZs7P0WBY98ULdDRQbQJq9b08M87nlLNdJ4adooYpPww2aiyx7caIpmdW58DggL1Rj0tDdx4RLRKFPmaiiOWBkJalOH7pv+KGn1fec5zPKUf5ccMftLPYjh078NWvfnWP8YsvvljaPzomg6IqkXd1qQK+psw+qX7xvn5GOcrbhD6/YcoPg1EzB7X8QHrx0jdRv33RuivH+ZxylLdJ6HuYin14qpJ+AhWVQKHzBHjlPcf5nHK2e2IMg4HONt/73vfw2c9+Vn5moljNiSeeiBtvvHHzZudoNJ0sk3hqLvJtloxO9SIkUUHmJMBxHgUoR3mb5OFw5YfB3JDlN5teWUrY54NNz2m+aldqfaWVjft/ylHeJlEUod2OkO8GWoGPnIqACbDMEfD48hEFPnoF86AikR83BjoJJEmCe++9937j119/PY4++ujNmJdjBCjyEnkPmKW932zoir4X4TifU47yNhm1GHay0eAZy8E2SKIIYczug8A8w4bNSdA3V95znM8pR3mreDpRLAB7DOey8LeTGNNJLFfec5zPKSfOgjFjICXAHIFLLrkEaZqungR++MMf4sUvfjHOO++8zZ6jo6EUqKTeVpoDvXytj0BgrrznOJ9TjvI2oUlqmPLDYKMmc8smdp2BGwD3FiwqCRwL4IQAONnXV95znM/FT2R5TVWVktpAR0zPYH4qQcTuYaiknSSvvOc4n1OO8uPGQErgrW99K372s59JxVDazLZv347TTjsNs7OzeOMb37j5s3Q0khk231A6/0qVZtHve+VmnM8pR3mr8z1iuPLDYHp2uPKbjZRaLrU5cOsW7RdiNVaGXPI6ZcYlTqw08hYpyhJpt5Cd/7apNubaCWbiAO04kCvvOc7nlKP8uDGQ1XPr1q34yle+gmuuuQbf/va3RRE85jGPccliE4YqFavuSg+RIyq98E/3fbAWWHK8Amg4fECo5W3SiocrPxQ2ulO2vLPO81z6MPBzUFdYiKRDl7myCVFlTENs5J7bTb7yTAs8xZOJopO4LcfWVqjnK12TpMCc7jk8htagwZQAS0XcfPPNOOecc+S1t2eO8WdmKgEr63J/T8su90hMEsr77nnlc8pR3iaJP1z5YdAOhyu/2fhhCD8BZuZ043ZZ4ss9r1xI+ZxylLeJotZUnvS/jnxmDEcIwhARG9BTaRUFuHfJyxItdhezrWWHwED/AqwTtDeKosDtt99+qHNyjAj3dXrI+GUx5h+YnADu92vrP8f5nHKUt0mUDFd+GGx0n2y7qEHOpCvumqU6p+kyR39Qqa88CciOmjJcXC3X4gl8D1HoofADxHEgp1XWQpNUAUYISdkIjgciR/mJVgKf+9zn9vozoUmISWQnnXTS5s3O0WgSfiHUWliojPWVjeiZk4BsqJWRt8hKNlz5YcBY+mHKbzbTdPYGQK8LTG3RCWFTLBmSs3YU0FnQkUGdZcDfpuVt4kkNLHOclaqi7C6mlZWkMFQl/CBEO/FFbvxUwAaVwHOe85y9/kwYP0tT0Nvf/vbNm52j0dzb7WFpeS1JKerLD6jNQRynY5hylLfJqCVekZXOcOU3G5pLfC6gVPq6Xa8EB8jOutT3HO9Jrf4GVJYNWAQxRlHkZvevTwLUBZWcWJQ+ufiUi0R+3NjQb0RzDzn22GNx5513DmtOjhGhBSULfWUWfb7qr3StCCLzXCsEu47hjRYFbUARUcxPDVd+s+EiyRLcNEulKdcMIKSvlf/0vr7nOJ9Tzvai6vs+ptsRFlcyMI2FfoCAO34f4AGhzEsUJbuOKZEbxyrJA/0LOAXgIBn7sppewvwgqXUlAjLjKObzLUbeJlvi4coPg1SqmKkNytuDJv5WFGCmVSLLdcIdd/4swRHSUexBxmdaWs52eX7f15/ddhIiUh7ytERFsyU/2FQEUYgoCRF6SuTGUAcMlifw85//HO94xzvuN86xO+5gwKBjEoiSZHXx5wepaxb8euHvmnE+D428TTZqjbJsvRLmNlhbZ6Pym01eVOhmJea3Ascd5yNu6eSwbqqvvOc4n1OO8rbxAu0gnmlH8pprh5iZCvXVjPE55caRgZTAK17xCjzoQQ+63zjHXvnKV27GvBwjQKAqiaXmIl+boiVBrC9KpVOfEHjMZraQRVpT/lDlh0GwwSzrjcpvNpFXiV+IIcGhF4JRwTRRzU7pK+85zuexkbeLB0/R6RtK7wBe45COYH3tH6ec9USMITDQp5x9A84+++z7jT/96U/H5z//+c2Yl2MU8EwSTd9XY32xsPoZ5Wxn2nR61VDlh0EyN6ezaw+C2MjbxAsi+K1Idv6dXiZhYx67yrX0lfcc53PKUd4mFctAeB6mWeTK0yeCMNBF43iVkFAP5rmn5ceMgZRAu93ea0LYTTfdhJhFloZIWZb40Y9+hJ/85CerjmqHHUK244vXQkIJlyCWr6mXIo7zuRQVs+wELLPhyg8DvwK2HaTsNiNvkzhOcESSSIkIbWYxNYL8Pe/5nHKUt4nHKGelZKc/34rQikNEogg8ufKe43xOuXHMGB5ICTz3uc/FH/7hH+6hCKgAOMZnw+JNb3qTNLd//vOfj1//9V+XkNRPf/rTQ/v7HPsnrwqUqXb6Mh6cJlPuk4q+RvMc53PKUd4mzGAdpvwwSOLwoA08lZG3ic/6CyayJvACSbhL4gBJEsiV9zLOD4dv5C3jezrPKQx9JFGAdhJgylx5z3E+H8M8scGVwFve8hbZkT/kIQ+RhZi+gJNPPlk0JYvLDQP+fd1uVxrb80WlwyY2F154oYtWskSVl7Kz486/tpb6fa/6XmrH+1reJqxzNEz5YcB3rPZHbt2HTD1OOfvlzTyJBNpyRIQTtm3FzDTLiXvwPU+uvOc4n+umPbbzBHxZ6GnloZO6ZFXRiu0kdb0j3nOc95Sj/LgxcAE5ZgdfffXV+O53vyvlpM8444yhFpBj6vb6CqUvfelLcemll8ocnv3sZw/l73XsmzBJ4DEZKNV1dmZMlci6dhC/3hxfoWkg0vI2afnDlR8Gc3Ek7RglPNGMSV2zdVc+nzXyVglCJO0pzFUBgijELGvyRwmSSn8WqjyV8bnWFBJ2HLKefOUhDgOkeYkeNylVAc8PwKAldpJUkkEcIqYjm97sMXQMD/wvwMX+Wc96lrxs8a1vfUuuPJHsC/Y84KtmcZEBjI7NgK25ueZ4qf7C0B5d7/7rK8cZACJylr9ALamuVmxQ3i4rLLccAq1ibebVumthspspR3mbsNbObKuNlu/j3l4p9fiDOJHAAPZsLlWBsihx9GwbUZyIvO35Bp4n65lfVZLLwnWfta5iqX1UiQLgcy03wUqgtr2zXMSB7PDrS0oMg3vuuUdCVV/wghfglFNO2acceyHztODYfGYiHzMM+VvWC1JqPlB1mCjvKzNGOcrbZKY9hRYWV4vd7Y+WkbfNlum2mFBaC2sngdrsU18T8z5TjvI2ibwA7cCH58c4bj7CwkKBihljJds3snJoC/Pzc1B5Lu0cKW8TJcXilJibK5a8YIRQ4Elp6UjKn5uM97IE08W0c9ibTCVw/vnny7XX663+vC8oM0wWFhbwzGc+U8pX/PVf//V+ZdkB7VWvetUeJwE2wXEcOiqMEU4BxS7aU00UkNmZ8ovDe47znnKUtwkjPeifOJhP54yRt02a57Iz5WIf95l9aiWwZMaYmEc5ytuEjumZVoROL8dsFANTbVRBgKgApkLWCyoxFcVYylLMtFrWHdlEfAHKkybymefv4RNgj2GO82fKtXgsGDMO+l+gf2Ef9iK/P7iIMzKIPgJWMmU3swP1Q+bLsfmwPyzNuqXZ9YsPoK7MaBYmjvM55Wz3k/WCQJqZ3NMXurqeenzayNtmmnH35mRyRAsoe9rfUvtdYjO+q2f6+FqOu2eZhSPnp3HPwgoW0xQhPCRhSwIDaBrMy46MB54SOcrbpCy1CYg7/azQJp/IpwPY+FyqEr2sQuBRzhf5casfZF8ND6AACJPS5ufnbU9posmLDKlZlKK+MNGwLzyUSkGKifW0vE1acYxpD5hlq0vojmh1ZZ76ylh7FkalHOVtk0GBG2opv6H0+zzHQmzmfV5k20ZW5OS/geRs2E1m8iRLOMFcexqZdOTKdW8BE4oZ+4zGiRDHWo7yNlFKaYew5yMWT7BOb6z9WtxsUjGwtDTllBqpJfOgOOjf6BOf+MRB/6EHMhcNAtvQ0QnN0ND3ve99+MEPfrD67KEPfSiOOeaYTf87HfsnS3MsL+pd6txWILtv7QMljkqJJAMW74PIUd4mVeWh3Qa2mRoX/JJPmdMKlVXHXPmiHOVt44c6tv74GV3aeHcKMJG5TtDjkt/i80g3waG8TZSiZR04esuMOFd7SxWqIETPNz4Bv4XW7LQ4XXUmud3strKskGal9ApgljCVgv496gR3T3wAqtJylJ9YJfCSl7xkj/tdu3bJtc4QzlgdijupbduGogQ6nY78Y3DBp7O3n9e+9rWHxRnt2JOyqqCC2nGmd6OmMoB8sOpxXilHeZvMTrcwMw8sdHQGa7vSyqo2Y/Hrz8WJ06Qc5W3D7ltJCKQ+0NM9fPS4uUoNfE/XZqIc5e0i/9o4ar6FvPKw5Jdib++UwJQkkMWYZWSQr5BJ0/aqET2GvfXO3vW3fD7pPYYZjVPzzne+E3/7t3+L9773vXjUox4lY9///vclbv+iiy4aykRp+rn22muH8mc7BiOFbr4xHQN5T++kudevd6n8ebann4vT0rKpgr1jp2JT1TQCfNavWZfgxnFGFFOO8rah6YT+9G4GtGd09jV7odchjK0uSzID3WXgiNi+34VbgMBnGTsfrchHNdWSHr1hoZUUA4VYQjovK/ETrKXC2cJD6OkTAOdUHwFWTwKr90rkxjFPYCAPx+WXX44Pf/jDePSjHy0aki/+zDE+c0wG0jrSB+7LaC/VYy3jC6j30Bznc8rZXp5aIUsBmMilTF/7m+D0j1OO8rZh9EwS6XlRGUxPATMzwNysvvJe6jdlVAD2y0Ywo5YduLK8wEK3kCJBXPSnWoFcec9xPteduuw6WYPAl4gfnSmsu4r1w/v6GeVsz3cYDPSJufXWW6WI3Ho4xmeOyYBRFEWqbepbaEPv6IQgmiQi44CdagNLHYgc5W2i6KistFOVc6wdwquVTqkIlKl9JJtC+7s+2YFGOgeAb5+8hbyaVOF6jM8pt34RO9yIsg+AdhygW1RYWSlQ9CowcpWHFFZCmpoO0aavwxSWsztfD0noS8YwS1t4puEl3UHijBentif3lBvHZLGB/gke//jH42Uve9keJiL+zLEnPOEJmzk/R4PhgsOs//qQTDNQprRS4DXryxymnO0FKi1KpJmJZqIdvW9+q+0wzTjlKG8fH0mY4IhtXFjNeyk1bfSV9xznc8oN+JXeNGgVYFz9cjcD374o9DGVhJhqMxoolHuO8znlbCdeeQwJNfWDuMhL8xizI+CV9xznc8rZnm9jTgJXXnklnve850lFTxaQ45f7lltuEaftVVddtfmzdDSSiMf8KaC1BCx3dE/eutMYN6q8TzraNEQ5ytskz3pyKuHXmOvlNP0VfZFM9XjR06cXytum5Kz8CLMzCqmqEEeFFLYLWKwz1OU44laIhPZqP9LyFpEYes9DWgDtlo8oiRCGofgF6A8oCg+58sXHQTnbMfcelUAYIDGF4+Q0YBLGaPmR6CWTO0A5pwQMD3vYw3DDDTdIATlW9CSPeMQjhlpAztE8Ui9AwHIQIVAyqoZtBI1DuM4alv6y/EIlWt4mK1mGlSW902d1Ba7xkgBqipt5dHK3dUIW5Shvm5iVN0MfnbREECWYmy/gt9cWqapbIYhiVEUqcpS3SZYV6GUljpqLJTqILT96ebVakE0iyEIPM3OxyFG+1bKXj6G44/c9OaVkua4iSoOQtEyVMFaeDth5TJ8C1kJHx4eRLiDnsEuL34jChFiye1S2Z8awKAFmFFMzFEbeMnU1a26cxRzE3bT5Ykc6Z2gPOdtw98kdf1GU2DY7jW5VyKLfVUCbJXnCDO32NHbd1xE5ytvE8xQKpTDVipEXCplXyaKalVrhclFlg5Yo9NDLC5G3O1+YpDBfTgE0VfFjWitZPg+DQHwB7Co2bgqADLxt37lzJ972treJH6C/7SSTuhwTgon7z8TTqk0rDBeYMVfec1ye98nbQpVKnJGcBSuf5KudpfQ1N+N8LoEstGFYhuGWzKyNAhZgoEObO9U+xzYLmsl8dQYu5W3CRZSLP3fUUaQXfCZiMTKIV1EAkW/q9CuRt41nuotxoacSlfnG+ipK2NchouOoAAZWAuwlcOqpp+KTn/wk3vOe96yOf+Yzn8EVV1yxmfNzNJggSSQyJa8byRsHsPRqpd3ajPM55Shvk/ZUgrowKGvDcP2hSYhhrLxKUTazhlKO8rYJwgBHTM3gyOkpdPNUF5SrmJ+h5Mp7jvM55ShvE2nLGHrIikpeXOwZcVVHXvG+fkY5ytvEo1+CvYMPoO/5XPsLxk8TDKQE/vRP/1Sydr/61a/uMc5OX+9+97s3a26OhkOnGeuVSTXL7lpBtvp7kplxUQ4Svmj3JBCHocTV19VNOc12i03E9ZX3dTVUylHeNpViWGKI2XYbW1stTLNVI0MVGbES+nLPcT6nHOVtwn97+iVoEVjp0T9QIM0rpEUlV95znM8p14Q11fd1CWlWCS1KvhSKiqcUvioZ5/NxDA8lA33Kv/e97+Gzn/2s/NyvGU888UTceOONmzc7R6PJ8wJ5BsyzTDSTxlJguTAnA5be5WLKZjI8LWRa3ibtKJYoJdrSueh3Otr2S6dl7QvgeNHV0UyUtw1PUh6jgsIYc9MJ2shRhSHajL5heG4SYn5uDr00FTnLLRvg+wHCwEc3VxIUUJZMwFpzDNN8xVNiN1PYMkMFZz8hb9IZSAmwNPO9996LGaYs9nH99dfj6KOP3qy5ORqObAC4iJZA0gaml9fKRdSVRRlymbIsp0Ta2d1JsbRZFHnYOq90u0tjptK7PH3PhKat87x6Im8bFi7j4hl7lYQutuOWHKt4SEkkyYFVOn15rtsh2q/Fw/IKjK9hVFDsKckNkAgxVj+VNo4sKqHLMDThJFAZkxXnua8CcmLWqrTfYNwYaN/AHAE2a2HbxvqL/cMf/hAvfvGLcd555232HB1NhTrAAzop2waafIBZvYvmlfcc53MpyGn5+0Pzzky7jakZIGkBs8zEbeusZl55z3E+p1wTzEFhFKMVJVDUWnWRY1k8zdV8hfmccpS3Cats5qrClukYM4mOq6c5heYgXnnPcT6nnO2qnEpRASjZCJC6DA4X+/pnwueUs53w2Bgl8Na3vhU/+9nPpGJoVVXSqeu0006TBi/rm8E7xhh+KRj6R7OEyRTudddevOc4n1NOtlcWoULil3uKfoCZCNOzQEKzT1tfec9xPqdcA4KDZIeaxJGEV3ZpTqPJJwgQM3mJXmxVyTifU+5ADs7DQZErSRCbbVMx+WgxdDVgLSYWj/NlnM8p1wSU7Pq9tXaTVAymjlC96Nc5AuPIQFudrVu34itf+QquueYafPvb3xZF8JjHPMYli00YsmMyJl2ahKTRSWkWW3NfhwBSzrY5KA49xIGPkKGLcYJqLtdJbCZZrAxZ8TRBVpUiR3nbBNSiqDDXbqOlPHQ7BdjtVqw+vunuNtUSswvltLw9ZPE0foxuzqggDx57CUunNm2u6ualVEClHOVtokzkUj13KY+u6migunSErhkkZbtdspjmiU98Ir72ta/hnHPOkZdjUvHFEckFiV8aiVc3dSNYg4c9ZDjO59phaTlyxffRZqlNWvuDELMzAZL2NFLutjnf7oqM8znlKG8bCajijrRSmKeJShVQno9uBLRlsQ3RbrXQ6XaMnN35ihlFAb1CJ4nJ7tlUaBbFxUW3VOiVqhEF2TyTLFZHBdVlBeuQVk6cioGhrDpEFGPHQJ9ylopYWmKLa8ckE4QeKh71aUtPTBE5acitr3UmMZ9TjvI2YQhl5EWYn57DkVMtYz7RoYC88p7jfE45ytuG7Q1jFgjyfLGpBwGzbWNMR7Fcec9xaY8YszRzA6JtfCWhoLWZhYsnC7HVcfYc53OxFTYApZhvwfOVma9v5mv8AhyX52NqDxpICbCL1wc/+MHNn41jpKjyUgqZcee3Wo7BHKHrHZO0b2XxsELL28RXCtPtBNtaMUo6A8tcWh5SN0nrwzKXcT6nHOVtI93OwhCt0EdeldL4XMbN1HjPcT6nnO0Zy799fRrx9uForZ2wujZbY6KDAnMq6fcJEI7rE63td3c4DLTV4W7j5S9/OT7+8Y9L4bi6xWTNZZddtlnzczSYKIwQMBaczl+znRDTNHeA5vvCsEXWuaEc5W3CTmFxGKHNEKBKoecHyJgUZE4wUqKBMfh+JHJN6CzG3TP9Ka12gsT30FsuUaLSVTmlXESA1kwCj+GLEu5qd1WVddPzpPSyNg0pycGgKYjWNV2UUz+vO3jZna8SxRkxwY0nqj5zkFEJ8hOfa+sQy0c0QHNtIgN9ypkj8Bu/8Rvys2siM7nkHndLejfHgpvyfa53gbQDm05ddX0eytskjELMJBHuvm8RQdzCVBghSlpIKmBaylvwC+5jJe3hmK0zIm8bKWynPPQU8wBitJIQnh+sOrNVVSL0A5RlhkgxJBONUALTrUgWft2ty5wKTHSWOFrZelKib+zPt1qNDtr3ZPhcyl+M4WFgw5/ysiwlRJQakSWlGerlmExCk5gkuzsuSCYChEV4JBKEpiKz++uXtzZfacjOPlE8vUixYJRgrL2uGyT3dUE2n71nrU5Xz4hljNsB/JQ2a72aShIbFy+dyiTjq3LW6/OzbwDrB5ly12JCYbKVThbjxDlH/qzzBmCditVBpXjc/pPF6JwfRzb0iWFJCOYD0ATEAnKnn366KxMxweRK6Z68JheAlUMZBUQ/Jq+85zifU47yNpESBpVCEgSIxDahZFOTFaVcec9xPqcc5e3jIYLe4RdFJeHY/fCe43JiEAOR7WibtaJwcehLFU6WkeACq6+BjBPK2TetKHlpY8++k8WMMWi/p4WJUAKvec1rJEfgH/7hH+Q1Pz8vY44JxYT9SYtJUzWU9fnF92fuZZyKoDa32oTZq0xdZn14mI5SdLqymXvIqBs9zuciZ32BMu8lK7Ca/Aapex94stuWa9845WxPWRq3R7pxuzJOVSoArRB0+0aOS+P2yH7jds9VEd2YOejaa6+VJLGHPOQhcn/yySfjSU960rD+fRwNpypLcfYx0q/2CTAclFsL+v1YQ4jjfE45ytskKwp5xZ6HHktfhyG8OESr1CWklQolgSmpvFVZ29A8UTI01PekFn+OCsr3dVMcLvos3ZyEKPNC5GyHMdZO37zkqYXlGNYcrZIjIGUatCOWcvZPAp4ooqrUZa91gtjanOr5Eq2wbM/XshK46667VhVArQTuvPPOYczLMQqEgdjS4yldQC7dDfRSnSfA7Ft+oViXh8lYsvxbrnVP50SnyMSxOhcl8jPt64XpMuazymiUIM9TeWY988qgzMIU0pYe0zHso1Dax8EMXN5XjLRpwPqkzUG+nK5oTisr7cuQEyM3DDRbBTy5aDnbSsAzzeQZEMB8EV0qoo4JIpLzLKeYcU0W27BXt8fWSwcYa7VYOswx7gT0BUS6MTurhfKbw4RcmiUYMpqyUQvLR7CX71Ytbz0evKqQlbpfb8SgBj+EX2c0V3S6AlnJWvdBI+LCZWOvTEglkVVIO7f1rf5Zniv7IZeE9nSafwpP7dMxLBm4DanI6RlnNhf5+5eN0NFM47j4D6wE2qy2dYAx20dSx+EhYrtAvfbIplm6hzH5iqYWlmfW9c3kOeUobxO9+ATolAWyspAY9tXdnakSWZaF7AinpK+s/bIRq4sqFyhZTHUSBgvy0e/CFYu7anozmmSp4C6fpiAu/lwOxGy4rhZPE/Bk8WdPCbV6IsC6GkF1dFBonMUTrQQ+8pGPDG8mjtHDD2R3xxywsKW/OPQByBdfB9/IeJiaXaDlBiISBhgwWoUx39zusRSATryi6VqycX2lWyQGgcjbhoslFx++p+wyXNaFzngSo+KV0Fc9TzG3NGDONXouej51stjaeHPwWSJCagSt+QTqtV71jTdt3laUwAtf+MLhzcQxcoR08CU+Qr9CybrR9A/EDAXVBeS6NAel+mQgcpYPiNz1xx7bMobwwxB5xdYma0FL3KHSRFShFDnb2beECxJNKwsrGZSvHak8zXi1M7sskZYVvKrE/HTcqJ1qXY6htrHrbGFdma1pC2pI57DM15SMMOpLmuSYOkLjisv0cgwMnZH8ljAiiCWZe5Hp1MUNtZh/dAE5CbdnxqXlBSqgAohDhGkhi31YRfDCSEpGSGljmipEORQiR3nbMCKFuQusaMAENgkRNclW4saAQqkY+srnOlS0CbAqpyiAqtTmFKO0ZKH1A9l5c+FtEr6pgLo3c9A445SAY2DEaUbncALE0z6yqUqUAZUAA4FormhznA3p+xp32IJ17VthhKmohEfHL0NEg1DMFDy5SOYtE8miSOQob5vaOT3NLl2+r7NWZTets7Fpx2bUEB3ZtbztQqL1CYAhq5mEXuqNAP1EfEvZYJ7Hwya2a/Tq5LBmTWuoOCXgGBjG0vgM82Obk8qTxuKszVbXtUmZhFvp6BUtZzfkkjv71lSEiiGsrMnPOEtTjC2WQ41COwoRhFquCScBOWz5HmbasdjVWWqhNmFJ43aT9MaG7f3VW223a+z0Mkm4i3z2GA7EFMi5MTN7OSsRFYX8Tl4DNgeTjlMCjkOAMSk+2tOAH4foVCVWOroiJ2PvWSo4SVjDnxV6uKBadgx7nlQJVW2FlYzNzj0UjA6hU5ibUy6pLHcRhyLXhMVJV4mgX8BDzr4HFfMBdDEz7vilTLc4sj3dF6EBqQ1pyvLWnjSNqfs1rNnY6ZPxpOcw5ababgmyjf2tzgDccccdkr28sLBgeyoTDXfMU0mCvAd0eqk4/ugY5omAV95znM8pR3mbhGGAqVaILCvhe5x7jC1TrdUX7znO55SjvG3qBie6y5UOc+X/QiYv8X9SA0nHtdeNUGxSFHRUU+lXEnbZ/zvUc+M4n1OO8g67jJQSYD/j888/H4961KNw1lln4brrrrM9pYlGCoJFdPhyj89esqZksMmul5o3NAIxSzTSGaJNiAmnbZ2ljpMkkuxV1t7hlfcc5/P15QPszVnb0rO8EGMa38MkDtCOArlKVAsT3PJC5GxPWQrdlazKyfDh+8fV6+QrnrgCLWf/LZ54RkoJ3HDDDbjwwgvxjW98w/ZUHHW8elGKSaLVYicubZ6QRCbuWs04f6ac7Qxc5gRwLrNToSl050FxQaKJpa4aGZrnEtpo37ZSx6yzeEES6TILktRmwhl1rR6Gumo524qrKJTs9OuqnPuCzylHeYddRsog9wd/8Adyve2222xPxVFb+D1fqoTmeb4Wc6/L3cuL49K7nXLW3zV9TGFnPNrWvZCVOH2kHpAwfNGjn0DXtVk9zjQAyV8IKmSMA1UMudS7f/pcKia7MTyUWcMNyHAOQ53cprsy7Bs+pxzlm4S6Xz8B+4p12IyUEhiENE3lVbO4uGh1PuNEWrB8gaejbfwSLMUTt9dCRFlGVOr0FFy76Ay03U8AyCsl1TjDSmGl8MXZWha64imjgdqRLmlAOctFT+/XrrGT6dOUMuUYKjrfWfoiUA1q16j7BDA/oBRjoD6t1I5h3c5RPxe5Bh0EKnO66i8gx/V/nLOFif2tw5DZsWOH9D2oX9u3b7c9pbEhCD10qxxB4mPL/BxYQkpqBpnaQbznOJ+LnOVdn+9zp69QlQW6RSVfbtrV41jb13nPcT6nHOWbQB13n7D/QRRIU/lWxJwHX+453pRG6HSmsymPnKnEP1AhzUt001KuvOc4n1OuCc53wnntz5HN5+PK2CuBSy65RKKI6tfOnTttT2lsSFk9tsjRCiuJBJLicUGMKIzlKmUNKshzyom8VXSVyE5WSfiiH4SodJ1mufKe43xOuWaYg3TlU+6gWc6YMff9TVrqe4nPb0TnHoYFB/BUiaVugaIoVnfUvPKe43xOuSYp2WA/juymKNlhMPbmoCRJ5OUYxnsbw2ND8dzDdBSiCgPJxOVxmicBFQZoRSFWUsqFIm8X/SXvpYUs+JyjRAcZ/4ZuNank+dyUODLQCEwPdHHEm7o2dUG2uub9qpxlZBFlSYgwRNvTfgzmBLDsha4u66Ed61aTnLZte7syyW0HsvbI6YWO+AbMebMZeyXgGB6lCtAOEiwi1fHeXiUlDCSUkS4Bj/1vaVgv0Q6mRd4mzAhmUTjmAORliZzlpEPtK5BTCzuJBZDnusR0E3Z+DGul76IU/4rHCCe+x1VdlK1Cxrr9THYT00ozFlWeSpjD0KaZzTdN59ldjqcaOrYr1hbSTVxsL6pK8i/2PweJynInAfvcfffd+PGPf4xf/OIXcv+DH/xAdhwnnHCCvByHl3bkYSaOsBIlyFh5p1TIVCm7PjE0SqaowkyUiBzlmxC+KAtTpctalLQFmy6SnDLDLVnyog5fbNIhUhYh8Vpq8wVDcHUYi+4p0AS4qLO0hZSyMGY2ORnSby0+A391nHK2m80r4wQ+KNl1UUPjwkidBL7zne/gTW96k/x85pln4qMf/ai8XvSiF8nLcXjxwNBFJizpfIDlLIDPKJYCoDWlqgLMtBIUvULX57fsgpIFyPewkilpfxi3dZeruvQ1d6csKNfLCky3GL7oN8snYModC5Kgp43t/B2Y06B9AnbnzPlRgdJPITkO+6jKyXEqAV1Ezt58PeOrOCjZMS0sN1JK4FnPepa8HM0gimNMxwmUF6Id0u7fgh8l0mSmzUXVo1M4xqKXihzlbcJdP1ejJNBmCOYC6ApCUpRT5zeY55QT+QYg5hUWuZPdPhd8fQqok8PouMwKLdcE9ILv7bcqp4SNNmO60G6M/Zul9HOMJU3Y6jhGFEZ/TycxjmwnKNilizZr2eXpIz7vOc7nlDtQFumw4c6eNfdZsiCOWJOfu2i9w5OwVrZxZFauH4hcE04CeqHkgqnEwcprfwhj/7iWa86iuj+asqh6prfwgcz9uueway/pcNz/iwEPW6enERUV7usG2sZOW7tkugaYT2LMSLGzA3/Rho1SbIATIC1ycawGYkv3peIpUxg4d45TWUVRKPJNgG8bbexlqePVVWHaSxpnN9/nIAwaEBza3w5Tt+ncF3XP3iYkYfl7aS+5p6N7vBPGRsoc5GgWbHMoZRfE2dpCODsLL4xX+wmoIkMUt5AWKeYYimm52wm/xLSrs4497dHdtEKRK2QlTS1UBArtRJu5WIahCV96ybBdv2uu7Vd9BxUqLu0ztqsKuIDSH9DLy/0uquLjiHS7zCYQuvaSDsfGEUcqY8KhELO1IRUBE8WY3cpsUWmDyJWK8dV1MpM9uN4wySrLM+l5QGtPzGSrgjttoCoKZNyhViVimq+8hrQ8BNDLdcRNZPoM147WugwDF11mENtWXLoHsi9lOWql1F+GQVcNMjJsNNSEN9ng2ks6HBuEYYnsejXdakvj9k4JdKtCQkRZ1ybyWZYhROS3Rc52GCMLr3E1YsOTmYTmFV3orC5zwXaSLC7H8gY6kakhPoE+G7uuKqorhvbLaEd37UOwv5hS2UozGTOh2qSypiiacdJaj2sv6XBsAMZ6x2GEXq+LrCglYmUqjlbNK2WWynioKsRhoks0WEWbVaQtI80WshD5q/1vdSITbdp1NIv9FVUXMNMF5GplsEe8+mo5aR2X35SNNXf5vil0Z1IZVk1DPB02UQFMKs4n4Bj8w8Momoh5ApGUYC7F5s8vuTZXs2k7nZZ0Coucb9cnUC+gs+1IykPwxMLdap3NyjlTAbTbkVloVWPCLdlekspKGs1TAVM58AfTg5jlGEweWbPMK+Y0NUmlmUcNpwQcA6NQgTEpMa0sXoC89GUnzcgVRtuwvIEkiSktR3mbMNpHIn54GqApi/Px2JvXlL6WzFbWD9U/NyE6qA5hlIWeWc+rDuC1nTV33bqEhP0SDOuZRPPKqOGUgGPwDw+de5IZ6iNiKQYVc/uPgE1OuAGsfIRxgCJjrwFTNMwiOrlqzcgj/XnppAzrXbW6n6xtxHwV1N3E6tOJ+SWMeYhROHxrxUfTgDk7RgunBBwDoxR3+vwIZbIisSZ/EEWrFSPLnPkCelWiHOXtotse6oW0jkzRxSz2WDtZpE0b3GGbOiM4z1lwTTtYpYqozNPMm78PFa9pP+lwbASnBByHtksNfczNtWWXmnUrlFkhhdlYKp5moKTtY6rVNicGu282d/40rfQKhalE1+Df016tI286aYWpSDuNm2IOytgER0Ju61pBes50ZtNXwCSyqTh0SsCxYZwScBwCCqHnYbYVYCmt9C7b2KwJ72mimE3qHartRvPa5h+WlSyqPK1wQa2VExdUtpuUuve0s9s/CKyWZmbI5WqkfV350jiN+W/AONemlGae9J69o4ZTAo6B8X22B/Rx71ImkUBxEmmfgEm+ok+Ai+xSr8QRs7HINyHccroVSbMTNmkvWMnSJN+yBANrBsVRZBZYWKe2+TMElAspO56J9WddyCXnKqUYGqQEJrVn76jhlIDj0OrEBLRXlwgZJCplJEJ4gYm7l3r9CgWfNyA5qPap0qTSigPkhV6gah+GLnkQrC6ozTgJ6AWfIaDaWb3vkMt6wW0CNE/treYOlRpLTbNWj+1AAYfGKQHHwLCGvZRmjjzJEGZsKKMqZdh8v7lm8TnlRN4iUn3TVIzUlUO1yYfhrHpXreXqRde20hrVkMv+nr3rkZOLUbK6l0CDf5EJwSkBxyHAapFAHMeI4wC9boWKWaLcbXNhDX20mJiV6faCtlsfEvoo8qxAqbxV239tpKJPgGWZWV00ipvx1ajNJwdT775fkdnC9ewdPZrxSXeMJDT1MOgyCT1xqHLnx0qh3P0zT0D6CZRKnlOO8k1ogs4JJib2nrvRNXu1/l1ormhCE/R6znxfi4MszdyEOU96z95RwykBx8BIQxZP17pnf+GiLl1Ac1CdzWrKN3OptR1xWRdZ4wlAMgVMyYU9K3Lq53Uilu1Ftc4IZnOe/ZVmJk2oyul69o4eTgk4BkackGwsXlaSDOZJYxPtwBRHK7Nx2cO3KGQX2wSnJedApVXbrdeHW2pfQF8vXzSvKufeSjOzhn8T7OuuZ+/o4ZSAY/APT+jL4rTcyzEVmMqRrBdkokJoY69MLfwjksh6u8b+XeqBasfvUamzUVU59x4i2gQFUDPpPXtHDacEHAMjkTW+r+3oJVu2s8mMjr4RZ6ZRAnxOOdsngfW71P1F2tQx7U1iFKpy6gxnht0qCQ7YF/yMNMWHMek4JeAYGNmFhj7aSSTRP0VRShgoq3Lq8vd0CuvuYpRrwhd+1HepoxAiOuk9e0cNpwQchwR7BYi9WprOSx0G+YLrjGEgiHwdh9+A8FC3Sz18jGrPXjWBZS6cEnAcEvx+SFEz5aGMWCnUgx9DYu+lXaOUNGjOztrtUg/ve70/v0vTqCa0zIVTAo5Dy8BlmeNSSXQKG8zr+G8dPqpDMhkdVCJu0O5vVHepo8gomK/6y1xIRotpOlGbDuWUO8ZlLpwScAyM7m6le/XWNULrXdRaJVH6B3Q5ZNuO4VHepTqGR2XChfkvL2HD6zYGEunGiKwxLXPhlIDj0ArImYwxKRRX0jHsIefCX1fl5AkhDKTccdO+QKOyS3UMv8xFxdBbNhjaR8E7nhAqz5eNw7htFMbzfOM4fCcBOQUo5BWjgioU/NLkPEJTKVQyzueUa9JJYFTRyWLGjGV+dmxO+ZPALP797y/heBPKngwLdxJwHLJJhclgdYFQ2SnxcFCbWir9PGaZ6YadBEaNUXRcNj3apqoUSqXrXu33/e2rfMoihOOEUwKOQ2x4Uonjl4dK7vz5zclLRgYZDWCyXMuKTVGakSswioxifX5ZYO+X4YxGZTh7xpklC/z+3l8jN44fX6cEHAOjTN0gfoFY4CzLSiklnRVAHjKiokKMUuoIUa5ppoum71L3Vp+/LEtjwmAZbP08CILG1ecX02CpUJaF7Km5TwhlvtxJh1JLqglKS4mC0rv/vc2n7n/A30f0QLM+wpuCUwKOgeGik5YVOmmBvNJZorT9c3HiF4YL00paIvIVklgXbasXLttwLtqRzXlygTUhog0zW/XX56eSTYtCZ2ebbmicdxICUaR7DDfBccn3lj2c85w9m0tUyludL+sfMVqsiphUaD9YwDOlRA5mbW9iKZGJVQI7d+7EXXfdhYc97GGYm5uzPZ2JpSwrLHdz3Usg9FEVnthXy9ocRGcbm7gUWm5LKwTb99qGuzr2GC7KQqKZ1tpL0qQCxMxybsAutYaKqpPm6OUKPkrp1VwvRjTFpQXQKj1MscezZcR8Ip+LDEWlG/dIUUGpKksFUWIlKxGysqyfIGLEjeWV1ddde2TTUucJ7Fle3EQNjaMGGLXooF6vh+c///k45ZRT8Lu/+7s49thj8a53vcv2tCYWfqG5OIlZxdhV2bhdIoUKbSbiOJ9TjvK24S6VJ5duVoryogKgT5tX3nOcz5tSSppvbco5ZZXufaw8ZCXNcEquvOc4n1POtrmC/9bdXoG00OHBVAD1blucrFQIoS/PKWffROjpciL0U5gNAt/Hbl7KVRdG1PPWymr8FMFInQQuvfRSfPOb38SNN96I4447DldddRXOPfdcPO5xj8PjH/9429ObOOTYT4dlCeTKk8Yy3DIxY7jgN4dKASWqooQfaHmbcMHJcr3I047OHAd+udd+H60M+DwOfDFh2d6lUnGmeYGiKFDRli5Z2v1zpslFoSoLpD7Qirmg2ftas4hgJy9WEwj3lXzF55RrFz7i2Lde9iQrSlGq/BCwUqvHmAbftBxlfSypkbV2AhsnRuok8P73vx8XX3yxKADyvOc9D6eddpqMOyxgSkT00lLMK9z51xs7bWvnolvJc8rZ/gbxC91NC1nYWfSuHpPIG5kgZJzPKVeP2VZcPXpVPd27oV9pEd7L7+L5Imd7Z62DBbRJRdp09pUXqe3/knzl6XIjtue7FuWm/SmSD2BOh7xKyx7zWW7CXCf6JPDzn/9c/ACPfexj9xjnKeC6667b53+Xpqm8ahYXF4c6z8nLFtN2VO72mHMp/+OXSfoJ6Hs+p5xtWwV9GGlVIQkDE72iwy5XQwPFMawVQVqUIs8Tg02Kgk5WhYRG9f6Ipj7DRN2HOKWfg2YYi64BfZpS0lhobz2R16JtdOhlA/Qsakc2O86FrHe7F58ATwo8HY4jI/Nb3XvvvXLdtm3bHuO8r5/tjR07dmB+fn71tX379qHPdVKQo70cmz2EEu2hnatc/HmVRTXy5bnIWT5Ky+mkgHzhmcBG6ADmol87gjnO55RrwsaPG38pzxH4EmYryksim/QiKlnZZWW6unG3bX++XOTXwm/3nuHMK+Vsz1eZU0CdLUwFoH0E+lqbAyU8d0xPAyOjBCKzvaFzuJ9ut4s4jvf5311yySVYWFhYfTGyyLE50HYaxQyp9KU372rnLhMiKvZW43SjXN0Vyyalp23o+zOt8DnlGnPYklNMuRbHuJcrn1PO9hrFxZONhMRXURiltaqwjNIqtPmNcrZDRCvJceFJiz4iry/JTSsuwnE+1yeX8VMCI2MO4g6eX9Lbb799j3Hen3DCCfv875IkkZdj8+EuqRWEKCKdNMYViLt+KRlhzEH80tOUQTnbTlY5nYjzmgv8fsw8qoJvTjO2iaIAScw+zhVm2/5eEtz0bnWpW2Km5Yu8TRi+2kpC3LecIWTNKOklcf/OYlQIM+1I5G2jTG6FTNOUE63LoZNaUdlWsMPC/tbsIJmamsKv/uqv4lOf+tTq2MrKCv7xH/8R55xzjtW5TSr8cjCmnrukVhzILppRHzw688p7jvM55Wzv+mSnnwTyPd/b0b42DfA55dafFGzRkiqslYSvcgfdb64QZzfj7r1K5GwjJ4FAfxa4mErxQJMjoK96keVzytn+TJDa9l9nZvc7husS0k1uOToxJwHyxje+URZ8mnie+MQnSo7A0UcfjRe/+MW2pzaRcBHiUZn26KkwRE47OjzQ3K6TgxgTHiGTxKAmNBX3EfPkEpg8ANml+qtOVvZHZnar+AkCfjXsKwExpQUBptvJapYzw1x5oBGbuqfQjriYJiJnW3HJYukD81ORzmfIdcYz58uDFTcILW4KGEJqGg/Z/Fz4Ug6dTnUm4fn7rB1EZUvHcBOU1kQrgSc/+cn44he/iMsvv1zyBU4//XR86EMfwszMjO2pTSSy64sCsaGzXETiBfC42zZ1bZScqRljrU8Ltr9AXB+1LyBEr6iguNVjnfi6bAQUQp5ewjqHANbhYYXZ2C3oKKHA03HsdZYzFZe856Encv11kGwgZhXJFA8wFQC5zBHSnYu9pjm3KKShqPYb2TYRetrpy2zs/fx7i/M4asJGZsKVADnzzDPl5WgCnoTVTSU6yYqnAH7LVaDDLfl/EjkUhiLXhGxLUQS+L4s8C91RAXBHKvt+n2aMsBGLf03tbG/FTBSjU1vPmYM6ukafFKi8eFKwvUbpjqK6jhQPW/x3l7yMPUIu64qia6GY1s2a4VoIbn8paZMpYDYP9j+/w2DklICjaeYgH16sw+cYoy5fmboWD3RXMe60dPSQ7ZMAF3/IKaA+EZA9nYBUDrSv3z96yBb14smFvp7S+jk3xWZdK61gtY/zWstRXYpZfxa4oDZBaRHOSaJ/+pLX6tyR+jlNhLY/v8PCKQHHwOiqm9z16eJagVSNYxE5vUvlt17CR6V6pIm+sAwX0rDSuQB1cbO1hXVtnHJNQJzATK6iOcLs/Ml6/cRFqxl+lzWltb8+zk1RWsooKMmzkN4XZq6r/Q90mQ7+LnVGfBPmvZk4JeA4ZHsqe8fQJl1/gfx1DUToGAwaskDBmFZY4K4whe5oXdFFwhiJ4zdGAdRIEpiJXKoXpvUhl03pLrZeae2rj3NTlJZX57bUnfJMLsveeky4UtIOx/2+QPqYzIYy3E3VC/2eKfeaph2nxbRS7d200kT4/tXtDyVksW9R4mLaBAUwikqL1J/V/gzh9R/VppxchoE7CTg2xalGeyrpt/8Sfm90SeHmfYP2ZVppKvszrzSNUVFa3rqTy75oysllGDgl4Dj0D9GqPXV9P9k1e6pjc9jXTrWJjIrS8kfs5LLZOCXg2BQOZE91TFZf5FFTWuGInFyGgVMCjon7wo8q9SLVH8deN2kZ50XqcOGPyMlls3FKwOEYAereB/sqa0BzRpP6Io8q3gRuZNynxuFoOHXS1d7CbOsw3brQmcOxUZwScDgajHZMaofl/uBzbSpyisCxMZwScDgaTl3vfn/U+RkOx0ZxPgHHxEaujAKreRcHI7vuvXc4DganBBybgotcGX5ZgwPKTphD07E5OCXgOGRc5MrhK2uwL8a5rIFjuDifgOOQcJErh6OsgY7+2e+/g6nk6sxvjo3ilIBjYFzkymEsa+Dtvy+ySxhzDIozBzkOCSkdfYD4Rd0Q3YWuHAqTXNbAMVycEnAMjItcObxMalkDx3BxSsAxMC5y5fAziWUNHMPF+QQcmxK5sj9c5IrD0VycEnAMjItccThGH6cEHIf2AXKRKw7HSON8Ao5D/xC5yBWHY2RxSsCxKbjIFYdjNHFKwLFpuMgVh2P0cD4Bh8PhmGCcEnA4HI4JxikBh8PhmGCcEnA4HI4JxikBh8PhmGCcEnA4HI4JZiSVwB133IFrr70WCwsLtqficDgcI81IKYFvf/vbOP/88/GoRz0KZ511Fq677jrbU3I4HI6RZqSUwA033IALL7wQ3/jGN2xPxeFwOMaCkcoY/oM/+AO53nbbbban4nA4HGPBSCmBQUjTVF41tR9hcXHR4qwcDodj86jXswP19micEvjJT36Cu+66a78yv/zLv4xWqzXw37Fjxw5ceuml9xvfvn37wH+mw+FwNJFdu3Zhfn5+dJTAxz/+cfzDP/zDfmU++tGP4gEPeMDAf8cll1yCV73qVav3u3fvxoMe9CDceuutG36zbGl4KqydO3dibm4OTcfN173H7jNx+KGF44QTTsARRxyx4f/WqhL4z//5P8trmCRJIq/1UAGMwqJaw7m6+br3130m3Hduf/i+P97RQQ6Hw+GYYMfw3XffjR//+Mf4xS9+Ifc/+MEPEIahHIP4cjgcDscYK4HvfOc7eNOb3iQ/n3nmmeIv4OtFL3qRvA4GmoZe//rX79VE1ETcfN376z4T7js3zHXCU4PEFDkcDodjLHA+AYfD4ZhgnBJwOByOCcYpAYfD4ZhgRsoxPCyWl5fx/e9/X5LIHvjAB6IpZFkmRfOmp6dxyimnYBSos8B/9Vd/daCY5cNJVVX46U9/KteTTjoJcRyj6TDZ8Wc/+xmOP/54HHvssRgV+D7feeedUgF4dnYWTeRf//VfVyMP+/OJTj/9dDSdG2+8Eb1eD7/0S7+08e+dmmB27typ/uiP/kgde+yxKooitWPHDtUUrr76anXkkUeqE088UR1xxBHqjDPOULfddptqKn//93+vzjrrLLV161YGGqilpSXVZN75zneqBz7wgeqhD32oOvnkk9VRRx2lPvzhD6umcvPNN6tzzz1X5vmYxzxGzczMqKc+9anqrrvuUk3nlltuUdu2bZPPxde+9jXVVC688EJ1zDHHqDPPPHP19dKXvlQ1meuuu06dfvrp6uijj1aPfexj1amnnqq+973vbejPaPZW7TBoz0c84hGyAzj66KPRFO6991684AUvwB/90R/Jru/nP/85pqam8G//7b9FU/nhD3+IP//zP8f73vc+jAJ8j7/1rW9J3glPL6973evw+7//+/JZaCK33HILXvrSl0quDEOlWUmXO+tXv/rVaDJFUeCiiy7CxRdfjFHgOc95jjSsql/vec970FR44j777LPxa7/2a7JGsN/K3//930vTrQ0xNBU1YjzgAQ9ozEngiiuuUK1Wa4/d9FVXXSU7qVtvvVU1mb/7u78biZPAerIsU57nqQ984ANqVPit3/otdfbZZ6smc8kll6jzzz9f/ehHPxqJk8BFF12kvvWtb6mbbrpJVVWlmv7e8gTQ6/UO6c9xPoEGwo5p9AHMzMysjj3ucY+T6/e+9z1XAXUIcHfNlJmTTz4ZTYYNlVZWVmTX9/nPf16SJZvKNddcgw9/+MPyeeYJZhT45Cc/Kafa22+/XfwB/+N//A885SlPQVPf33POOUd8AHyPt2zZIn7NjfoExkoJ8HhMB9T+4OJ61FFHoemmim3btu0xVt/zmWPzAwP+/b//93j6058uDu0mQ5Mbj/s0W11wwQVSar2J0MH6e7/3e/jQhz4klS1HQQk8//nPx3vf+15s3boVeZ7jP/yH/4Bzzz0X//Iv/4LjjjsOTYMmIFZYPu2009But2X94zrxN3/zN+KAn0glwF3SW9/61v3K/Nmf/Rl+/dd/HU0miiLx9PfT7XblOgoRLKME39fnPve5cgr427/9WzSdT3/606ubgWc+85n47d/+bfyf//N/0DRe+cpX4pGPfKR8XmlbZ+l2cv3118uO9eEPfziaxgUXXLDHd/Ad73gH/vqv/xqf+9znGumP4xw/85nP4Ctf+YpsBhhNyPa7L3zhC/GjH/1oMpXAb/7mb8pr1OGR7p//+Z/3GOPxlLhCeZsHFS0VAB1sX/ziF3HkkUdiVODu+t/9u3+HV7ziFRLi2rRwXC70XPhf+9rX7rGJufzyy6U3Bk80TafVakn59vq71zQe/OAHywmlPg1S4bKGGj/T99xzz0F/nsdKCYwLtPOxUB53TdxNEXr9+cX6lV/5FdvTGysFwC84FUCTosP2Bv0AzBfph6ZPmi6apgDI+qia//f//p/EsP/VX/0VnvCEJ6CJUUxVVe1x0v7ud78rJy6aW5rIM57xDHk/+zcBjBrj77CR3iMTrQS4O6FDkPAoxTA8Hl35xTr11FOtzevJT34ynvWsZ8nR7g1veIPsVHl9y1ve0lhzUB3KWh9Dv/a1r4mdku8j38+mcd5554n5kCGtDBHlq95dNSlhsN+8wiSrJz3pSVIp8stf/jIuu+wy/Lf/9t9sT20sWFhYEAcwfUM0VTF8/I1vfKOM/Zt/82/QRBhCfuWVV4rv5Xd+53fk5MVQ5z/5kz/Z0Dox0VVE+ab91m/91v3GuVP5y7/8S9hWUG9/+9vxpS99SXIEGGtNpdBUaD9lZMV6qLia6GxlbPXeYCw+7exN3Kn+z//5PyUiiI7sE088UY7+j33sYzFK37UrrrhCcnOayC233IJ3v/vd0qeEppSnPe1pkjsSBAGaCh3u/I4xapBzpjmcPgHP8w76z5hoJeBwOByTTvOMiQ6Hw+E4bDgl4HA4HBOMUwIOh8MxwTgl4HA4HBOMUwIOh8MxwTgl4HA4HBOMUwIOh8MxwTgl4HA0HJaNZpEwh2MYTHTZCMd4wLpKdYGyvcFevE2tCb8edjtjdvATn/jE1TFWsmRBsDPPPNPq3BzjiVMCjpHns5/9rDRgJ6ypzlIbLA7H2kWEjcJHRQmwIBjLQvQrARYNXFpasjovx/jiykY4xgrWfmfxPZYrrgvBff3rX5daKqxZ89WvflWqLlKGyoLdox796Eev/vfs0MRF+Kyzztrjz2VFVxbJ2759O84444z9Vu7c1993ww03yIuwIiyVE5uC9P8df/zHfywVTtnQhLB+DevupGm6ehKo/3xWt+R8O50OHv/4x8vv0g9PRyw0x2JinPPNN98symT97+aYbNxJwDH2sCgYq5suLi7iIQ95iFQ25aK8Y8cOWUj7lcAHPvABKdFcL5T8b84//3wphUw5XlkVlY1c9lV+el9/H//bq666SmR27dolCoLVYf/jf/yPMsa2hixiRnNQLcdS4uvNQfWfz/LSLCTHctgsJMYF/2EPe5jIcMF/6lOfKsrqoQ99qHTHosJh5ymnBBz9OCXgmAhYGZJlw7n73ggsy8vmIiwtzE5OZVlKG8JXv/rVUtVzI38flQlf/Q5fLuwcYyMhVopl31ieRA7U5YwKhacALvqsAUlz19ve9jYxJ5HXvOY10oDoC1/4gpwEeMpg85Gmd9VzHH6cEnBMBFwkN6oA2GOC/VpZy5/OZy62fNHMdKCWjvv6+1i3nmV/uXOnQpmZmZHmJVQCG4H9kOtdP01D7DNQd6Oj+env/u7v8JGPfGS1rjxPFGxC4ooGO9bjlIBjIhikUTidzLTPc8dN88r6xj8b/fs+9rGPSdMSmmfoW2BzGCqaQZqws71kP/yz6r7UnDcbpbNBTj+8v+mmmzb8dznGG6cEHBPB3pps0F7OXXM/9UJK2MmL/OEf/qF0IjvUv+/lL385/uIv/kIa19TQQbzZu3P6LPj31xFTNffdd9+m/j2O8cAlizkmFjpK6QSuoXmmNqnUiymjbmhnX79Qb7T5OHfm7Fd7yimnrI794z/+o5iH+qF5qF8RDQJDYxkNRBNWf6QQ/QMOx3rcScAxsfzu7/6uhGDSyUsTDc01NM0w4qbmv//3/46zzz5bXnTg1osp+9CypebBQqfys5/9bLziFa8QHwP7Rr/rXe9azWWoofP2gx/8IN773veKEuL8BuHNb34znvOc58jPjE5i1BOV3EbaDjomA6cEHGMFbfHsxcy+zDVMvNpbXD+dqYzG+fjHPy7hmQzVpBKgTb2GYaF8xkggNqY/6qijJGJof1E2+/r7GPFz+eWXSwkI/jnsF8w/9+STT16VYR9e5gQwF4Ax/XTork8W29ufz4We/10NncBf/OIX8b/+1/+S+TNaiGGn/TIOB3HJYg7HGEKlwVNGGOp9Hhd/mqJ4EqnzEhwO4k4CDscYcscdd+D3f//3ccEFF0iY6Ic+9CFRCC960YtsT83RMNxJwOEYU5iPQBMUHdIsYXHxxReL49nh6McpAYfD4ZhgXIiow+FwTDBOCTgcDscE45SAw+FwTDBOCTgcDscE45SAw+FwTDBOCTgcDscE45SAw+FwTDBOCTgcDscE45SAw+FwYHL5/wEZPQJG+0BzcgAAAABJRU5ErkJggg==", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "from sklearn.metrics import mean_squared_error\n", "from sklearn.metrics import mean_absolute_error\n", @@ -470,9 +1504,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 24, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "[(944, 64), (1683, 64)]" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# weights and shape\n", "weights = model.get_weights()\n", @@ -481,7 +1526,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 25, "metadata": {}, "outputs": [], "source": [ @@ -491,9 +1536,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 27, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Title for item_id=181: Return of the Jedi (1983)\n" + ] + } + ], "source": [ "item_id = 181\n", "print(f\"Title for item_id={item_id}: {indexed_items['title'][item_id]}\")" @@ -501,9 +1554,29 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 28, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Embedding vector for item_id=181\n", + "[-0.52785015 0.464275 -0.33132845 -0.47566327 0.19347334 -0.45298615\n", + " 0.33928812 -0.03706389 -0.4088814 -0.17555797 0.38225913 -0.39968315\n", + " 0.29265144 -0.0155953 0.17605668 -0.45605636 0.233777 -0.41119868\n", + " -0.01031354 0.19210331 0.10234811 0.24212372 0.34031865 -0.04571527\n", + " 0.38255188 0.40120232 -0.26605287 0.16304302 0.26158562 -0.2731512\n", + " 0.2889027 -0.23419413 0.41922078 -0.22169952 -0.26011303 0.4307433\n", + " -0.2844937 0.2925528 -0.06835906 -0.1289394 -0.42127562 0.31096235\n", + " -0.4952544 0.05832252 0.6731083 0.42020866 -0.30686066 -0.23507756\n", + " -0.30006236 -0.36499518 0.00812508 0.33057338 -0.48508546 0.25127468\n", + " 0.33890042 0.168747 0.1934448 0.13973525 -0.4676584 0.06273\n", + " 0.56887424 -0.08815414 -0.35720435 -0.40181917]\n", + "shape: (64,)\n" + ] + } + ], "source": [ "print(f\"Embedding vector for item_id={item_id}\")\n", "print(item_embeddings[item_id])\n", @@ -530,7 +1603,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 29, "metadata": { "collapsed": false }, @@ -547,9 +1620,19 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 30, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Star Wars (1977)\n", + "Return of the Jedi (1983)\n", + "Cosine similarity: 0.913\n" + ] + } + ], "source": [ "def print_similarity(item_a, item_b, item_embeddings, titles):\n", " print(titles[item_a])\n", @@ -572,27 +1655,57 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 31, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Return of the Jedi (1983)\n", + "Scream (1996)\n", + "Cosine similarity: 0.73\n" + ] + } + ], "source": [ "print_similarity(181, 288, item_embeddings, indexed_items[\"title\"])" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Return of the Jedi (1983)\n", + "Toy Story (1995)\n", + "Cosine similarity: 0.832\n" + ] + } + ], "source": [ "print_similarity(181, 1, item_embeddings, indexed_items[\"title\"])" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 33, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Return of the Jedi (1983)\n", + "Return of the Jedi (1983)\n", + "Cosine similarity: 1.0\n" + ] + } + ], "source": [ "print_similarity(181, 181, item_embeddings, indexed_items[\"title\"])" ] @@ -610,17 +1723,52 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 38, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Toy Story (1995)\n", + "Star Wars (1977)\n", + "Cosine similarity: 0.825\n", + "\n", + "Toy Story (1995)\n", + "Scream (1996)\n", + "Cosine similarity: 0.73\n", + "\n", + "Toy Story (1995)\n", + "Spanish Prisoner, The (1997)\n", + "Cosine similarity: -0.237\n" + ] + } + ], "source": [ "# Code to help you search for a movie title\n", "partial_title = \"Jedi\"\n", "indexed_items[indexed_items['title'].str.contains(partial_title)]\n", "\n", - "raise NotImplementedError(\"Please implement the next steps yourself\")" + "print_similarity(1, 50, item_embeddings, indexed_items[\"title\"])\n", + "print()\n", + "print_similarity(1, 288, item_embeddings, indexed_items[\"title\"])\n", + "\n", + "# Find the movie least similar to movie 1\n", + "movie_ids = indexed_items.index.to_numpy()\n", + "\n", + "similarities = cosine_similarity(\n", + " item_embeddings[1].reshape(1, -1),\n", + " item_embeddings[movie_ids]\n", + ").ravel()\n", + "\n", + "least_similar_id = movie_ids[similarities.argmin()]\n", + "\n", + "print()\n", + "print_similarity(\n", + " 1, least_similar_id, item_embeddings, indexed_items[\"title\"]\n", + ")" ] }, { @@ -634,9 +1782,29 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 39, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "[(np.int64(50), 'Star Wars (1977)', np.float32(1.0000001)),\n", + " (np.int64(181), 'Return of the Jedi (1983)', np.float32(0.9126321)),\n", + " (np.int64(172), 'Empire Strikes Back, The (1980)', np.float32(0.9048265)),\n", + " (np.int64(174), 'Raiders of the Lost Ark (1981)', np.float32(0.8998636)),\n", + " (np.int64(751), 'Tomorrow Never Dies (1997)', np.float32(0.8735501)),\n", + " (np.int64(480), 'North by Northwest (1959)', np.float32(0.8649571)),\n", + " (np.int64(619), 'Extreme Measures (1996)', np.float32(0.8626034)),\n", + " (np.int64(173), 'Princess Bride, The (1987)', np.float32(0.8554762)),\n", + " (np.int64(187), 'Godfather: Part II, The (1974)', np.float32(0.85195786)),\n", + " (np.int64(318), \"Schindler's List (1993)\", np.float32(0.8517903))]" + ] + }, + "execution_count": 39, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "def most_similar(item_id, item_embeddings, titles,\n", " top_n=30):\n", @@ -657,9 +1825,33 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 40, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "[(np.int64(227),\n", + " 'Star Trek VI: The Undiscovered Country (1991)',\n", + " np.float32(0.9999998)),\n", + " (np.int64(1444), 'That Darn Cat! (1965)', np.float32(0.92228276)),\n", + " (np.int64(1269), 'Love in the Afternoon (1957)', np.float32(0.8930695)),\n", + " (np.int64(566), 'Clear and Present Danger (1994)', np.float32(0.8901913)),\n", + " (np.int64(228), 'Star Trek: The Wrath of Khan (1982)', np.float32(0.8843865)),\n", + " (np.int64(609), 'Father of the Bride (1950)', np.float32(0.8823442)),\n", + " (np.int64(1063), 'Little Princess, A (1995)', np.float32(0.880399)),\n", + " (np.int64(27), 'Bad Boys (1995)', np.float32(0.8778589)),\n", + " (np.int64(1000), 'Lightning Jack (1994)', np.float32(0.87373877)),\n", + " (np.int64(429),\n", + " 'Day the Earth Stood Still, The (1951)',\n", + " np.float32(0.8716618))]" + ] + }, + "execution_count": 40, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# Find the most similar films to \"Star Trek VI: The Undiscovered Country\"\n", "most_similar(227, item_embeddings, indexed_items[\"title\"], top_n=10)" @@ -683,7 +1875,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 41, "metadata": {}, "outputs": [], "source": [ @@ -694,9 +1886,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 42, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "import matplotlib.pyplot as plt\n", "\n", @@ -708,11 +1911,9299 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 43, "metadata": { "tags": [] }, - "outputs": [], + "outputs": [ + { + "data": { + "application/vnd.plotly.v1+json": { + "data": [ + { + "customdata": [ + [ + 1, + "Toy Story (1995)", + 452 + ], + [ + 2, + "GoldenEye (1995)", + 131 + ], + [ + 3, + "Four Rooms (1995)", + 90 + ], + [ + 4, + "Get Shorty (1995)", + 209 + ], + [ + 5, + "Copycat (1995)", + 86 + ], + [ + 6, + "Shanghai Triad (Yao a yao yao dao waipo qiao) (1995)", + 26 + ], + [ + 7, + "Twelve Monkeys (1995)", + 392 + ], + [ + 8, + "Babe (1995)", + 219 + ], + [ + 9, + "Dead Man Walking (1995)", + 299 + ], + [ + 10, + "Richard III (1995)", + 89 + ], + [ + 11, + "Seven (Se7en) (1995)", + 236 + ], + [ + 12, + "Usual Suspects, The (1995)", + 267 + ], + [ + 13, + "Mighty Aphrodite (1995)", + 184 + ], + [ + 14, + "Postino, Il (1994)", + 183 + ], + [ + 15, + "Mr. Holland's Opus (1995)", + 293 + ], + [ + 16, + "French Twist (Gazon maudit) (1995)", + 39 + ], + [ + 17, + "From Dusk Till Dawn (1996)", + 92 + ], + [ + 18, + "White Balloon, The (1995)", + 10 + ], + [ + 19, + "Antonia's Line (1995)", + 69 + ], + [ + 20, + "Angels and Insects (1995)", + 72 + ], + [ + 21, + "Muppet Treasure Island (1996)", + 84 + ], + [ + 22, + "Braveheart (1995)", + 297 + ], + [ + 23, + "Taxi Driver (1976)", + 182 + ], + [ + 24, + "Rumble in the Bronx (1995)", + 174 + ], + [ + 25, + "Birdcage, The (1996)", + 293 + ], + [ + 26, + "Brothers McMullen, The (1995)", + 73 + ], + [ + 27, + "Bad Boys (1995)", + 57 + ], + [ + 28, + "Apollo 13 (1995)", + 276 + ], + [ + 29, + "Batman Forever (1995)", + 114 + ], + [ + 30, + "Belle de jour (1967)", + 37 + ], + [ + 31, + "Crimson Tide (1995)", + 154 + ], + [ + 32, + "Crumb (1994)", + 81 + ], + [ + 33, + "Desperado (1995)", + 97 + ], + [ + 34, + "Doom Generation, The (1995)", + 7 + ], + [ + 35, + "Free Willy 2: The Adventure Home (1995)", + 11 + ], + [ + 36, + "Mad Love (1995)", + 13 + ], + [ + 37, + "Nadja (1994)", + 8 + ], + [ + 38, + "Net, The (1995)", + 120 + ], + [ + 39, + "Strange Days (1995)", + 87 + ], + [ + 40, + "To Wong Foo, Thanks for Everything! Julie Newmar (1995)", + 57 + ], + [ + 41, + "Billy Madison (1995)", + 37 + ], + [ + 42, + "Clerks (1994)", + 148 + ], + [ + 43, + "Disclosure (1994)", + 40 + ], + [ + 44, + "Dolores Claiborne (1994)", + 79 + ], + [ + 45, + "Eat Drink Man Woman (1994)", + 80 + ], + [ + 46, + "Exotica (1994)", + 27 + ], + [ + 47, + "Ed Wood (1994)", + 133 + ], + [ + 48, + "Hoop Dreams (1994)", + 117 + ], + [ + 49, + "I.Q. (1994)", + 81 + ], + [ + 50, + "Star Wars (1977)", + 583 + ], + [ + 51, + "Legends of the Fall (1994)", + 81 + ], + [ + 52, + "Madness of King George, The (1994)", + 91 + ], + [ + 53, + "Natural Born Killers (1994)", + 128 + ], + [ + 54, + "Outbreak (1995)", + 104 + ], + [ + 55, + "Professional, The (1994)", + 149 + ], + [ + 56, + "Pulp Fiction (1994)", + 394 + ], + [ + 57, + "Priest (1994)", + 40 + ], + [ + 58, + "Quiz Show (1994)", + 175 + ], + [ + 59, + "Three Colors: Red (1994)", + 83 + ], + [ + 60, + "Three Colors: Blue (1993)", + 64 + ], + [ + 61, + "Three Colors: White (1994)", + 59 + ], + [ + 62, + "Stargate (1994)", + 127 + ], + [ + 63, + "Santa Clause, The (1994)", + 82 + ], + [ + 64, + "Shawshank Redemption, The (1994)", + 283 + ], + [ + 65, + "What's Eating Gilbert Grape (1993)", + 115 + ], + [ + 66, + "While You Were Sleeping (1995)", + 162 + ], + [ + 67, + "Ace Ventura: Pet Detective (1994)", + 103 + ], + [ + 68, + "Crow, The (1994)", + 134 + ], + [ + 69, + "Forrest Gump (1994)", + 321 + ], + [ + 70, + "Four Weddings and a Funeral (1994)", + 251 + ], + [ + 71, + "Lion King, The (1994)", + 220 + ], + [ + 72, + "Mask, The (1994)", + 129 + ], + [ + 73, + "Maverick (1994)", + 128 + ], + [ + 74, + "Faster Pussycat! Kill! Kill! (1965)", + 7 + ], + [ + 75, + "Brother Minister: The Assassination of Malcolm X (1994)", + 5 + ], + [ + 76, + "Carlito's Way (1993)", + 54 + ], + [ + 77, + "Firm, The (1993)", + 151 + ], + [ + 78, + "Free Willy (1993)", + 33 + ], + [ + 79, + "Fugitive, The (1993)", + 336 + ], + [ + 80, + "Hot Shots! Part Deux (1993)", + 68 + ], + [ + 81, + "Hudsucker Proxy, The (1994)", + 110 + ], + [ + 82, + "Jurassic Park (1993)", + 261 + ], + [ + 83, + "Much Ado About Nothing (1993)", + 176 + ], + [ + 84, + "Robert A. Heinlein's The Puppet Masters (1994)", + 18 + ], + [ + 85, + "Ref, The (1994)", + 58 + ], + [ + 86, + "Remains of the Day, The (1993)", + 150 + ], + [ + 87, + "Searching for Bobby Fischer (1993)", + 138 + ], + [ + 88, + "Sleepless in Seattle (1993)", + 213 + ], + [ + 89, + "Blade Runner (1982)", + 275 + ], + [ + 90, + "So I Married an Axe Murderer (1993)", + 95 + ], + [ + 91, + "Nightmare Before Christmas, The (1993)", + 143 + ], + [ + 92, + "True Romance (1993)", + 104 + ], + [ + 93, + "Welcome to the Dollhouse (1995)", + 112 + ], + [ + 94, + "Home Alone (1990)", + 137 + ], + [ + 95, + "Aladdin (1992)", + 219 + ], + [ + 96, + "Terminator 2: Judgment Day (1991)", + 295 + ], + [ + 97, + "Dances with Wolves (1990)", + 256 + ], + [ + 98, + "Silence of the Lambs, The (1991)", + 390 + ], + [ + 99, + "Snow White and the Seven Dwarfs (1937)", + 172 + ], + [ + 100, + "Fargo (1996)", + 508 + ], + [ + 101, + "Heavy Metal (1981)", + 73 + ], + [ + 102, + "Aristocats, The (1970)", + 54 + ], + [ + 103, + "All Dogs Go to Heaven 2 (1996)", + 15 + ], + [ + 104, + "Theodore Rex (1995)", + 5 + ], + [ + 105, + "Sgt. Bilko (1996)", + 74 + ], + [ + 106, + "Diabolique (1996)", + 71 + ], + [ + 107, + "Moll Flanders (1996)", + 42 + ], + [ + 108, + "Kids in the Hall: Brain Candy (1996)", + 65 + ], + [ + 109, + "Mystery Science Theater 3000: The Movie (1996)", + 130 + ], + [ + 110, + "Operation Dumbo Drop (1995)", + 31 + ], + [ + 111, + "Truth About Cats & Dogs, The (1996)", + 272 + ], + [ + 112, + "Flipper (1996)", + 20 + ], + [ + 113, + "Horseman on the Roof, The (Hussard sur le toit, Le) (1995)", + 9 + ], + [ + 114, + "Wallace & Gromit: The Best of Aardman Animation (1996)", + 67 + ], + [ + 115, + "Haunted World of Edward D. Wood Jr., The (1995)", + 15 + ], + [ + 116, + "Cold Comfort Farm (1995)", + 125 + ], + [ + 117, + "Rock, The (1996)", + 378 + ], + [ + 118, + "Twister (1996)", + 293 + ], + [ + 119, + "Maya Lin: A Strong Clear Vision (1994)", + 4 + ], + [ + 120, + "Striptease (1996)", + 67 + ], + [ + 121, + "Independence Day (ID4) (1996)", + 429 + ], + [ + 122, + "Cable Guy, The (1996)", + 106 + ], + [ + 123, + "Frighteners, The (1996)", + 115 + ], + [ + 124, + "Lone Star (1996)", + 187 + ], + [ + 125, + "Phenomenon (1996)", + 244 + ], + [ + 126, + "Spitfire Grill, The (1996)", + 97 + ], + [ + 127, + "Godfather, The (1972)", + 413 + ], + [ + 128, + "Supercop (1992)", + 65 + ], + [ + 129, + "Bound (1996)", + 129 + ], + [ + 130, + "Kansas City (1996)", + 23 + ], + [ + 131, + "Breakfast at Tiffany's (1961)", + 95 + ], + [ + 132, + "Wizard of Oz, The (1939)", + 246 + ], + [ + 133, + "Gone with the Wind (1939)", + 171 + ], + [ + 134, + "Citizen Kane (1941)", + 198 + ], + [ + 135, + "2001: A Space Odyssey (1968)", + 259 + ], + [ + 136, + "Mr. Smith Goes to Washington (1939)", + 105 + ], + [ + 137, + "Big Night (1996)", + 171 + ], + [ + 138, + "D3: The Mighty Ducks (1996)", + 19 + ], + [ + 139, + "Love Bug, The (1969)", + 50 + ], + [ + 140, + "Homeward Bound: The Incredible Journey (1993)", + 61 + ], + [ + 141, + "20,000 Leagues Under the Sea (1954)", + 72 + ], + [ + 142, + "Bedknobs and Broomsticks (1971)", + 57 + ], + [ + 143, + "Sound of Music, The (1965)", + 222 + ], + [ + 144, + "Die Hard (1988)", + 243 + ], + [ + 145, + "Lawnmower Man, The (1992)", + 65 + ], + [ + 146, + "Unhook the Stars (1996)", + 10 + ], + [ + 147, + "Long Kiss Goodnight, The (1996)", + 185 + ], + [ + 148, + "Ghost and the Darkness, The (1996)", + 128 + ], + [ + 149, + "Jude (1996)", + 23 + ], + [ + 150, + "Swingers (1996)", + 157 + ], + [ + 151, + "Willy Wonka and the Chocolate Factory (1971)", + 326 + ], + [ + 152, + "Sleeper (1973)", + 82 + ], + [ + 153, + "Fish Called Wanda, A (1988)", + 247 + ], + [ + 154, + "Monty Python's Life of Brian (1979)", + 174 + ], + [ + 155, + "Dirty Dancing (1987)", + 98 + ], + [ + 156, + "Reservoir Dogs (1992)", + 148 + ], + [ + 157, + "Platoon (1986)", + 127 + ], + [ + 158, + "Weekend at Bernie's (1989)", + 60 + ], + [ + 159, + "Basic Instinct (1992)", + 101 + ], + [ + 160, + "Glengarry Glen Ross (1992)", + 69 + ], + [ + 161, + "Top Gun (1986)", + 220 + ], + [ + 162, + "On Golden Pond (1981)", + 106 + ], + [ + 163, + "Return of the Pink Panther, The (1974)", + 92 + ], + [ + 164, + "Abyss, The (1989)", + 151 + ], + [ + 165, + "Jean de Florette (1986)", + 64 + ], + [ + 166, + "Manon of the Spring (Manon des sources) (1986)", + 58 + ], + [ + 167, + "Private Benjamin (1980)", + 67 + ], + [ + 168, + "Monty Python and the Holy Grail (1974)", + 316 + ], + [ + 169, + "Wrong Trousers, The (1993)", + 118 + ], + [ + 170, + "Cinema Paradiso (1988)", + 121 + ], + [ + 171, + "Delicatessen (1991)", + 65 + ], + [ + 172, + "Empire Strikes Back, The (1980)", + 367 + ], + [ + 173, + "Princess Bride, The (1987)", + 324 + ], + [ + 174, + "Raiders of the Lost Ark (1981)", + 420 + ], + [ + 175, + "Brazil (1985)", + 208 + ], + [ + 176, + "Aliens (1986)", + 284 + ], + [ + 177, + "Good, The Bad and The Ugly, The (1966)", + 137 + ], + [ + 178, + "12 Angry Men (1957)", + 125 + ], + [ + 179, + "Clockwork Orange, A (1971)", + 221 + ], + [ + 180, + "Apocalypse Now (1979)", + 221 + ], + [ + 181, + "Return of the Jedi (1983)", + 507 + ], + [ + 182, + "GoodFellas (1990)", + 226 + ], + [ + 183, + "Alien (1979)", + 291 + ], + [ + 184, + "Army of Darkness (1993)", + 116 + ], + [ + 185, + "Psycho (1960)", + 239 + ], + [ + 186, + "Blues Brothers, The (1980)", + 251 + ], + [ + 187, + "Godfather: Part II, The (1974)", + 209 + ], + [ + 188, + "Full Metal Jacket (1987)", + 170 + ], + [ + 189, + "Grand Day Out, A (1992)", + 66 + ], + [ + 190, + "Henry V (1989)", + 124 + ], + [ + 191, + "Amadeus (1984)", + 276 + ], + [ + 192, + "Raging Bull (1980)", + 116 + ], + [ + 193, + "Right Stuff, The (1983)", + 157 + ], + [ + 194, + "Sting, The (1973)", + 241 + ], + [ + 195, + "Terminator, The (1984)", + 301 + ], + [ + 196, + "Dead Poets Society (1989)", + 251 + ], + [ + 197, + "Graduate, The (1967)", + 239 + ], + [ + 198, + "Nikita (La Femme Nikita) (1990)", + 127 + ], + [ + 199, + "Bridge on the River Kwai, The (1957)", + 165 + ], + [ + 200, + "Shining, The (1980)", + 206 + ], + [ + 201, + "Evil Dead II (1987)", + 89 + ], + [ + 202, + "Groundhog Day (1993)", + 280 + ], + [ + 203, + "Unforgiven (1992)", + 182 + ], + [ + 204, + "Back to the Future (1985)", + 350 + ], + [ + 205, + "Patton (1970)", + 136 + ], + [ + 206, + "Akira (1988)", + 50 + ], + [ + 207, + "Cyrano de Bergerac (1990)", + 66 + ], + [ + 208, + "Young Frankenstein (1974)", + 200 + ], + [ + 209, + "This Is Spinal Tap (1984)", + 191 + ], + [ + 210, + "Indiana Jones and the Last Crusade (1989)", + 331 + ], + [ + 211, + "M*A*S*H (1970)", + 206 + ], + [ + 212, + "Unbearable Lightness of Being, The (1988)", + 92 + ], + [ + 213, + "Room with a View, A (1986)", + 134 + ], + [ + 214, + "Pink Floyd - The Wall (1982)", + 114 + ], + [ + 215, + "Field of Dreams (1989)", + 212 + ], + [ + 216, + "When Harry Met Sally... (1989)", + 290 + ], + [ + 217, + "Bram Stoker's Dracula (1992)", + 120 + ], + [ + 218, + "Cape Fear (1991)", + 171 + ], + [ + 219, + "Nightmare on Elm Street, A (1984)", + 111 + ], + [ + 220, + "Mirror Has Two Faces, The (1996)", + 66 + ], + [ + 221, + "Breaking the Waves (1996)", + 74 + ], + [ + 222, + "Star Trek: First Contact (1996)", + 365 + ], + [ + 223, + "Sling Blade (1996)", + 136 + ], + [ + 224, + "Ridicule (1996)", + 44 + ], + [ + 225, + "101 Dalmatians (1996)", + 109 + ], + [ + 226, + "Die Hard 2 (1990)", + 166 + ], + [ + 227, + "Star Trek VI: The Undiscovered Country (1991)", + 161 + ], + [ + 228, + "Star Trek: The Wrath of Khan (1982)", + 244 + ], + [ + 229, + "Star Trek III: The Search for Spock (1984)", + 171 + ], + [ + 230, + "Star Trek IV: The Voyage Home (1986)", + 199 + ], + [ + 231, + "Batman Returns (1992)", + 142 + ], + [ + 232, + "Young Guns (1988)", + 101 + ], + [ + 233, + "Under Siege (1992)", + 124 + ], + [ + 234, + "Jaws (1975)", + 280 + ], + [ + 235, + "Mars Attacks! (1996)", + 217 + ], + [ + 236, + "Citizen Ruth (1996)", + 45 + ], + [ + 237, + "Jerry Maguire (1996)", + 384 + ], + [ + 238, + "Raising Arizona (1987)", + 256 + ], + [ + 239, + "Sneakers (1992)", + 150 + ], + [ + 240, + "Beavis and Butt-head Do America (1996)", + 156 + ], + [ + 241, + "Last of the Mohicans, The (1992)", + 128 + ], + [ + 242, + "Kolya (1996)", + 117 + ], + [ + 243, + "Jungle2Jungle (1997)", + 132 + ], + [ + 244, + "Smilla's Sense of Snow (1997)", + 48 + ], + [ + 245, + "Devil's Own, The (1997)", + 240 + ], + [ + 246, + "Chasing Amy (1997)", + 124 + ], + [ + 247, + "Turbo: A Power Rangers Movie (1997)", + 5 + ], + [ + 248, + "Grosse Pointe Blank (1997)", + 160 + ], + [ + 249, + "Austin Powers: International Man of Mystery (1997)", + 130 + ], + [ + 250, + "Fifth Element, The (1997)", + 197 + ], + [ + 251, + "Shall We Dance? (1996)", + 46 + ], + [ + 252, + "Lost World: Jurassic Park, The (1997)", + 158 + ], + [ + 253, + "Pillow Book, The (1995)", + 26 + ], + [ + 254, + "Batman & Robin (1997)", + 62 + ], + [ + 255, + "My Best Friend's Wedding (1997)", + 172 + ], + [ + 256, + "When the Cats Away (Chacun cherche son chat) (1996)", + 16 + ], + [ + 257, + "Men in Black (1997)", + 303 + ], + [ + 258, + "Contact (1997)", + 509 + ], + [ + 259, + "George of the Jungle (1997)", + 162 + ], + [ + 260, + "Event Horizon (1997)", + 127 + ], + [ + 261, + "Air Bud (1997)", + 43 + ], + [ + 262, + "In the Company of Men (1997)", + 66 + ], + [ + 263, + "Steel (1997)", + 19 + ], + [ + 264, + "Mimic (1997)", + 101 + ], + [ + 265, + "Hunt for Red October, The (1990)", + 227 + ], + [ + 266, + "Kull the Conqueror (1997)", + 35 + ], + [ + 267, + "unknown", + 9 + ], + [ + 268, + "Chasing Amy (1997)", + 255 + ], + [ + 269, + "Full Monty, The (1997)", + 315 + ], + [ + 270, + "Gattaca (1997)", + 136 + ], + [ + 271, + "Starship Troopers (1997)", + 211 + ], + [ + 272, + "Good Will Hunting (1997)", + 198 + ], + [ + 273, + "Heat (1995)", + 223 + ], + [ + 274, + "Sabrina (1995)", + 190 + ], + [ + 275, + "Sense and Sensibility (1995)", + 268 + ], + [ + 276, + "Leaving Las Vegas (1995)", + 298 + ], + [ + 277, + "Restoration (1995)", + 71 + ], + [ + 278, + "Bed of Roses (1996)", + 60 + ], + [ + 279, + "Once Upon a Time... When We Were Colored (1995)", + 28 + ], + [ + 280, + "Up Close and Personal (1996)", + 85 + ], + [ + 281, + "River Wild, The (1994)", + 146 + ], + [ + 282, + "Time to Kill, A (1996)", + 232 + ], + [ + 283, + "Emma (1996)", + 177 + ], + [ + 284, + "Tin Cup (1996)", + 193 + ], + [ + 285, + "Secrets & Lies (1996)", + 162 + ], + [ + 286, + "English Patient, The (1996)", + 481 + ], + [ + 287, + "Marvin's Room (1996)", + 78 + ], + [ + 288, + "Scream (1996)", + 478 + ], + [ + 289, + "Evita (1996)", + 259 + ], + [ + 290, + "Fierce Creatures (1997)", + 96 + ], + [ + 291, + "Absolute Power (1997)", + 127 + ], + [ + 292, + "Rosewood (1997)", + 114 + ], + [ + 293, + "Donnie Brasco (1997)", + 147 + ], + [ + 294, + "Liar Liar (1997)", + 485 + ], + [ + 295, + "Breakdown (1997)", + 77 + ], + [ + 296, + "Promesse, La (1996)", + 6 + ], + [ + 297, + "Ulee's Gold (1997)", + 50 + ], + [ + 298, + "Face/Off (1997)", + 194 + ], + [ + 299, + "Hoodlum (1997)", + 73 + ], + [ + 300, + "Air Force One (1997)", + 431 + ], + [ + 301, + "In & Out (1997)", + 230 + ], + [ + 302, + "L.A. Confidential (1997)", + 297 + ], + [ + 303, + "Ulee's Gold (1997)", + 134 + ], + [ + 304, + "Fly Away Home (1996)", + 149 + ], + [ + 305, + "Ice Storm, The (1997)", + 87 + ], + [ + 306, + "Mrs. Brown (Her Majesty, Mrs. Brown) (1997)", + 96 + ], + [ + 307, + "Devil's Advocate, The (1997)", + 188 + ], + [ + 308, + "FairyTale: A True Story (1997)", + 30 + ], + [ + 309, + "Deceiver (1997)", + 28 + ], + [ + 310, + "Rainmaker, The (1997)", + 145 + ], + [ + 311, + "Wings of the Dove, The (1997)", + 75 + ], + [ + 312, + "Midnight in the Garden of Good and Evil (1997)", + 80 + ], + [ + 313, + "Titanic (1997)", + 350 + ], + [ + 314, + "3 Ninjas: High Noon At Mega Mountain (1998)", + 5 + ], + [ + 315, + "Apt Pupil (1998)", + 160 + ], + [ + 316, + "As Good As It Gets (1997)", + 112 + ], + [ + 317, + "In the Name of the Father (1993)", + 102 + ], + [ + 318, + "Schindler's List (1993)", + 298 + ], + [ + 319, + "Everyone Says I Love You (1996)", + 168 + ], + [ + 320, + "Paradise Lost: The Child Murders at Robin Hood Hills (1996)", + 20 + ], + [ + 321, + "Mother (1996)", + 169 + ], + [ + 322, + "Murder at 1600 (1997)", + 218 + ], + [ + 323, + "Dante's Peak (1997)", + 240 + ], + [ + 324, + "Lost Highway (1997)", + 125 + ], + [ + 325, + "Crash (1996)", + 128 + ], + [ + 326, + "G.I. Jane (1997)", + 175 + ], + [ + 327, + "Cop Land (1997)", + 175 + ], + [ + 328, + "Conspiracy Theory (1997)", + 295 + ], + [ + 329, + "Desperate Measures (1998)", + 45 + ], + [ + 330, + "187 (1997)", + 41 + ], + [ + 331, + "Edge, The (1997)", + 113 + ], + [ + 332, + "Kiss the Girls (1997)", + 143 + ], + [ + 333, + "Game, The (1997)", + 251 + ], + [ + 334, + "U Turn (1997)", + 64 + ], + [ + 335, + "How to Be a Player (1997)", + 21 + ], + [ + 336, + "Playing God (1997)", + 43 + ], + [ + 337, + "House of Yes, The (1997)", + 18 + ], + [ + 338, + "Bean (1997)", + 91 + ], + [ + 339, + "Mad City (1997)", + 47 + ], + [ + 340, + "Boogie Nights (1997)", + 189 + ], + [ + 341, + "Critical Care (1997)", + 11 + ], + [ + 342, + "Man Who Knew Too Little, The (1997)", + 52 + ], + [ + 343, + "Alien: Resurrection (1997)", + 124 + ], + [ + 344, + "Apostle, The (1997)", + 55 + ], + [ + 345, + "Deconstructing Harry (1997)", + 65 + ], + [ + 346, + "Jackie Brown (1997)", + 126 + ], + [ + 347, + "Wag the Dog (1997)", + 137 + ], + [ + 348, + "Desperate Measures (1998)", + 27 + ], + [ + 349, + "Hard Rain (1998)", + 31 + ], + [ + 350, + "Fallen (1998)", + 41 + ], + [ + 351, + "Prophecy II, The (1998)", + 20 + ], + [ + 352, + "Spice World (1997)", + 26 + ], + [ + 353, + "Deep Rising (1998)", + 14 + ], + [ + 354, + "Wedding Singer, The (1998)", + 72 + ], + [ + 355, + "Sphere (1998)", + 41 + ], + [ + 356, + "Client, The (1994)", + 97 + ], + [ + 357, + "One Flew Over the Cuckoo's Nest (1975)", + 264 + ], + [ + 358, + "Spawn (1997)", + 143 + ], + [ + 359, + "Assignment, The (1997)", + 18 + ], + [ + 360, + "Wonderland (1997)", + 10 + ], + [ + 361, + "Incognito (1997)", + 10 + ], + [ + 362, + "Blues Brothers 2000 (1998)", + 28 + ], + [ + 363, + "Sudden Death (1995)", + 47 + ], + [ + 364, + "Ace Ventura: When Nature Calls (1995)", + 37 + ], + [ + 365, + "Powder (1995)", + 48 + ], + [ + 366, + "Dangerous Minds (1995)", + 47 + ], + [ + 367, + "Clueless (1995)", + 170 + ], + [ + 368, + "Bio-Dome (1996)", + 31 + ], + [ + 369, + "Black Sheep (1996)", + 55 + ], + [ + 370, + "Mary Reilly (1996)", + 39 + ], + [ + 371, + "Bridges of Madison County, The (1995)", + 67 + ], + [ + 372, + "Jeffrey (1995)", + 34 + ], + [ + 373, + "Judge Dredd (1995)", + 39 + ], + [ + 374, + "Mighty Morphin Power Rangers: The Movie (1995)", + 11 + ], + [ + 375, + "Showgirls (1995)", + 23 + ], + [ + 376, + "Houseguest (1994)", + 24 + ], + [ + 377, + "Heavyweights (1994)", + 13 + ], + [ + 378, + "Miracle on 34th Street (1994)", + 101 + ], + [ + 379, + "Tales From the Crypt Presents: Demon Knight (1995)", + 43 + ], + [ + 380, + "Star Trek: Generations (1994)", + 116 + ], + [ + 381, + "Muriel's Wedding (1994)", + 100 + ], + [ + 382, + "Adventures of Priscilla, Queen of the Desert, The (1994)", + 111 + ], + [ + 383, + "Flintstones, The (1994)", + 31 + ], + [ + 384, + "Naked Gun 33 1/3: The Final Insult (1994)", + 69 + ], + [ + 385, + "True Lies (1994)", + 208 + ], + [ + 386, + "Addams Family Values (1993)", + 87 + ], + [ + 387, + "Age of Innocence, The (1993)", + 65 + ], + [ + 388, + "Beverly Hills Cop III (1994)", + 28 + ], + [ + 389, + "Black Beauty (1994)", + 27 + ], + [ + 390, + "Fear of a Black Hat (1993)", + 10 + ], + [ + 391, + "Last Action Hero (1993)", + 59 + ], + [ + 392, + "Man Without a Face, The (1993)", + 68 + ], + [ + 393, + "Mrs. Doubtfire (1993)", + 192 + ], + [ + 394, + "Radioland Murders (1994)", + 12 + ], + [ + 395, + "Robin Hood: Men in Tights (1993)", + 56 + ], + [ + 396, + "Serial Mom (1994)", + 54 + ], + [ + 397, + "Striking Distance (1993)", + 12 + ], + [ + 398, + "Super Mario Bros. (1993)", + 26 + ], + [ + 399, + "Three Musketeers, The (1993)", + 89 + ], + [ + 400, + "Little Rascals, The (1994)", + 18 + ], + [ + 401, + "Brady Bunch Movie, The (1995)", + 76 + ], + [ + 402, + "Ghost (1990)", + 170 + ], + [ + 403, + "Batman (1989)", + 201 + ], + [ + 404, + "Pinocchio (1940)", + 101 + ], + [ + 405, + "Mission: Impossible (1996)", + 344 + ], + [ + 406, + "Thinner (1996)", + 49 + ], + [ + 407, + "Spy Hard (1996)", + 43 + ], + [ + 408, + "Close Shave, A (1995)", + 112 + ], + [ + 409, + "Jack (1996)", + 70 + ], + [ + 410, + "Kingpin (1996)", + 162 + ], + [ + 411, + "Nutty Professor, The (1996)", + 163 + ], + [ + 412, + "Very Brady Sequel, A (1996)", + 93 + ], + [ + 413, + "Tales from the Crypt Presents: Bordello of Blood (1996)", + 55 + ], + [ + 414, + "My Favorite Year (1982)", + 62 + ], + [ + 415, + "Apple Dumpling Gang, The (1975)", + 25 + ], + [ + 416, + "Old Yeller (1957)", + 64 + ], + [ + 417, + "Parent Trap, The (1961)", + 73 + ], + [ + 418, + "Cinderella (1950)", + 129 + ], + [ + 419, + "Mary Poppins (1964)", + 178 + ], + [ + 420, + "Alice in Wonderland (1951)", + 81 + ], + [ + 421, + "William Shakespeare's Romeo and Juliet (1996)", + 106 + ], + [ + 422, + "Aladdin and the King of Thieves (1996)", + 26 + ], + [ + 423, + "E.T. the Extra-Terrestrial (1982)", + 300 + ], + [ + 424, + "Children of the Corn: The Gathering (1996)", + 19 + ], + [ + 425, + "Bob Roberts (1992)", + 85 + ], + [ + 426, + "Transformers: The Movie, The (1986)", + 32 + ], + [ + 427, + "To Kill a Mockingbird (1962)", + 219 + ], + [ + 428, + "Harold and Maude (1971)", + 121 + ], + [ + 429, + "Day the Earth Stood Still, The (1951)", + 97 + ], + [ + 430, + "Duck Soup (1933)", + 93 + ], + [ + 431, + "Highlander (1986)", + 153 + ], + [ + 432, + "Fantasia (1940)", + 174 + ], + [ + 433, + "Heathers (1989)", + 171 + ], + [ + 434, + "Forbidden Planet (1956)", + 67 + ], + [ + 435, + "Butch Cassidy and the Sundance Kid (1969)", + 216 + ], + [ + 436, + "American Werewolf in London, An (1981)", + 99 + ], + [ + 437, + "Amityville 1992: It's About Time (1992)", + 5 + ], + [ + 438, + "Amityville 3-D (1983)", + 6 + ], + [ + 439, + "Amityville: A New Generation (1993)", + 5 + ], + [ + 440, + "Amityville II: The Possession (1982)", + 14 + ], + [ + 441, + "Amityville Horror, The (1979)", + 53 + ], + [ + 442, + "Amityville Curse, The (1990)", + 4 + ], + [ + 443, + "Birds, The (1963)", + 162 + ], + [ + 444, + "Blob, The (1958)", + 46 + ], + [ + 445, + "Body Snatcher, The (1945)", + 22 + ], + [ + 446, + "Burnt Offerings (1976)", + 9 + ], + [ + 447, + "Carrie (1976)", + 121 + ], + [ + 448, + "Omen, The (1976)", + 85 + ], + [ + 449, + "Star Trek: The Motion Picture (1979)", + 117 + ], + [ + 450, + "Star Trek V: The Final Frontier (1989)", + 63 + ], + [ + 451, + "Grease (1978)", + 170 + ], + [ + 452, + "Jaws 2 (1978)", + 66 + ], + [ + 453, + "Jaws 3-D (1983)", + 16 + ], + [ + 454, + "Bastard Out of Carolina (1996)", + 16 + ], + [ + 455, + "Jackie Chan's First Strike (1996)", + 145 + ], + [ + 456, + "Beverly Hills Ninja (1997)", + 48 + ], + [ + 457, + "Free Willy 3: The Rescue (1997)", + 27 + ], + [ + 458, + "Nixon (1995)", + 90 + ], + [ + 459, + "Cry, the Beloved Country (1995)", + 24 + ], + [ + 460, + "Crossing Guard, The (1995)", + 28 + ], + [ + 461, + "Smoke (1995)", + 74 + ], + [ + 462, + "Like Water For Chocolate (Como agua para chocolate) (1992)", + 148 + ], + [ + 463, + "Secret of Roan Inish, The (1994)", + 71 + ], + [ + 464, + "Vanya on 42nd Street (1994)", + 27 + ], + [ + 465, + "Jungle Book, The (1994)", + 85 + ], + [ + 466, + "Red Rock West (1992)", + 52 + ], + [ + 467, + "Bronx Tale, A (1993)", + 48 + ], + [ + 468, + "Rudy (1993)", + 64 + ], + [ + 469, + "Short Cuts (1993)", + 67 + ], + [ + 470, + "Tombstone (1993)", + 108 + ], + [ + 471, + "Courage Under Fire (1996)", + 221 + ], + [ + 472, + "Dragonheart (1996)", + 158 + ], + [ + 473, + "James and the Giant Peach (1996)", + 126 + ], + [ + 474, + "Dr. Strangelove or: How I Learned to Stop Worrying and Love the Bomb (1963)", + 194 + ], + [ + 475, + "Trainspotting (1996)", + 250 + ], + [ + 476, + "First Wives Club, The (1996)", + 160 + ], + [ + 477, + "Matilda (1996)", + 95 + ], + [ + 478, + "Philadelphia Story, The (1940)", + 104 + ], + [ + 479, + "Vertigo (1958)", + 179 + ], + [ + 480, + "North by Northwest (1959)", + 179 + ], + [ + 481, + "Apartment, The (1960)", + 63 + ], + [ + 482, + "Some Like It Hot (1959)", + 128 + ], + [ + 483, + "Casablanca (1942)", + 243 + ], + [ + 484, + "Maltese Falcon, The (1941)", + 138 + ], + [ + 485, + "My Fair Lady (1964)", + 125 + ], + [ + 486, + "Sabrina (1954)", + 64 + ], + [ + 487, + "Roman Holiday (1953)", + 68 + ], + [ + 488, + "Sunset Blvd. (1950)", + 65 + ], + [ + 489, + "Notorious (1946)", + 52 + ], + [ + 490, + "To Catch a Thief (1955)", + 50 + ], + [ + 491, + "Adventures of Robin Hood, The (1938)", + 67 + ], + [ + 492, + "East of Eden (1955)", + 59 + ], + [ + 493, + "Thin Man, The (1934)", + 60 + ], + [ + 494, + "His Girl Friday (1940)", + 56 + ], + [ + 495, + "Around the World in 80 Days (1956)", + 59 + ], + [ + 496, + "It's a Wonderful Life (1946)", + 231 + ], + [ + 497, + "Bringing Up Baby (1938)", + 68 + ], + [ + 498, + "African Queen, The (1951)", + 152 + ], + [ + 499, + "Cat on a Hot Tin Roof (1958)", + 62 + ], + [ + 500, + "Fly Away Home (1996)", + 31 + ], + [ + 501, + "Dumbo (1941)", + 123 + ], + [ + 502, + "Bananas (1971)", + 57 + ], + [ + 503, + "Candidate, The (1972)", + 39 + ], + [ + 504, + "Bonnie and Clyde (1967)", + 122 + ], + [ + 505, + "Dial M for Murder (1954)", + 68 + ], + [ + 506, + "Rebel Without a Cause (1955)", + 90 + ], + [ + 507, + "Streetcar Named Desire, A (1951)", + 98 + ], + [ + 508, + "People vs. Larry Flynt, The (1996)", + 215 + ], + [ + 509, + "My Left Foot (1989)", + 121 + ], + [ + 510, + "Magnificent Seven, The (1954)", + 121 + ], + [ + 511, + "Lawrence of Arabia (1962)", + 173 + ], + [ + 512, + "Wings of Desire (1987)", + 57 + ], + [ + 513, + "Third Man, The (1949)", + 72 + ], + [ + 514, + "Annie Hall (1977)", + 180 + ], + [ + 515, + "Boot, Das (1981)", + 201 + ], + [ + 516, + "Local Hero (1983)", + 63 + ], + [ + 517, + "Manhattan (1979)", + 91 + ], + [ + 518, + "Miller's Crossing (1990)", + 89 + ], + [ + 519, + "Treasure of the Sierra Madre, The (1948)", + 80 + ], + [ + 520, + "Great Escape, The (1963)", + 124 + ], + [ + 521, + "Deer Hunter, The (1978)", + 120 + ], + [ + 522, + "Down by Law (1986)", + 35 + ], + [ + 523, + "Cool Hand Luke (1967)", + 164 + ], + [ + 524, + "Great Dictator, The (1940)", + 46 + ], + [ + 525, + "Big Sleep, The (1946)", + 73 + ], + [ + 526, + "Ben-Hur (1959)", + 124 + ], + [ + 527, + "Gandhi (1982)", + 195 + ], + [ + 528, + "Killing Fields, The (1984)", + 121 + ], + [ + 529, + "My Life as a Dog (Mitt liv som hund) (1985)", + 93 + ], + [ + 530, + "Man Who Would Be King, The (1975)", + 80 + ], + [ + 531, + "Shine (1996)", + 129 + ], + [ + 532, + "Kama Sutra: A Tale of Love (1996)", + 22 + ], + [ + 533, + "Daytrippers, The (1996)", + 15 + ], + [ + 534, + "Traveller (1997)", + 13 + ], + [ + 535, + "Addicted to Love (1997)", + 54 + ], + [ + 536, + "Ponette (1996)", + 10 + ], + [ + 537, + "My Own Private Idaho (1991)", + 30 + ], + [ + 538, + "Anastasia (1997)", + 66 + ], + [ + 539, + "Mouse Hunt (1997)", + 44 + ], + [ + 540, + "Money Train (1995)", + 43 + ], + [ + 541, + "Mortal Kombat (1995)", + 49 + ], + [ + 542, + "Pocahontas (1995)", + 51 + ], + [ + 543, + "Misérables, Les (1995)", + 21 + ], + [ + 544, + "Things to Do in Denver when You're Dead (1995)", + 71 + ], + [ + 545, + "Vampire in Brooklyn (1995)", + 12 + ], + [ + 546, + "Broken Arrow (1996)", + 254 + ], + [ + 547, + "Young Poisoner's Handbook, The (1995)", + 41 + ], + [ + 548, + "NeverEnding Story III, The (1994)", + 12 + ], + [ + 549, + "Rob Roy (1995)", + 92 + ], + [ + 550, + "Die Hard: With a Vengeance (1995)", + 151 + ], + [ + 551, + "Lord of Illusions (1995)", + 24 + ], + [ + 552, + "Species (1995)", + 45 + ], + [ + 553, + "Walk in the Clouds, A (1995)", + 63 + ], + [ + 554, + "Waterworld (1995)", + 102 + ], + [ + 555, + "White Man's Burden (1995)", + 10 + ], + [ + 556, + "Wild Bill (1995)", + 12 + ], + [ + 557, + "Farinelli: il castrato (1994)", + 17 + ], + [ + 558, + "Heavenly Creatures (1994)", + 70 + ], + [ + 559, + "Interview with the Vampire (1994)", + 137 + ], + [ + 560, + "Kid in King Arthur's Court, A (1995)", + 22 + ], + [ + 561, + "Mary Shelley's Frankenstein (1994)", + 59 + ], + [ + 562, + "Quick and the Dead, The (1995)", + 48 + ], + [ + 563, + "Stephen King's The Langoliers (1995)", + 29 + ], + [ + 564, + "Tales from the Hood (1995)", + 27 + ], + [ + 565, + "Village of the Damned (1995)", + 22 + ], + [ + 566, + "Clear and Present Danger (1994)", + 179 + ], + [ + 567, + "Wes Craven's New Nightmare (1994)", + 35 + ], + [ + 568, + "Speed (1994)", + 230 + ], + [ + 569, + "Wolf (1994)", + 67 + ], + [ + 570, + "Wyatt Earp (1994)", + 50 + ], + [ + 571, + "Another Stakeout (1993)", + 28 + ], + [ + 572, + "Blown Away (1994)", + 29 + ], + [ + 573, + "Body Snatchers (1993)", + 33 + ], + [ + 574, + "Boxing Helena (1993)", + 15 + ], + [ + 575, + "City Slickers II: The Legend of Curly's Gold (1994)", + 44 + ], + [ + 576, + "Cliffhanger (1993)", + 93 + ], + [ + 577, + "Coneheads (1993)", + 41 + ], + [ + 578, + "Demolition Man (1993)", + 92 + ], + [ + 579, + "Fatal Instinct (1993)", + 19 + ], + [ + 580, + "Englishman Who Went Up a Hill, But Came Down a Mountain, The (1995)", + 32 + ], + [ + 581, + "Kalifornia (1993)", + 59 + ], + [ + 582, + "Piano, The (1993)", + 168 + ], + [ + 583, + "Romeo Is Bleeding (1993)", + 37 + ], + [ + 584, + "Secret Garden, The (1993)", + 79 + ], + [ + 585, + "Son in Law (1993)", + 39 + ], + [ + 586, + "Terminal Velocity (1994)", + 34 + ], + [ + 587, + "Hour of the Pig, The (1993)", + 14 + ], + [ + 588, + "Beauty and the Beast (1991)", + 202 + ], + [ + 589, + "Wild Bunch, The (1969)", + 43 + ], + [ + 590, + "Hellraiser: Bloodline (1996)", + 18 + ], + [ + 591, + "Primal Fear (1996)", + 178 + ], + [ + 592, + "True Crime (1995)", + 9 + ], + [ + 593, + "Stalingrad (1993)", + 12 + ], + [ + 594, + "Heavy (1995)", + 5 + ], + [ + 595, + "Fan, The (1996)", + 64 + ], + [ + 596, + "Hunchback of Notre Dame, The (1996)", + 127 + ], + [ + 597, + "Eraser (1996)", + 206 + ], + [ + 598, + "Big Squeeze, The (1996)", + 4 + ], + [ + 599, + "Police Story 4: Project S (Chao ji ji hua) (1993)", + 1 + ], + [ + 600, + "Daniel Defoe's Robinson Crusoe (1996)", + 2 + ], + [ + 601, + "For Whom the Bell Tolls (1943)", + 20 + ], + [ + 602, + "American in Paris, An (1951)", + 50 + ], + [ + 603, + "Rear Window (1954)", + 209 + ], + [ + 604, + "It Happened One Night (1934)", + 81 + ], + [ + 605, + "Meet Me in St. Louis (1944)", + 31 + ], + [ + 606, + "All About Eve (1950)", + 66 + ], + [ + 607, + "Rebecca (1940)", + 66 + ], + [ + 608, + "Spellbound (1945)", + 30 + ], + [ + 609, + "Father of the Bride (1950)", + 60 + ], + [ + 610, + "Gigi (1958)", + 41 + ], + [ + 611, + "Laura (1944)", + 40 + ], + [ + 612, + "Lost Horizon (1937)", + 34 + ], + [ + 613, + "My Man Godfrey (1936)", + 27 + ], + [ + 614, + "Giant (1956)", + 51 + ], + [ + 615, + "39 Steps, The (1935)", + 59 + ], + [ + 616, + "Night of the Living Dead (1968)", + 64 + ], + [ + 617, + "Blue Angel, The (Blaue Engel, Der) (1930)", + 18 + ], + [ + 618, + "Picnic (1955)", + 18 + ], + [ + 619, + "Extreme Measures (1996)", + 64 + ], + [ + 620, + "Chamber, The (1996)", + 43 + ], + [ + 621, + "Davy Crockett, King of the Wild Frontier (1955)", + 11 + ], + [ + 622, + "Swiss Family Robinson (1960)", + 39 + ], + [ + 623, + "Angels in the Outfield (1994)", + 39 + ], + [ + 624, + "Three Caballeros, The (1945)", + 22 + ], + [ + 625, + "Sword in the Stone, The (1963)", + 82 + ], + [ + 626, + "So Dear to My Heart (1949)", + 4 + ], + [ + 627, + "Robin Hood: Prince of Thieves (1991)", + 75 + ], + [ + 628, + "Sleepers (1996)", + 169 + ], + [ + 629, + "Victor/Victoria (1982)", + 77 + ], + [ + 630, + "Great Race, The (1965)", + 31 + ], + [ + 631, + "Crying Game, The (1992)", + 119 + ], + [ + 632, + "Sophie's Choice (1982)", + 58 + ], + [ + 633, + "Christmas Carol, A (1938)", + 69 + ], + [ + 634, + "Microcosmos: Le peuple de l'herbe (1996)", + 24 + ], + [ + 635, + "Fog, The (1980)", + 23 + ], + [ + 636, + "Escape from New York (1981)", + 91 + ], + [ + 637, + "Howling, The (1981)", + 38 + ], + [ + 638, + "Return of Martin Guerre, The (Retour de Martin Guerre, Le) (1982)", + 44 + ], + [ + 639, + "Tin Drum, The (Blechtrommel, Die) (1979)", + 40 + ], + [ + 640, + "Cook the Thief His Wife & Her Lover, The (1989)", + 82 + ], + [ + 641, + "Paths of Glory (1957)", + 33 + ], + [ + 642, + "Grifters, The (1990)", + 89 + ], + [ + 643, + "The Innocent (1994)", + 4 + ], + [ + 644, + "Thin Blue Line, The (1988)", + 35 + ], + [ + 645, + "Paris Is Burning (1990)", + 27 + ], + [ + 646, + "Once Upon a Time in the West (1969)", + 38 + ], + [ + 647, + "Ran (1985)", + 70 + ], + [ + 648, + "Quiet Man, The (1952)", + 67 + ], + [ + 649, + "Once Upon a Time in America (1984)", + 50 + ], + [ + 650, + "Seventh Seal, The (Sjunde inseglet, Det) (1957)", + 72 + ], + [ + 651, + "Glory (1989)", + 171 + ], + [ + 652, + "Rosencrantz and Guildenstern Are Dead (1990)", + 90 + ], + [ + 653, + "Touch of Evil (1958)", + 34 + ], + [ + 654, + "Chinatown (1974)", + 147 + ], + [ + 655, + "Stand by Me (1986)", + 227 + ], + [ + 656, + "M (1931)", + 44 + ], + [ + 657, + "Manchurian Candidate, The (1962)", + 131 + ], + [ + 658, + "Pump Up the Volume (1990)", + 79 + ], + [ + 659, + "Arsenic and Old Lace (1944)", + 115 + ], + [ + 660, + "Fried Green Tomatoes (1991)", + 153 + ], + [ + 661, + "High Noon (1952)", + 88 + ], + [ + 662, + "Somewhere in Time (1980)", + 82 + ], + [ + 663, + "Being There (1979)", + 116 + ], + [ + 664, + "Paris, Texas (1984)", + 46 + ], + [ + 665, + "Alien 3 (1992)", + 100 + ], + [ + 666, + "Blood For Dracula (Andy Warhol's Dracula) (1974)", + 5 + ], + [ + 667, + "Audrey Rose (1977)", + 12 + ], + [ + 668, + "Blood Beach (1981)", + 6 + ], + [ + 669, + "Body Parts (1991)", + 13 + ], + [ + 670, + "Body Snatchers (1993)", + 36 + ], + [ + 671, + "Bride of Frankenstein (1935)", + 46 + ], + [ + 672, + "Candyman (1992)", + 65 + ], + [ + 673, + "Cape Fear (1962)", + 86 + ], + [ + 674, + "Cat People (1982)", + 48 + ], + [ + 675, + "Nosferatu (Nosferatu, eine Symphonie des Grauens) (1922)", + 54 + ], + [ + 676, + "Crucible, The (1996)", + 77 + ], + [ + 677, + "Fire on the Mountain (1996)", + 1 + ], + [ + 678, + "Volcano (1997)", + 219 + ], + [ + 679, + "Conan the Barbarian (1981)", + 107 + ], + [ + 680, + "Kull the Conqueror (1997)", + 34 + ], + [ + 681, + "Wishmaster (1997)", + 27 + ], + [ + 682, + "I Know What You Did Last Summer (1997)", + 100 + ], + [ + 683, + "Rocket Man (1997)", + 49 + ], + [ + 684, + "In the Line of Fire (1993)", + 169 + ], + [ + 685, + "Executive Decision (1996)", + 157 + ], + [ + 686, + "Perfect World, A (1993)", + 50 + ], + [ + 687, + "McHale's Navy (1997)", + 69 + ], + [ + 688, + "Leave It to Beaver (1997)", + 44 + ], + [ + 689, + "Jackal, The (1997)", + 87 + ], + [ + 690, + "Seven Years in Tibet (1997)", + 155 + ], + [ + 691, + "Dark City (1998)", + 16 + ], + [ + 692, + "American President, The (1995)", + 164 + ], + [ + 693, + "Casino (1995)", + 91 + ], + [ + 694, + "Persuasion (1995)", + 44 + ], + [ + 695, + "Kicking and Screaming (1995)", + 13 + ], + [ + 696, + "City Hall (1996)", + 79 + ], + [ + 697, + "Basketball Diaries, The (1995)", + 40 + ], + [ + 698, + "Browning Version, The (1994)", + 10 + ], + [ + 699, + "Little Women (1994)", + 102 + ], + [ + 700, + "Miami Rhapsody (1995)", + 15 + ], + [ + 701, + "Wonderful, Horrible Life of Leni Riefenstahl, The (1993)", + 10 + ], + [ + 702, + "Barcelona (1994)", + 53 + ], + [ + 703, + "Widows' Peak (1994)", + 19 + ], + [ + 704, + "House of the Spirits, The (1993)", + 24 + ], + [ + 705, + "Singin' in the Rain (1952)", + 137 + ], + [ + 706, + "Bad Moon (1996)", + 6 + ], + [ + 707, + "Enchanted April (1991)", + 70 + ], + [ + 708, + "Sex, Lies, and Videotape (1989)", + 101 + ], + [ + 709, + "Strictly Ballroom (1992)", + 104 + ], + [ + 710, + "Better Off Dead... (1985)", + 79 + ], + [ + 711, + "Substance of Fire, The (1996)", + 1 + ], + [ + 712, + "Tin Men (1987)", + 51 + ], + [ + 713, + "Othello (1995)", + 72 + ], + [ + 714, + "Carrington (1995)", + 13 + ], + [ + 715, + "To Die For (1995)", + 87 + ], + [ + 716, + "Home for the Holidays (1995)", + 58 + ], + [ + 717, + "Juror, The (1996)", + 82 + ], + [ + 718, + "In the Bleak Midwinter (1995)", + 16 + ], + [ + 719, + "Canadian Bacon (1994)", + 29 + ], + [ + 720, + "First Knight (1995)", + 86 + ], + [ + 721, + "Mallrats (1995)", + 54 + ], + [ + 722, + "Nine Months (1995)", + 58 + ], + [ + 723, + "Boys on the Side (1995)", + 34 + ], + [ + 724, + "Circle of Friends (1995)", + 76 + ], + [ + 725, + "Exit to Eden (1994)", + 16 + ], + [ + 726, + "Fluke (1995)", + 14 + ], + [ + 727, + "Immortal Beloved (1994)", + 63 + ], + [ + 728, + "Junior (1994)", + 45 + ], + [ + 729, + "Nell (1994)", + 81 + ], + [ + 730, + "Queen Margot (Reine Margot, La) (1994)", + 24 + ], + [ + 731, + "Corrina, Corrina (1994)", + 39 + ], + [ + 732, + "Dave (1993)", + 180 + ], + [ + 733, + "Go Fish (1994)", + 15 + ], + [ + 734, + "Made in America (1993)", + 27 + ], + [ + 735, + "Philadelphia (1993)", + 137 + ], + [ + 736, + "Shadowlands (1993)", + 78 + ], + [ + 737, + "Sirens (1994)", + 59 + ], + [ + 738, + "Threesome (1994)", + 31 + ], + [ + 739, + "Pretty Woman (1990)", + 164 + ], + [ + 740, + "Jane Eyre (1996)", + 63 + ], + [ + 741, + "Last Supper, The (1995)", + 58 + ], + [ + 742, + "Ransom (1996)", + 267 + ], + [ + 743, + "Crow: City of Angels, The (1996)", + 39 + ], + [ + 744, + "Michael Collins (1996)", + 92 + ], + [ + 745, + "Ruling Class, The (1972)", + 16 + ], + [ + 746, + "Real Genius (1985)", + 119 + ], + [ + 747, + "Benny & Joon (1993)", + 102 + ], + [ + 748, + "Saint, The (1997)", + 316 + ], + [ + 749, + "MatchMaker, The (1997)", + 51 + ], + [ + 750, + "Amistad (1997)", + 124 + ], + [ + 751, + "Tomorrow Never Dies (1997)", + 180 + ], + [ + 752, + "Replacement Killers, The (1998)", + 39 + ], + [ + 753, + "Burnt By the Sun (1994)", + 24 + ], + [ + 754, + "Red Corner (1997)", + 57 + ], + [ + 755, + "Jumanji (1995)", + 96 + ], + [ + 756, + "Father of the Bride Part II (1995)", + 128 + ], + [ + 757, + "Across the Sea of Time (1995)", + 4 + ], + [ + 758, + "Lawnmower Man 2: Beyond Cyberspace (1996)", + 21 + ], + [ + 759, + "Fair Game (1995)", + 11 + ], + [ + 760, + "Screamers (1995)", + 46 + ], + [ + 761, + "Nick of Time (1995)", + 44 + ], + [ + 762, + "Beautiful Girls (1996)", + 115 + ], + [ + 763, + "Happy Gilmore (1996)", + 149 + ], + [ + 764, + "If Lucy Fell (1996)", + 29 + ], + [ + 765, + "Boomerang (1992)", + 32 + ], + [ + 766, + "Man of the Year (1995)", + 9 + ], + [ + 767, + "Addiction, The (1995)", + 11 + ], + [ + 768, + "Casper (1995)", + 52 + ], + [ + 769, + "Congo (1995)", + 42 + ], + [ + 770, + "Devil in a Blue Dress (1995)", + 57 + ], + [ + 771, + "Johnny Mnemonic (1995)", + 41 + ], + [ + 772, + "Kids (1995)", + 49 + ], + [ + 773, + "Mute Witness (1994)", + 17 + ], + [ + 774, + "Prophecy, The (1995)", + 32 + ], + [ + 775, + "Something to Talk About (1995)", + 26 + ], + [ + 776, + "Three Wishes (1995)", + 9 + ], + [ + 777, + "Castle Freak (1995)", + 4 + ], + [ + 778, + "Don Juan DeMarco (1995)", + 76 + ], + [ + 779, + "Drop Zone (1994)", + 31 + ], + [ + 780, + "Dumb & Dumber (1994)", + 69 + ], + [ + 781, + "French Kiss (1995)", + 84 + ], + [ + 782, + "Little Odessa (1994)", + 10 + ], + [ + 783, + "Milk Money (1994)", + 37 + ], + [ + 784, + "Beyond Bedlam (1993)", + 2 + ], + [ + 785, + "Only You (1994)", + 39 + ], + [ + 786, + "Perez Family, The (1995)", + 14 + ], + [ + 787, + "Roommates (1995)", + 13 + ], + [ + 788, + "Relative Fear (1994)", + 3 + ], + [ + 789, + "Swimming with Sharks (1995)", + 47 + ], + [ + 790, + "Tommy Boy (1995)", + 66 + ], + [ + 791, + "Baby-Sitters Club, The (1995)", + 10 + ], + [ + 792, + "Bullets Over Broadway (1994)", + 86 + ], + [ + 793, + "Crooklyn (1994)", + 10 + ], + [ + 794, + "It Could Happen to You (1994)", + 46 + ], + [ + 795, + "Richie Rich (1994)", + 21 + ], + [ + 796, + "Speechless (1994)", + 36 + ], + [ + 797, + "Timecop (1994)", + 31 + ], + [ + 798, + "Bad Company (1995)", + 9 + ], + [ + 799, + "Boys Life (1995)", + 5 + ], + [ + 800, + "In the Mouth of Madness (1995)", + 26 + ], + [ + 801, + "Air Up There, The (1994)", + 16 + ], + [ + 802, + "Hard Target (1993)", + 40 + ], + [ + 803, + "Heaven & Earth (1993)", + 9 + ], + [ + 804, + "Jimmy Hollywood (1994)", + 8 + ], + [ + 805, + "Manhattan Murder Mystery (1993)", + 27 + ], + [ + 806, + "Menace II Society (1993)", + 50 + ], + [ + 807, + "Poetic Justice (1993)", + 9 + ], + [ + 808, + "Program, The (1993)", + 31 + ], + [ + 809, + "Rising Sun (1993)", + 43 + ], + [ + 810, + "Shadow, The (1994)", + 45 + ], + [ + 811, + "Thirty-Two Short Films About Glenn Gould (1993)", + 18 + ], + [ + 812, + "Andre (1994)", + 18 + ], + [ + 813, + "Celluloid Closet, The (1995)", + 56 + ], + [ + 814, + "Great Day in Harlem, A (1994)", + 1 + ], + [ + 815, + "One Fine Day (1996)", + 112 + ], + [ + 816, + "Candyman: Farewell to the Flesh (1995)", + 21 + ], + [ + 817, + "Frisk (1995)", + 3 + ], + [ + 818, + "Girl 6 (1996)", + 25 + ], + [ + 819, + "Eddie (1996)", + 40 + ], + [ + 820, + "Space Jam (1996)", + 93 + ], + [ + 821, + "Mrs. Winterbourne (1996)", + 22 + ], + [ + 822, + "Faces (1968)", + 4 + ], + [ + 823, + "Mulholland Falls (1996)", + 82 + ], + [ + 824, + "Great White Hype, The (1996)", + 49 + ], + [ + 825, + "Arrival, The (1996)", + 83 + ], + [ + 826, + "Phantom, The (1996)", + 80 + ], + [ + 827, + "Daylight (1996)", + 57 + ], + [ + 828, + "Alaska (1996)", + 13 + ], + [ + 829, + "Fled (1996)", + 34 + ], + [ + 830, + "Power 98 (1995)", + 1 + ], + [ + 831, + "Escape from L.A. (1996)", + 91 + ], + [ + 832, + "Bogus (1996)", + 22 + ], + [ + 833, + "Bulletproof (1996)", + 49 + ], + [ + 834, + "Halloween: The Curse of Michael Myers (1995)", + 25 + ], + [ + 835, + "Gay Divorcee, The (1934)", + 15 + ], + [ + 836, + "Ninotchka (1939)", + 26 + ], + [ + 837, + "Meet John Doe (1941)", + 25 + ], + [ + 838, + "In the Line of Duty 2 (1987)", + 4 + ], + [ + 839, + "Loch Ness (1995)", + 4 + ], + [ + 840, + "Last Man Standing (1996)", + 53 + ], + [ + 841, + "Glimmer Man, The (1996)", + 48 + ], + [ + 842, + "Pollyanna (1960)", + 27 + ], + [ + 843, + "Shaggy Dog, The (1959)", + 30 + ], + [ + 844, + "Freeway (1996)", + 42 + ], + [ + 845, + "That Thing You Do! (1996)", + 176 + ], + [ + 846, + "To Gillian on Her 37th Birthday (1996)", + 44 + ], + [ + 847, + "Looking for Richard (1996)", + 55 + ], + [ + 848, + "Murder, My Sweet (1944)", + 9 + ], + [ + 849, + "Days of Thunder (1990)", + 53 + ], + [ + 850, + "Perfect Candidate, A (1996)", + 4 + ], + [ + 851, + "Two or Three Things I Know About Her (1966)", + 4 + ], + [ + 852, + "Bloody Child, The (1996)", + 1 + ], + [ + 853, + "Braindead (1992)", + 14 + ], + [ + 854, + "Bad Taste (1987)", + 16 + ], + [ + 855, + "Diva (1981)", + 66 + ], + [ + 856, + "Night on Earth (1991)", + 36 + ], + [ + 857, + "Paris Was a Woman (1995)", + 1 + ], + [ + 858, + "Amityville: Dollhouse (1996)", + 3 + ], + [ + 859, + "April Fool's Day (1986)", + 15 + ], + [ + 860, + "Believers, The (1987)", + 16 + ], + [ + 861, + "Nosferatu a Venezia (1986)", + 3 + ], + [ + 862, + "Jingle All the Way (1996)", + 18 + ], + [ + 863, + "Garden of Finzi-Contini, The (Giardino dei Finzi-Contini, Il) (1970)", + 24 + ], + [ + 864, + "My Fellow Americans (1996)", + 86 + ], + [ + 865, + "Ice Storm, The (1997)", + 21 + ], + [ + 866, + "Michael (1996)", + 119 + ], + [ + 867, + "Whole Wide World, The (1996)", + 6 + ], + [ + 868, + "Hearts and Minds (1996)", + 5 + ], + [ + 869, + "Fools Rush In (1997)", + 24 + ], + [ + 870, + "Touch (1997)", + 9 + ], + [ + 871, + "Vegas Vacation (1997)", + 75 + ], + [ + 872, + "Love Jones (1997)", + 42 + ], + [ + 873, + "Picture Perfect (1997)", + 81 + ], + [ + 874, + "Career Girls (1997)", + 39 + ], + [ + 875, + "She's So Lovely (1997)", + 53 + ], + [ + 876, + "Money Talks (1997)", + 47 + ], + [ + 877, + "Excess Baggage (1997)", + 52 + ], + [ + 878, + "That Darn Cat! (1997)", + 33 + ], + [ + 879, + "Peacemaker, The (1997)", + 136 + ], + [ + 880, + "Soul Food (1997)", + 59 + ], + [ + 881, + "Money Talks (1997)", + 45 + ], + [ + 882, + "Washington Square (1997)", + 34 + ], + [ + 883, + "Telling Lies in America (1997)", + 13 + ], + [ + 884, + "Year of the Horse (1997)", + 7 + ], + [ + 885, + "Phantoms (1998)", + 13 + ], + [ + 886, + "Life Less Ordinary, A (1997)", + 53 + ], + [ + 887, + "Eve's Bayou (1997)", + 64 + ], + [ + 888, + "One Night Stand (1997)", + 15 + ], + [ + 889, + "Tango Lesson, The (1997)", + 13 + ], + [ + 890, + "Mortal Kombat: Annihilation (1997)", + 43 + ], + [ + 891, + "Bent (1997)", + 6 + ], + [ + 892, + "Flubber (1997)", + 53 + ], + [ + 893, + "For Richer or Poorer (1997)", + 14 + ], + [ + 894, + "Home Alone 3 (1997)", + 19 + ], + [ + 895, + "Scream 2 (1997)", + 106 + ], + [ + 896, + "Sweet Hereafter, The (1997)", + 44 + ], + [ + 897, + "Time Tracers (1995)", + 2 + ], + [ + 898, + "Postman, The (1997)", + 58 + ], + [ + 899, + "Winter Guest, The (1997)", + 9 + ], + [ + 900, + "Kundun (1997)", + 42 + ], + [ + 901, + "Mr. Magoo (1997)", + 12 + ], + [ + 902, + "Big Lebowski, The (1998)", + 42 + ], + [ + 903, + "Afterglow (1997)", + 18 + ], + [ + 904, + "Ma vie en rose (My Life in Pink) (1997)", + 20 + ], + [ + 905, + "Great Expectations (1998)", + 27 + ], + [ + 906, + "Oscar & Lucinda (1997)", + 21 + ], + [ + 907, + "Vermin (1998)", + 2 + ], + [ + 908, + "Half Baked (1998)", + 20 + ], + [ + 909, + "Dangerous Beauty (1998)", + 13 + ], + [ + 910, + "Nil By Mouth (1997)", + 4 + ], + [ + 911, + "Twilight (1998)", + 4 + ], + [ + 912, + "U.S. Marshalls (1998)", + 9 + ], + [ + 913, + "Love and Death on Long Island (1997)", + 2 + ], + [ + 914, + "Wild Things (1998)", + 11 + ], + [ + 915, + "Primary Colors (1998)", + 13 + ], + [ + 916, + "Lost in Space (1998)", + 18 + ], + [ + 917, + "Mercury Rising (1998)", + 7 + ], + [ + 918, + "City of Angels (1998)", + 8 + ], + [ + 919, + "City of Lost Children, The (1995)", + 96 + ], + [ + 920, + "Two Bits (1995)", + 5 + ], + [ + 921, + "Farewell My Concubine (1993)", + 46 + ], + [ + 922, + "Dead Man (1995)", + 34 + ], + [ + 923, + "Raise the Red Lantern (1991)", + 58 + ], + [ + 924, + "White Squall (1996)", + 85 + ], + [ + 925, + "Unforgettable (1996)", + 34 + ], + [ + 926, + "Down Periscope (1996)", + 101 + ], + [ + 927, + "Flower of My Secret, The (Flor de mi secreto, La) (1995)", + 6 + ], + [ + 928, + "Craft, The (1996)", + 104 + ], + [ + 929, + "Harriet the Spy (1996)", + 40 + ], + [ + 930, + "Chain Reaction (1996)", + 80 + ], + [ + 931, + "Island of Dr. Moreau, The (1996)", + 57 + ], + [ + 932, + "First Kid (1996)", + 40 + ], + [ + 933, + "Funeral, The (1996)", + 21 + ], + [ + 934, + "Preacher's Wife, The (1996)", + 68 + ], + [ + 935, + "Paradise Road (1997)", + 7 + ], + [ + 936, + "Brassed Off (1996)", + 32 + ], + [ + 937, + "Thousand Acres, A (1997)", + 37 + ], + [ + 938, + "Smile Like Yours, A (1997)", + 25 + ], + [ + 939, + "Murder in the First (1995)", + 60 + ], + [ + 940, + "Airheads (1994)", + 32 + ], + [ + 941, + "With Honors (1994)", + 46 + ], + [ + 942, + "What's Love Got to Do with It (1993)", + 45 + ], + [ + 943, + "Killing Zoe (1994)", + 40 + ], + [ + 944, + "Renaissance Man (1994)", + 43 + ], + [ + 945, + "Charade (1963)", + 40 + ], + [ + 946, + "Fox and the Hound, The (1981)", + 61 + ], + [ + 947, + "Big Blue, The (Grand bleu, Le) (1988)", + 17 + ], + [ + 948, + "Booty Call (1997)", + 48 + ], + [ + 949, + "How to Make an American Quilt (1995)", + 71 + ], + [ + 950, + "Georgia (1995)", + 30 + ], + [ + 951, + "Indian in the Cupboard, The (1995)", + 39 + ], + [ + 952, + "Blue in the Face (1995)", + 45 + ], + [ + 953, + "Unstrung Heroes (1995)", + 22 + ], + [ + 954, + "Unzipped (1995)", + 11 + ], + [ + 955, + "Before Sunrise (1995)", + 49 + ], + [ + 956, + "Nobody's Fool (1994)", + 46 + ], + [ + 957, + "Pushing Hands (1992)", + 2 + ], + [ + 958, + "To Live (Huozhe) (1994)", + 14 + ], + [ + 959, + "Dazed and Confused (1993)", + 64 + ], + [ + 960, + "Naked (1993)", + 25 + ], + [ + 961, + "Orlando (1993)", + 34 + ], + [ + 962, + "Ruby in Paradise (1993)", + 23 + ], + [ + 963, + "Some Folks Call It a Sling Blade (1993)", + 41 + ], + [ + 964, + "Month by the Lake, A (1995)", + 9 + ], + [ + 965, + "Funny Face (1957)", + 21 + ], + [ + 966, + "Affair to Remember, An (1957)", + 26 + ], + [ + 967, + "Little Lord Fauntleroy (1936)", + 12 + ], + [ + 968, + "Inspector General, The (1949)", + 18 + ], + [ + 969, + "Winnie the Pooh and the Blustery Day (1968)", + 75 + ], + [ + 970, + "Hear My Song (1991)", + 8 + ], + [ + 971, + "Mediterraneo (1991)", + 34 + ], + [ + 972, + "Passion Fish (1992)", + 28 + ], + [ + 973, + "Grateful Dead (1995)", + 4 + ], + [ + 974, + "Eye for an Eye (1996)", + 32 + ], + [ + 975, + "Fear (1996)", + 44 + ], + [ + 976, + "Solo (1996)", + 12 + ], + [ + 977, + "Substitute, The (1996)", + 49 + ], + [ + 978, + "Heaven's Prisoners (1996)", + 27 + ], + [ + 979, + "Trigger Effect, The (1996)", + 35 + ], + [ + 980, + "Mother Night (1996)", + 22 + ], + [ + 981, + "Dangerous Ground (1997)", + 8 + ], + [ + 982, + "Maximum Risk (1996)", + 20 + ], + [ + 983, + "Rich Man's Wife, The (1996)", + 15 + ], + [ + 984, + "Shadow Conspiracy (1997)", + 44 + ], + [ + 985, + "Blood & Wine (1997)", + 22 + ], + [ + 986, + "Turbulence (1997)", + 23 + ], + [ + 987, + "Underworld (1997)", + 4 + ], + [ + 988, + "Beautician and the Beast, The (1997)", + 86 + ], + [ + 989, + "Cats Don't Dance (1997)", + 32 + ], + [ + 990, + "Anna Karenina (1997)", + 33 + ], + [ + 991, + "Keys to Tulsa (1997)", + 25 + ], + [ + 992, + "Head Above Water (1996)", + 4 + ], + [ + 993, + "Hercules (1997)", + 66 + ], + [ + 994, + "Last Time I Committed Suicide, The (1997)", + 7 + ], + [ + 995, + "Kiss Me, Guido (1997)", + 31 + ], + [ + 996, + "Big Green, The (1995)", + 14 + ], + [ + 997, + "Stuart Saves His Family (1995)", + 16 + ], + [ + 998, + "Cabin Boy (1994)", + 16 + ], + [ + 999, + "Clean Slate (1994)", + 10 + ], + [ + 1000, + "Lightning Jack (1994)", + 10 + ], + [ + 1001, + "Stupids, The (1996)", + 17 + ], + [ + 1002, + "Pest, The (1997)", + 8 + ], + [ + 1003, + "That Darn Cat! (1997)", + 8 + ], + [ + 1004, + "Geronimo: An American Legend (1993)", + 9 + ], + [ + 1005, + "Double vie de Véronique, La (Double Life of Veronique, The) (1991)", + 22 + ], + [ + 1006, + "Until the End of the World (Bis ans Ende der Welt) (1991)", + 23 + ], + [ + 1007, + "Waiting for Guffman (1996)", + 47 + ], + [ + 1008, + "I Shot Andy Warhol (1996)", + 37 + ], + [ + 1009, + "Stealing Beauty (1996)", + 64 + ], + [ + 1010, + "Basquiat (1996)", + 44 + ], + [ + 1011, + "2 Days in the Valley (1996)", + 93 + ], + [ + 1012, + "Private Parts (1997)", + 100 + ], + [ + 1013, + "Anaconda (1997)", + 38 + ], + [ + 1014, + "Romy and Michele's High School Reunion (1997)", + 98 + ], + [ + 1015, + "Shiloh (1997)", + 12 + ], + [ + 1016, + "Con Air (1997)", + 137 + ], + [ + 1017, + "Trees Lounge (1996)", + 50 + ], + [ + 1018, + "Tie Me Up! Tie Me Down! (1990)", + 32 + ], + [ + 1019, + "Die xue shuang xiong (Killer, The) (1989)", + 31 + ], + [ + 1020, + "Gaslight (1944)", + 35 + ], + [ + 1021, + "8 1/2 (1963)", + 38 + ], + [ + 1022, + "Fast, Cheap & Out of Control (1997)", + 32 + ], + [ + 1023, + "Fathers' Day (1997)", + 31 + ], + [ + 1024, + "Mrs. Dalloway (1997)", + 15 + ], + [ + 1025, + "Fire Down Below (1997)", + 44 + ], + [ + 1026, + "Lay of the Land, The (1997)", + 4 + ], + [ + 1027, + "Shooter, The (1995)", + 3 + ], + [ + 1028, + "Grumpier Old Men (1995)", + 148 + ], + [ + 1029, + "Jury Duty (1995)", + 14 + ], + [ + 1030, + "Beverly Hillbillies, The (1993)", + 20 + ], + [ + 1031, + "Lassie (1994)", + 7 + ], + [ + 1032, + "Little Big League (1994)", + 16 + ], + [ + 1033, + "Homeward Bound II: Lost in San Francisco (1996)", + 32 + ], + [ + 1034, + "Quest, The (1996)", + 27 + ], + [ + 1035, + "Cool Runnings (1993)", + 68 + ], + [ + 1036, + "Drop Dead Fred (1991)", + 24 + ], + [ + 1037, + "Grease 2 (1982)", + 24 + ], + [ + 1038, + "Switchback (1997)", + 17 + ], + [ + 1039, + "Hamlet (1996)", + 90 + ], + [ + 1040, + "Two if by Sea (1996)", + 25 + ], + [ + 1041, + "Forget Paris (1995)", + 62 + ], + [ + 1042, + "Just Cause (1995)", + 28 + ], + [ + 1043, + "Rent-a-Kid (1995)", + 8 + ], + [ + 1044, + "Paper, The (1994)", + 40 + ], + [ + 1045, + "Fearless (1993)", + 25 + ], + [ + 1046, + "Malice (1993)", + 46 + ], + [ + 1047, + "Multiplicity (1996)", + 134 + ], + [ + 1048, + "She's the One (1996)", + 73 + ], + [ + 1049, + "House Arrest (1996)", + 25 + ], + [ + 1050, + "Ghost and Mrs. Muir, The (1947)", + 43 + ], + [ + 1051, + "Associate, The (1996)", + 41 + ], + [ + 1052, + "Dracula: Dead and Loving It (1995)", + 25 + ], + [ + 1053, + "Now and Then (1995)", + 24 + ], + [ + 1054, + "Mr. Wrong (1996)", + 23 + ], + [ + 1055, + "Simple Twist of Fate, A (1994)", + 10 + ], + [ + 1056, + "Cronos (1992)", + 10 + ], + [ + 1057, + "Pallbearer, The (1996)", + 22 + ], + [ + 1058, + "War, The (1994)", + 15 + ], + [ + 1059, + "Don't Be a Menace to South Central While Drinking Your Juice in the Hood (1996)", + 35 + ], + [ + 1060, + "Adventures of Pinocchio, The (1996)", + 39 + ], + [ + 1061, + "Evening Star, The (1996)", + 29 + ], + [ + 1062, + "Four Days in September (1997)", + 12 + ], + [ + 1063, + "Little Princess, A (1995)", + 41 + ], + [ + 1064, + "Crossfire (1947)", + 4 + ], + [ + 1065, + "Koyaanisqatsi (1983)", + 53 + ], + [ + 1066, + "Balto (1995)", + 16 + ], + [ + 1067, + "Bottle Rocket (1996)", + 44 + ], + [ + 1068, + "Star Maker, The (Uomo delle stelle, L') (1995)", + 12 + ], + [ + 1069, + "Amateur (1994)", + 18 + ], + [ + 1070, + "Living in Oblivion (1995)", + 27 + ], + [ + 1071, + "Party Girl (1995)", + 16 + ], + [ + 1072, + "Pyromaniac's Love Story, A (1995)", + 7 + ], + [ + 1073, + "Shallow Grave (1994)", + 66 + ], + [ + 1074, + "Reality Bites (1994)", + 77 + ], + [ + 1075, + "Man of No Importance, A (1994)", + 7 + ], + [ + 1076, + "Pagemaster, The (1994)", + 12 + ], + [ + 1077, + "Love and a .45 (1994)", + 8 + ], + [ + 1078, + "Oliver & Company (1988)", + 22 + ], + [ + 1079, + "Joe's Apartment (1996)", + 45 + ], + [ + 1080, + "Celestial Clockwork (1994)", + 2 + ], + [ + 1081, + "Curdled (1996)", + 8 + ], + [ + 1082, + "Female Perversions (1996)", + 8 + ], + [ + 1083, + "Albino Alligator (1996)", + 6 + ], + [ + 1084, + "Anne Frank Remembered (1995)", + 21 + ], + [ + 1085, + "Carried Away (1996)", + 11 + ], + [ + 1086, + "It's My Party (1995)", + 21 + ], + [ + 1087, + "Bloodsport 2 (1995)", + 10 + ], + [ + 1088, + "Double Team (1997)", + 13 + ], + [ + 1089, + "Speed 2: Cruise Control (1997)", + 38 + ], + [ + 1090, + "Sliver (1993)", + 37 + ], + [ + 1091, + "Pete's Dragon (1977)", + 43 + ], + [ + 1092, + "Dear God (1996)", + 12 + ], + [ + 1093, + "Live Nude Girls (1995)", + 23 + ], + [ + 1094, + "Thin Line Between Love and Hate, A (1996)", + 12 + ], + [ + 1095, + "High School High (1996)", + 29 + ], + [ + 1096, + "Commandments (1997)", + 3 + ], + [ + 1097, + "Hate (Haine, La) (1995)", + 18 + ], + [ + 1098, + "Flirting With Disaster (1996)", + 42 + ], + [ + 1099, + "Red Firecracker, Green Firecracker (1994)", + 13 + ], + [ + 1100, + "What Happened Was... (1994)", + 8 + ], + [ + 1101, + "Six Degrees of Separation (1993)", + 74 + ], + [ + 1102, + "Two Much (1996)", + 7 + ], + [ + 1103, + "Trust (1990)", + 19 + ], + [ + 1104, + "C'est arrivé près de chez vous (1992)", + 4 + ], + [ + 1105, + "Firestorm (1998)", + 18 + ], + [ + 1106, + "Newton Boys, The (1998)", + 4 + ], + [ + 1107, + "Beyond Rangoon (1995)", + 18 + ], + [ + 1108, + "Feast of July (1995)", + 5 + ], + [ + 1109, + "Death and the Maiden (1994)", + 28 + ], + [ + 1110, + "Tank Girl (1995)", + 41 + ], + [ + 1111, + "Double Happiness (1994)", + 7 + ], + [ + 1112, + "Cobb (1994)", + 15 + ], + [ + 1113, + "Mrs. Parker and the Vicious Circle (1994)", + 22 + ], + [ + 1114, + "Faithful (1996)", + 10 + ], + [ + 1115, + "Twelfth Night (1996)", + 29 + ], + [ + 1116, + "Mark of Zorro, The (1940)", + 13 + ], + [ + 1117, + "Surviving Picasso (1996)", + 19 + ], + [ + 1118, + "Up in Smoke (1978)", + 47 + ], + [ + 1119, + "Some Kind of Wonderful (1987)", + 59 + ], + [ + 1120, + "I'm Not Rappaport (1996)", + 17 + ], + [ + 1121, + "Umbrellas of Cherbourg, The (Parapluies de Cherbourg, Les) (1964)", + 21 + ], + [ + 1122, + "They Made Me a Criminal (1939)", + 1 + ], + [ + 1123, + "Last Time I Saw Paris, The (1954)", + 3 + ], + [ + 1124, + "Farewell to Arms, A (1932)", + 12 + ], + [ + 1125, + "Innocents, The (1961)", + 4 + ], + [ + 1126, + "Old Man and the Sea, The (1958)", + 32 + ], + [ + 1127, + "Truman Show, The (1998)", + 11 + ], + [ + 1128, + "Heidi Fleiss: Hollywood Madam (1995) ", + 13 + ], + [ + 1129, + "Chungking Express (1994)", + 28 + ], + [ + 1130, + "Jupiter's Wife (1994)", + 1 + ], + [ + 1131, + "Safe (1995)", + 13 + ], + [ + 1132, + "Feeling Minnesota (1996)", + 32 + ], + [ + 1133, + "Escape to Witch Mountain (1975)", + 30 + ], + [ + 1134, + "Get on the Bus (1996)", + 38 + ], + [ + 1135, + "Doors, The (1991)", + 46 + ], + [ + 1136, + "Ghosts of Mississippi (1996)", + 29 + ], + [ + 1137, + "Beautiful Thing (1996)", + 29 + ], + [ + 1138, + "Best Men (1997)", + 5 + ], + [ + 1139, + "Hackers (1995)", + 33 + ], + [ + 1140, + "Road to Wellville, The (1994)", + 17 + ], + [ + 1141, + "War Room, The (1993)", + 9 + ], + [ + 1142, + "When We Were Kings (1996)", + 44 + ], + [ + 1143, + "Hard Eight (1996)", + 15 + ], + [ + 1144, + "Quiet Room, The (1996)", + 3 + ], + [ + 1145, + "Blue Chips (1994)", + 9 + ], + [ + 1146, + "Calendar Girl (1993)", + 3 + ], + [ + 1147, + "My Family (1995)", + 21 + ], + [ + 1148, + "Tom & Viv (1994)", + 9 + ], + [ + 1149, + "Walkabout (1971)", + 26 + ], + [ + 1150, + "Last Dance (1996)", + 9 + ], + [ + 1151, + "Original Gangstas (1996)", + 7 + ], + [ + 1152, + "In Love and War (1996)", + 28 + ], + [ + 1153, + "Backbeat (1993)", + 19 + ], + [ + 1154, + "Alphaville (1965)", + 12 + ], + [ + 1155, + "Rendezvous in Paris (Rendez-vous de Paris, Les) (1995)", + 3 + ], + [ + 1156, + "Cyclo (1995)", + 1 + ], + [ + 1157, + "Relic, The (1997)", + 25 + ], + [ + 1158, + "Fille seule, La (A Single Girl) (1995)", + 4 + ], + [ + 1159, + "Stalker (1979)", + 11 + ], + [ + 1160, + "Love! Valour! Compassion! (1997)", + 26 + ], + [ + 1161, + "Palookaville (1996)", + 13 + ], + [ + 1162, + "Phat Beach (1996)", + 5 + ], + [ + 1163, + "Portrait of a Lady, The (1996)", + 25 + ], + [ + 1164, + "Zeus and Roxanne (1997)", + 6 + ], + [ + 1165, + "Big Bully (1996)", + 14 + ], + [ + 1166, + "Love & Human Remains (1993)", + 12 + ], + [ + 1167, + "Sum of Us, The (1994)", + 11 + ], + [ + 1168, + "Little Buddha (1993)", + 22 + ], + [ + 1169, + "Fresh (1994)", + 10 + ], + [ + 1170, + "Spanking the Monkey (1994)", + 27 + ], + [ + 1171, + "Wild Reeds (1994)", + 14 + ], + [ + 1172, + "Women, The (1939)", + 15 + ], + [ + 1173, + "Bliss (1997)", + 7 + ], + [ + 1174, + "Caught (1996)", + 8 + ], + [ + 1175, + "Hugo Pool (1997)", + 5 + ], + [ + 1176, + "Welcome To Sarajevo (1997)", + 22 + ], + [ + 1177, + "Dunston Checks In (1996)", + 7 + ], + [ + 1178, + "Major Payne (1994)", + 19 + ], + [ + 1179, + "Man of the House (1995)", + 9 + ], + [ + 1180, + "I Love Trouble (1994)", + 10 + ], + [ + 1181, + "Low Down Dirty Shame, A (1994)", + 10 + ], + [ + 1182, + "Cops and Robbersons (1994)", + 13 + ], + [ + 1183, + "Cowboy Way, The (1994)", + 19 + ], + [ + 1184, + "Endless Summer 2, The (1994)", + 10 + ], + [ + 1185, + "In the Army Now (1994)", + 18 + ], + [ + 1186, + "Inkwell, The (1994)", + 3 + ], + [ + 1187, + "Switchblade Sisters (1975)", + 13 + ], + [ + 1188, + "Young Guns II (1990)", + 44 + ], + [ + 1189, + "Prefontaine (1997)", + 3 + ], + [ + 1190, + "That Old Feeling (1997)", + 11 + ], + [ + 1191, + "Letter From Death Row, A (1998)", + 3 + ], + [ + 1192, + "Boys of St. Vincent, The (1993)", + 13 + ], + [ + 1193, + "Before the Rain (Pred dozhdot) (1994)", + 10 + ], + [ + 1194, + "Once Were Warriors (1994)", + 31 + ], + [ + 1195, + "Strawberry and Chocolate (Fresa y chocolate) (1993)", + 11 + ], + [ + 1196, + "Savage Nights (Nuits fauves, Les) (1992)", + 3 + ], + [ + 1197, + "Family Thing, A (1996)", + 45 + ], + [ + 1198, + "Purple Noon (1960)", + 7 + ], + [ + 1199, + "Cemetery Man (Dellamorte Dellamore) (1994)", + 23 + ], + [ + 1200, + "Kim (1950)", + 7 + ], + [ + 1201, + "Marlene Dietrich: Shadow and Light (1996) ", + 1 + ], + [ + 1202, + "Maybe, Maybe Not (Bewegte Mann, Der) (1994)", + 8 + ], + [ + 1203, + "Top Hat (1935)", + 21 + ], + [ + 1204, + "To Be or Not to Be (1942)", + 18 + ], + [ + 1205, + "Secret Agent, The (1996)", + 6 + ], + [ + 1206, + "Amos & Andrew (1993)", + 19 + ], + [ + 1207, + "Jade (1995)", + 17 + ], + [ + 1208, + "Kiss of Death (1995)", + 20 + ], + [ + 1209, + "Mixed Nuts (1994)", + 15 + ], + [ + 1210, + "Virtuosity (1995)", + 38 + ], + [ + 1211, + "Blue Sky (1994)", + 12 + ], + [ + 1212, + "Flesh and Bone (1993)", + 6 + ], + [ + 1213, + "Guilty as Sin (1993)", + 6 + ], + [ + 1214, + "In the Realm of the Senses (Ai no corrida) (1976)", + 9 + ], + [ + 1215, + "Barb Wire (1996)", + 30 + ], + [ + 1216, + "Kissed (1996)", + 6 + ], + [ + 1217, + "Assassins (1995)", + 39 + ], + [ + 1218, + "Friday (1995)", + 26 + ], + [ + 1219, + "Goofy Movie, A (1995)", + 20 + ], + [ + 1220, + "Higher Learning (1995)", + 30 + ], + [ + 1221, + "When a Man Loves a Woman (1994)", + 39 + ], + [ + 1222, + "Judgment Night (1993)", + 25 + ], + [ + 1223, + "King of the Hill (1993)", + 4 + ], + [ + 1224, + "Scout, The (1994)", + 12 + ], + [ + 1225, + "Angus (1995)", + 14 + ], + [ + 1226, + "Night Falls on Manhattan (1997)", + 32 + ], + [ + 1227, + "Awfully Big Adventure, An (1995)", + 8 + ], + [ + 1228, + "Under Siege 2: Dark Territory (1995)", + 48 + ], + [ + 1229, + "Poison Ivy II (1995)", + 13 + ], + [ + 1230, + "Ready to Wear (Pret-A-Porter) (1994)", + 18 + ], + [ + 1231, + "Marked for Death (1990)", + 22 + ], + [ + 1232, + "Madonna: Truth or Dare (1991)", + 17 + ], + [ + 1233, + "Nénette et Boni (1996)", + 6 + ], + [ + 1234, + "Chairman of the Board (1998)", + 8 + ], + [ + 1235, + "Big Bang Theory, The (1994)", + 1 + ], + [ + 1236, + "Other Voices, Other Rooms (1997)", + 1 + ], + [ + 1237, + "Twisted (1996)", + 6 + ], + [ + 1238, + "Full Speed (1996)", + 8 + ], + [ + 1239, + "Cutthroat Island (1995)", + 18 + ], + [ + 1240, + "Ghost in the Shell (Kokaku kidotai) (1995)", + 26 + ], + [ + 1241, + "Van, The (1996)", + 6 + ], + [ + 1242, + "Old Lady Who Walked in the Sea, The (Vieille qui marchait dans la mer, La) (1991)", + 5 + ], + [ + 1243, + "Night Flier (1997)", + 7 + ], + [ + 1244, + "Metro (1997)", + 36 + ], + [ + 1245, + "Gridlock'd (1997)", + 19 + ], + [ + 1246, + "Bushwhacked (1995)", + 7 + ], + [ + 1247, + "Bad Girls (1994)", + 6 + ], + [ + 1248, + "Blink (1994)", + 19 + ], + [ + 1249, + "For Love or Money (1993)", + 12 + ], + [ + 1250, + "Best of the Best 3: No Turning Back (1995)", + 6 + ], + [ + 1251, + "A Chef in Love (1996)", + 8 + ], + [ + 1252, + "Contempt (Mépris, Le) (1963)", + 9 + ], + [ + 1253, + "Tie That Binds, The (1995)", + 7 + ], + [ + 1254, + "Gone Fishin' (1997)", + 11 + ], + [ + 1255, + "Broken English (1996)", + 8 + ], + [ + 1256, + "Designated Mourner, The (1997)", + 3 + ], + [ + 1257, + "Designated Mourner, The (1997)", + 4 + ], + [ + 1258, + "Trial and Error (1997)", + 23 + ], + [ + 1259, + "Pie in the Sky (1995)", + 4 + ], + [ + 1260, + "Total Eclipse (1995)", + 4 + ], + [ + 1261, + "Run of the Country, The (1995)", + 4 + ], + [ + 1262, + "Walking and Talking (1996)", + 8 + ], + [ + 1263, + "Foxfire (1996)", + 15 + ], + [ + 1264, + "Nothing to Lose (1994)", + 7 + ], + [ + 1265, + "Star Maps (1997)", + 19 + ], + [ + 1266, + "Bread and Chocolate (Pane e cioccolata) (1973)", + 12 + ], + [ + 1267, + "Clockers (1995)", + 33 + ], + [ + 1268, + "Bitter Moon (1992)", + 10 + ], + [ + 1269, + "Love in the Afternoon (1957)", + 10 + ], + [ + 1270, + "Life with Mikey (1993)", + 7 + ], + [ + 1271, + "North (1994)", + 7 + ], + [ + 1272, + "Talking About Sex (1994)", + 5 + ], + [ + 1273, + "Color of Night (1994)", + 15 + ], + [ + 1274, + "Robocop 3 (1993)", + 11 + ], + [ + 1275, + "Killer (Bulletproof Heart) (1994)", + 4 + ], + [ + 1276, + "Sunset Park (1996)", + 8 + ], + [ + 1277, + "Set It Off (1996)", + 19 + ], + [ + 1278, + "Selena (1997)", + 16 + ], + [ + 1279, + "Wild America (1997)", + 9 + ], + [ + 1280, + "Gang Related (1997)", + 16 + ], + [ + 1281, + "Manny & Lo (1996)", + 13 + ], + [ + 1282, + "Grass Harp, The (1995)", + 9 + ], + [ + 1283, + "Out to Sea (1997)", + 19 + ], + [ + 1284, + "Before and After (1996)", + 26 + ], + [ + 1285, + "Princess Caraboo (1994)", + 15 + ], + [ + 1286, + "Shall We Dance? (1937)", + 17 + ], + [ + 1287, + "Ed (1996)", + 6 + ], + [ + 1288, + "Denise Calls Up (1995)", + 7 + ], + [ + 1289, + "Jack and Sarah (1995)", + 7 + ], + [ + 1290, + "Country Life (1994)", + 2 + ], + [ + 1291, + "Celtic Pride (1996)", + 15 + ], + [ + 1292, + "Simple Wish, A (1997)", + 3 + ], + [ + 1293, + "Star Kid (1997)", + 3 + ], + [ + 1294, + "Ayn Rand: A Sense of Life (1997)", + 7 + ], + [ + 1295, + "Kicked in the Head (1997)", + 7 + ], + [ + 1296, + "Indian Summer (1996)", + 20 + ], + [ + 1297, + "Love Affair (1994)", + 12 + ], + [ + 1298, + "Band Wagon, The (1953)", + 9 + ], + [ + 1299, + "Penny Serenade (1941)", + 8 + ], + [ + 1300, + "'Til There Was You (1997)", + 9 + ], + [ + 1301, + "Stripes (1981)", + 5 + ], + [ + 1302, + "Late Bloomers (1996)", + 5 + ], + [ + 1303, + "Getaway, The (1994)", + 18 + ], + [ + 1304, + "New York Cop (1996)", + 2 + ], + [ + 1305, + "National Lampoon's Senior Trip (1995)", + 7 + ], + [ + 1306, + "Delta of Venus (1994)", + 2 + ], + [ + 1307, + "Carmen Miranda: Bananas Is My Business (1994)", + 2 + ], + [ + 1308, + "Babyfever (1994)", + 2 + ], + [ + 1309, + "Very Natural Thing, A (1974)", + 1 + ], + [ + 1310, + "Walk in the Sun, A (1945)", + 1 + ], + [ + 1311, + "Waiting to Exhale (1995)", + 16 + ], + [ + 1312, + "Pompatus of Love, The (1996)", + 7 + ], + [ + 1313, + "Palmetto (1998)", + 14 + ], + [ + 1314, + "Surviving the Game (1994)", + 11 + ], + [ + 1315, + "Inventing the Abbotts (1997)", + 23 + ], + [ + 1316, + "Horse Whisperer, The (1998)", + 7 + ], + [ + 1317, + "Journey of August King, The (1995)", + 4 + ], + [ + 1318, + "Catwalk (1995)", + 3 + ], + [ + 1319, + "Neon Bible, The (1995)", + 4 + ], + [ + 1320, + "Homage (1995)", + 1 + ], + [ + 1321, + "Open Season (1996)", + 2 + ], + [ + 1322, + "Metisse (Café au Lait) (1993)", + 6 + ], + [ + 1323, + "Wooden Man's Bride, The (Wu Kui) (1994)", + 3 + ], + [ + 1324, + "Loaded (1994)", + 5 + ], + [ + 1325, + "August (1996)", + 1 + ], + [ + 1326, + "Boys (1996)", + 6 + ], + [ + 1327, + "Captives (1994)", + 3 + ], + [ + 1328, + "Of Love and Shadows (1994)", + 6 + ], + [ + 1329, + "Low Life, The (1994)", + 1 + ], + [ + 1330, + "An Unforgettable Summer (1994)", + 4 + ], + [ + 1331, + "Last Klezmer: Leopold Kozlowski, His Life and Music, The (1995)", + 4 + ], + [ + 1332, + "My Life and Times With Antonin Artaud (En compagnie d'Antonin Artaud) (1993)", + 2 + ], + [ + 1333, + "Midnight Dancers (Sibak) (1994)", + 5 + ], + [ + 1334, + "Somebody to Love (1994)", + 2 + ], + [ + 1335, + "American Buffalo (1996)", + 11 + ], + [ + 1336, + "Kazaam (1996)", + 10 + ], + [ + 1337, + "Larger Than Life (1996)", + 9 + ], + [ + 1338, + "Two Deaths (1995)", + 4 + ], + [ + 1339, + "Stefano Quantestorie (1993)", + 1 + ], + [ + 1340, + "Crude Oasis, The (1995)", + 1 + ], + [ + 1341, + "Hedd Wyn (1992)", + 1 + ], + [ + 1342, + "Convent, The (Convento, O) (1995)", + 2 + ], + [ + 1343, + "Lotto Land (1995)", + 1 + ], + [ + 1344, + "Story of Xinghua, The (1993)", + 5 + ], + [ + 1345, + "Day the Sun Turned Cold, The (Tianguo niezi) (1994)", + 2 + ], + [ + 1346, + "Dingo (1992)", + 5 + ], + [ + 1347, + "Ballad of Narayama, The (Narayama Bushiko) (1958)", + 4 + ], + [ + 1348, + "Every Other Weekend (1990)", + 1 + ], + [ + 1349, + "Mille bolle blu (1993)", + 1 + ], + [ + 1350, + "Crows and Sparrows (1949)", + 2 + ], + [ + 1351, + "Lover's Knot (1996)", + 3 + ], + [ + 1352, + "Shadow of Angels (Schatten der Engel) (1976)", + 1 + ], + [ + 1353, + "1-900 (1994)", + 5 + ], + [ + 1354, + "Venice/Venice (1992)", + 2 + ], + [ + 1355, + "Infinity (1996)", + 6 + ], + [ + 1356, + "Ed's Next Move (1996)", + 3 + ], + [ + 1357, + "For the Moment (1994)", + 3 + ], + [ + 1358, + "The Deadly Cure (1996)", + 2 + ], + [ + 1359, + "Boys in Venice (1996)", + 2 + ], + [ + 1360, + "Sexual Life of the Belgians, The (1994)", + 2 + ], + [ + 1361, + "Search for One-eye Jimmy, The (1996)", + 3 + ], + [ + 1362, + "American Strays (1996)", + 2 + ], + [ + 1363, + "Leopard Son, The (1996)", + 1 + ], + [ + 1364, + "Bird of Prey (1996)", + 1 + ], + [ + 1365, + "Johnny 100 Pesos (1993)", + 2 + ], + [ + 1366, + "JLG/JLG - autoportrait de décembre (1994)", + 1 + ], + [ + 1367, + "Faust (1994)", + 5 + ], + [ + 1368, + "Mina Tannenbaum (1994)", + 6 + ], + [ + 1369, + "Forbidden Christ, The (Cristo proibito, Il) (1950)", + 4 + ], + [ + 1370, + "I Can't Sleep (J'ai pas sommeil) (1994)", + 3 + ], + [ + 1371, + "Machine, The (1994)", + 2 + ], + [ + 1372, + "Stranger, The (1994)", + 3 + ], + [ + 1373, + "Good Morning (1971)", + 1 + ], + [ + 1374, + "Falling in Love Again (1980)", + 2 + ], + [ + 1375, + "Cement Garden, The (1993)", + 10 + ], + [ + 1376, + "Meet Wally Sparks (1997)", + 7 + ], + [ + 1377, + "Hotel de Love (1996)", + 4 + ], + [ + 1378, + "Rhyme & Reason (1997)", + 5 + ], + [ + 1379, + "Love and Other Catastrophes (1996)", + 7 + ], + [ + 1380, + "Hollow Reed (1996)", + 6 + ], + [ + 1381, + "Losing Chase (1996)", + 8 + ], + [ + 1382, + "Bonheur, Le (1965)", + 4 + ], + [ + 1383, + "Second Jungle Book: Mowgli & Baloo, The (1997)", + 6 + ], + [ + 1384, + "Squeeze (1996)", + 3 + ], + [ + 1385, + "Roseanna's Grave (For Roseanna) (1997)", + 5 + ], + [ + 1386, + "Tetsuo II: Body Hammer (1992)", + 6 + ], + [ + 1387, + "Fall (1997)", + 3 + ], + [ + 1388, + "Gabbeh (1996)", + 6 + ], + [ + 1389, + "Mondo (1996)", + 3 + ], + [ + 1390, + "Innocent Sleep, The (1995)", + 2 + ], + [ + 1391, + "For Ever Mozart (1996)", + 3 + ], + [ + 1392, + "Locusts, The (1997)", + 5 + ], + [ + 1393, + "Stag (1997)", + 9 + ], + [ + 1394, + "Swept from the Sea (1997)", + 7 + ], + [ + 1395, + "Hurricane Streets (1998)", + 6 + ], + [ + 1396, + "Stonewall (1995)", + 5 + ], + [ + 1397, + "Of Human Bondage (1934)", + 5 + ], + [ + 1398, + "Anna (1996)", + 2 + ], + [ + 1399, + "Stranger in the House (1997)", + 7 + ], + [ + 1400, + "Picture Bride (1995)", + 10 + ], + [ + 1401, + "M. Butterfly (1993)", + 18 + ], + [ + 1402, + "Ciao, Professore! (1993)", + 4 + ], + [ + 1403, + "Caro Diario (Dear Diary) (1994)", + 4 + ], + [ + 1404, + "Withnail and I (1987)", + 13 + ], + [ + 1405, + "Boy's Life 2 (1997)", + 6 + ], + [ + 1406, + "When Night Is Falling (1995)", + 5 + ], + [ + 1407, + "Specialist, The (1994)", + 20 + ], + [ + 1408, + "Gordy (1995)", + 3 + ], + [ + 1409, + "Swan Princess, The (1994)", + 7 + ], + [ + 1410, + "Harlem (1993)", + 4 + ], + [ + 1411, + "Barbarella (1968)", + 28 + ], + [ + 1412, + "Land Before Time III: The Time of the Great Giving (1995) (V)", + 6 + ], + [ + 1413, + "Street Fighter (1994)", + 8 + ], + [ + 1414, + "Coldblooded (1995)", + 1 + ], + [ + 1415, + "Next Karate Kid, The (1994)", + 9 + ], + [ + 1416, + "No Escape (1994)", + 5 + ], + [ + 1417, + "Turning, The (1992)", + 2 + ], + [ + 1418, + "Joy Luck Club, The (1993)", + 3 + ], + [ + 1419, + "Highlander III: The Sorcerer (1994)", + 16 + ], + [ + 1420, + "Gilligan's Island: The Movie (1998)", + 3 + ], + [ + 1421, + "My Crazy Life (Mi vida loca) (1993)", + 11 + ], + [ + 1422, + "Suture (1993)", + 4 + ], + [ + 1423, + "Walking Dead, The (1995)", + 4 + ], + [ + 1424, + "I Like It Like That (1994)", + 3 + ], + [ + 1425, + "I'll Do Anything (1994)", + 10 + ], + [ + 1426, + "Grace of My Heart (1996)", + 8 + ], + [ + 1427, + "Drunks (1995)", + 5 + ], + [ + 1428, + "SubUrbia (1997)", + 12 + ], + [ + 1429, + "Sliding Doors (1998)", + 4 + ], + [ + 1430, + "Ill Gotten Gains (1997)", + 3 + ], + [ + 1431, + "Legal Deceit (1997)", + 5 + ], + [ + 1432, + "Mighty, The (1998)", + 3 + ], + [ + 1433, + "Men of Means (1998)", + 2 + ], + [ + 1434, + "Shooting Fish (1997)", + 10 + ], + [ + 1435, + "Steal Big, Steal Little (1995)", + 7 + ], + [ + 1436, + "Mr. Jones (1993)", + 2 + ], + [ + 1437, + "House Party 3 (1994)", + 9 + ], + [ + 1438, + "Panther (1995)", + 5 + ], + [ + 1439, + "Jason's Lyric (1994)", + 8 + ], + [ + 1440, + "Above the Rim (1994)", + 5 + ], + [ + 1441, + "Moonlight and Valentino (1995)", + 7 + ], + [ + 1442, + "Scarlet Letter, The (1995)", + 5 + ], + [ + 1443, + "8 Seconds (1994)", + 4 + ], + [ + 1444, + "That Darn Cat! (1965)", + 19 + ], + [ + 1445, + "Ladybird Ladybird (1994)", + 4 + ], + [ + 1446, + "Bye Bye, Love (1995)", + 15 + ], + [ + 1447, + "Century (1993)", + 1 + ], + [ + 1448, + "My Favorite Season (1993)", + 3 + ], + [ + 1449, + "Pather Panchali (1955)", + 8 + ], + [ + 1450, + "Golden Earrings (1947)", + 2 + ], + [ + 1451, + "Foreign Correspondent (1940)", + 15 + ], + [ + 1452, + "Lady of Burlesque (1943)", + 1 + ], + [ + 1453, + "Angel on My Shoulder (1946)", + 1 + ], + [ + 1454, + "Angel and the Badman (1947)", + 6 + ], + [ + 1455, + "Outlaw, The (1943)", + 2 + ], + [ + 1456, + "Beat the Devil (1954)", + 7 + ], + [ + 1457, + "Love Is All There Is (1996)", + 1 + ], + [ + 1458, + "Damsel in Distress, A (1937)", + 1 + ], + [ + 1459, + "Madame Butterfly (1995)", + 7 + ], + [ + 1460, + "Sleepover (1995)", + 1 + ], + [ + 1461, + "Here Comes Cookie (1935)", + 1 + ], + [ + 1462, + "Thieves (Voleurs, Les) (1996)", + 7 + ], + [ + 1463, + "Boys, Les (1997)", + 3 + ], + [ + 1464, + "Stars Fell on Henrietta, The (1995)", + 3 + ], + [ + 1465, + "Last Summer in the Hamptons (1995)", + 3 + ], + [ + 1466, + "Margaret's Museum (1995)", + 6 + ], + [ + 1467, + "Saint of Fort Washington, The (1993)", + 2 + ], + [ + 1468, + "Cure, The (1995)", + 6 + ], + [ + 1469, + "Tom and Huck (1995)", + 12 + ], + [ + 1470, + "Gumby: The Movie (1995)", + 5 + ], + [ + 1471, + "Hideaway (1995)", + 9 + ], + [ + 1472, + "Visitors, The (Visiteurs, Les) (1993)", + 2 + ], + [ + 1473, + "Little Princess, The (1939)", + 9 + ], + [ + 1474, + "Nina Takes a Lover (1994)", + 6 + ], + [ + 1475, + "Bhaji on the Beach (1993)", + 8 + ], + [ + 1476, + "Raw Deal (1948)", + 1 + ], + [ + 1477, + "Nightwatch (1997)", + 2 + ], + [ + 1478, + "Dead Presidents (1995)", + 18 + ], + [ + 1479, + "Reckless (1995)", + 8 + ], + [ + 1480, + "Herbie Rides Again (1974)", + 11 + ], + [ + 1481, + "S.F.W. (1994)", + 2 + ], + [ + 1482, + "Gate of Heavenly Peace, The (1995)", + 1 + ], + [ + 1483, + "Man in the Iron Mask, The (1998)", + 12 + ], + [ + 1484, + "Jerky Boys, The (1994)", + 3 + ], + [ + 1485, + "Colonel Chabert, Le (1994)", + 4 + ], + [ + 1486, + "Girl in the Cadillac (1995)", + 1 + ], + [ + 1487, + "Even Cowgirls Get the Blues (1993)", + 5 + ], + [ + 1488, + "Germinal (1993)", + 4 + ], + [ + 1489, + "Chasers (1994)", + 5 + ], + [ + 1490, + "Fausto (1993)", + 3 + ], + [ + 1491, + "Tough and Deadly (1995)", + 2 + ], + [ + 1492, + "Window to Paris (1994)", + 1 + ], + [ + 1493, + "Modern Affair, A (1995)", + 1 + ], + [ + 1494, + "Mostro, Il (1994)", + 1 + ], + [ + 1495, + "Flirt (1995)", + 5 + ], + [ + 1496, + "Carpool (1996)", + 5 + ], + [ + 1497, + "Line King: Al Hirschfeld, The (1996)", + 2 + ], + [ + 1498, + "Farmer & Chase (1995)", + 1 + ], + [ + 1499, + "Grosse Fatigue (1994)", + 4 + ], + [ + 1500, + "Santa with Muscles (1996)", + 2 + ], + [ + 1501, + "Prisoner of the Mountains (Kavkazsky Plennik) (1996)", + 5 + ], + [ + 1502, + "Naked in New York (1994)", + 2 + ], + [ + 1503, + "Gold Diggers: The Secret of Bear Mountain (1995)", + 10 + ], + [ + 1504, + "Bewegte Mann, Der (1994)", + 3 + ], + [ + 1505, + "Killer: A Journal of Murder (1995)", + 1 + ], + [ + 1506, + "Nelly & Monsieur Arnaud (1995)", + 3 + ], + [ + 1507, + "Three Lives and Only One Death (1996)", + 1 + ], + [ + 1508, + "Babysitter, The (1995)", + 3 + ], + [ + 1509, + "Getting Even with Dad (1994)", + 5 + ], + [ + 1510, + "Mad Dog Time (1996)", + 1 + ], + [ + 1511, + "Children of the Revolution (1996)", + 5 + ], + [ + 1512, + "World of Apu, The (Apur Sansar) (1959)", + 6 + ], + [ + 1513, + "Sprung (1997)", + 3 + ], + [ + 1514, + "Dream With the Fishes (1997)", + 7 + ], + [ + 1515, + "Wings of Courage (1995)", + 1 + ], + [ + 1516, + "Wedding Gift, The (1994)", + 3 + ], + [ + 1517, + "Race the Sun (1996)", + 5 + ], + [ + 1518, + "Losing Isaiah (1995)", + 12 + ], + [ + 1519, + "New Jersey Drive (1995)", + 2 + ], + [ + 1520, + "Fear, The (1995)", + 1 + ], + [ + 1521, + "Mr. Wonderful (1993)", + 4 + ], + [ + 1522, + "Trial by Jury (1994)", + 7 + ], + [ + 1523, + "Good Man in Africa, A (1994)", + 2 + ], + [ + 1524, + "Kaspar Hauser (1993)", + 8 + ], + [ + 1525, + "Object of My Affection, The (1998)", + 1 + ], + [ + 1526, + "Witness (1985)", + 1 + ], + [ + 1527, + "Senseless (1998)", + 7 + ], + [ + 1528, + "Nowhere (1997)", + 3 + ], + [ + 1529, + "Underground (1995)", + 5 + ], + [ + 1530, + "Jefferson in Paris (1995)", + 5 + ], + [ + 1531, + "Far From Home: The Adventures of Yellow Dog (1995)", + 7 + ], + [ + 1532, + "Foreign Student (1994)", + 2 + ], + [ + 1533, + "I Don't Want to Talk About It (De eso no se habla) (1993)", + 1 + ], + [ + 1534, + "Twin Town (1997)", + 6 + ], + [ + 1535, + "Enfer, L' (1994)", + 4 + ], + [ + 1536, + "Aiqing wansui (1994)", + 1 + ], + [ + 1537, + "Cosi (1996)", + 4 + ], + [ + 1538, + "All Over Me (1997)", + 3 + ], + [ + 1539, + "Being Human (1993)", + 4 + ], + [ + 1540, + "Amazing Panda Adventure, The (1995)", + 10 + ], + [ + 1541, + "Beans of Egypt, Maine, The (1994)", + 2 + ], + [ + 1542, + "Scarlet Letter, The (1926)", + 2 + ], + [ + 1543, + "Johns (1996)", + 1 + ], + [ + 1544, + "It Takes Two (1995)", + 3 + ], + [ + 1545, + "Frankie Starlight (1995)", + 4 + ], + [ + 1546, + "Shadows (Cienie) (1988)", + 1 + ], + [ + 1547, + "Show, The (1995)", + 2 + ], + [ + 1548, + "The Courtyard (1995)", + 1 + ], + [ + 1549, + "Dream Man (1995)", + 2 + ], + [ + 1550, + "Destiny Turns on the Radio (1995)", + 2 + ], + [ + 1551, + "Glass Shield, The (1994)", + 2 + ], + [ + 1552, + "Hunted, The (1995)", + 3 + ], + [ + 1553, + "Underneath, The (1995)", + 4 + ], + [ + 1554, + "Safe Passage (1994)", + 2 + ], + [ + 1555, + "Secret Adventures of Tom Thumb, The (1993)", + 5 + ], + [ + 1556, + "Condition Red (1995)", + 2 + ], + [ + 1557, + "Yankee Zulu (1994)", + 1 + ], + [ + 1558, + "Aparajito (1956)", + 7 + ], + [ + 1559, + "Hostile Intentions (1994)", + 1 + ], + [ + 1560, + "Clean Slate (Coup de Torchon) (1981)", + 4 + ], + [ + 1561, + "Tigrero: A Film That Was Never Made (1994)", + 1 + ], + [ + 1562, + "Eye of Vichy, The (Oeil de Vichy, L') (1993)", + 1 + ], + [ + 1563, + "Promise, The (Versprechen, Das) (1994)", + 1 + ], + [ + 1564, + "To Cross the Rubicon (1991)", + 1 + ], + [ + 1565, + "Daens (1992)", + 1 + ], + [ + 1566, + "Man from Down Under, The (1943)", + 1 + ], + [ + 1567, + "Careful (1992)", + 1 + ], + [ + 1568, + "Vermont Is For Lovers (1992)", + 1 + ], + [ + 1569, + "Vie est belle, La (Life is Rosey) (1987)", + 1 + ], + [ + 1570, + "Quartier Mozart (1992)", + 1 + ], + [ + 1571, + "Touki Bouki (Journey of the Hyena) (1973)", + 1 + ], + [ + 1572, + "Wend Kuuni (God's Gift) (1982)", + 1 + ], + [ + 1573, + "Spirits of the Dead (Tre passi nel delirio) (1968)", + 2 + ], + [ + 1574, + "Pharaoh's Army (1995)", + 1 + ], + [ + 1575, + "I, Worst of All (Yo, la peor de todas) (1990)", + 1 + ], + [ + 1576, + "Hungarian Fairy Tale, A (1987)", + 1 + ], + [ + 1577, + "Death in the Garden (Mort en ce jardin, La) (1956)", + 1 + ], + [ + 1578, + "Collectionneuse, La (1967)", + 2 + ], + [ + 1579, + "Baton Rouge (1988)", + 1 + ], + [ + 1580, + "Liebelei (1933)", + 1 + ], + [ + 1581, + "Woman in Question, The (1950)", + 1 + ], + [ + 1582, + "T-Men (1947)", + 1 + ], + [ + 1583, + "Invitation, The (Zaproszenie) (1986)", + 1 + ], + [ + 1584, + "Symphonie pastorale, La (1946)", + 1 + ], + [ + 1585, + "American Dream (1990)", + 2 + ], + [ + 1586, + "Lashou shentan (1992)", + 1 + ], + [ + 1587, + "Terror in a Texas Town (1958)", + 1 + ], + [ + 1588, + "Salut cousin! (1996)", + 2 + ], + [ + 1589, + "Schizopolis (1996)", + 4 + ], + [ + 1590, + "To Have, or Not (1995)", + 2 + ], + [ + 1591, + "Duoluo tianshi (1995)", + 6 + ], + [ + 1592, + "Magic Hour, The (1998)", + 5 + ], + [ + 1593, + "Death in Brunswick (1991)", + 1 + ], + [ + 1594, + "Everest (1998)", + 2 + ], + [ + 1595, + "Shopping (1994)", + 1 + ], + [ + 1596, + "Nemesis 2: Nebula (1995)", + 1 + ], + [ + 1597, + "Romper Stomper (1992)", + 5 + ], + [ + 1598, + "City of Industry (1997)", + 6 + ], + [ + 1599, + "Someone Else's America (1995)", + 1 + ], + [ + 1600, + "Guantanamera (1994)", + 4 + ], + [ + 1601, + "Office Killer (1997)", + 1 + ], + [ + 1602, + "Price Above Rubies, A (1998)", + 3 + ], + [ + 1603, + "Angela (1995)", + 1 + ], + [ + 1604, + "He Walked by Night (1948)", + 1 + ], + [ + 1605, + "Love Serenade (1996)", + 4 + ], + [ + 1606, + "Deceiver (1997)", + 1 + ], + [ + 1607, + "Hurricane Streets (1998)", + 3 + ], + [ + 1608, + "Buddy (1997)", + 4 + ], + [ + 1609, + "B*A*P*S (1997)", + 3 + ], + [ + 1610, + "Truth or Consequences, N.M. (1997)", + 3 + ], + [ + 1611, + "Intimate Relations (1996)", + 2 + ], + [ + 1612, + "Leading Man, The (1996)", + 4 + ], + [ + 1613, + "Tokyo Fist (1995)", + 1 + ], + [ + 1614, + "Reluctant Debutante, The (1958)", + 1 + ], + [ + 1615, + "Warriors of Virtue (1997)", + 10 + ], + [ + 1616, + "Desert Winds (1995)", + 1 + ], + [ + 1617, + "Hugo Pool (1997)", + 2 + ], + [ + 1618, + "King of New York (1990)", + 1 + ], + [ + 1619, + "All Things Fair (1996)", + 1 + ], + [ + 1620, + "Sixth Man, The (1997)", + 9 + ], + [ + 1621, + "Butterfly Kiss (1995)", + 1 + ], + [ + 1622, + "Paris, France (1993)", + 3 + ], + [ + 1623, + "Cérémonie, La (1995)", + 3 + ], + [ + 1624, + "Hush (1998)", + 1 + ], + [ + 1625, + "Nightwatch (1997)", + 1 + ], + [ + 1626, + "Nobody Loves Me (Keiner liebt mich) (1994)", + 1 + ], + [ + 1627, + "Wife, The (1995)", + 1 + ], + [ + 1628, + "Lamerica (1994)", + 4 + ], + [ + 1629, + "Nico Icon (1995)", + 2 + ], + [ + 1630, + "Silence of the Palace, The (Saimt el Qusur) (1994)", + 1 + ], + [ + 1631, + "Slingshot, The (1993)", + 2 + ], + [ + 1632, + "Land and Freedom (Tierra y libertad) (1995)", + 1 + ], + [ + 1633, + "Á köldum klaka (Cold Fever) (1994)", + 1 + ], + [ + 1634, + "Etz Hadomim Tafus (Under the Domin Tree) (1994)", + 1 + ], + [ + 1635, + "Two Friends (1986) ", + 1 + ], + [ + 1636, + "Brothers in Trouble (1995)", + 1 + ], + [ + 1637, + "Girls Town (1996)", + 1 + ], + [ + 1638, + "Normal Life (1996)", + 1 + ], + [ + 1639, + "Bitter Sugar (Azucar Amargo) (1996)", + 3 + ], + [ + 1640, + "Eighth Day, The (1996)", + 1 + ], + [ + 1641, + "Dadetown (1995)", + 1 + ], + [ + 1642, + "Some Mother's Son (1996)", + 2 + ], + [ + 1643, + "Angel Baby (1995)", + 4 + ], + [ + 1644, + "Sudden Manhattan (1996)", + 2 + ], + [ + 1645, + "Butcher Boy, The (1998)", + 1 + ], + [ + 1646, + "Men With Guns (1997)", + 2 + ], + [ + 1647, + "Hana-bi (1997)", + 1 + ], + [ + 1648, + "Niagara, Niagara (1997)", + 1 + ], + [ + 1649, + "Big One, The (1997)", + 1 + ], + [ + 1650, + "Butcher Boy, The (1998)", + 1 + ], + [ + 1651, + "Spanish Prisoner, The (1997)", + 1 + ], + [ + 1652, + "Temptress Moon (Feng Yue) (1996)", + 3 + ], + [ + 1653, + "Entertaining Angels: The Dorothy Day Story (1996)", + 1 + ], + [ + 1654, + "Chairman of the Board (1998)", + 1 + ], + [ + 1655, + "Favor, The (1994)", + 1 + ], + [ + 1656, + "Little City (1998)", + 2 + ], + [ + 1657, + "Target (1995)", + 1 + ], + [ + 1658, + "Substance of Fire, The (1996)", + 3 + ], + [ + 1659, + "Getting Away With Murder (1996)", + 1 + ], + [ + 1660, + "Small Faces (1995)", + 1 + ], + [ + 1661, + "New Age, The (1994)", + 1 + ], + [ + 1662, + "Rough Magic (1995)", + 2 + ], + [ + 1663, + "Nothing Personal (1995)", + 1 + ], + [ + 1664, + "8 Heads in a Duffel Bag (1997)", + 4 + ], + [ + 1665, + "Brother's Kiss, A (1997)", + 1 + ], + [ + 1666, + "Ripe (1996)", + 1 + ], + [ + 1667, + "Next Step, The (1995)", + 1 + ], + [ + 1668, + "Wedding Bell Blues (1996)", + 1 + ], + [ + 1669, + "MURDER and murder (1996)", + 1 + ], + [ + 1670, + "Tainted (1998)", + 1 + ], + [ + 1671, + "Further Gesture, A (1996)", + 1 + ], + [ + 1672, + "Kika (1993)", + 2 + ], + [ + 1673, + "Mirage (1995)", + 1 + ], + [ + 1674, + "Mamma Roma (1962)", + 1 + ], + [ + 1675, + "Sunchaser, The (1996)", + 1 + ], + [ + 1676, + "War at Home, The (1996)", + 1 + ], + [ + 1677, + "Sweet Nothing (1995)", + 1 + ], + [ + 1678, + "Mat' i syn (1997)", + 1 + ], + [ + 1679, + "B. Monkey (1998)", + 1 + ], + [ + 1680, + "Sliding Doors (1998)", + 1 + ], + [ + 1681, + "You So Crazy (1994)", + 1 + ], + [ + 1682, + "Scream of Stone (Schrei aus Stein) (1991)", + 1 + ] + ], + "hovertemplate": "tsne_1=%{x}
tsne_2=%{y}
item_id=%{customdata[0]}
title=%{customdata[1]}
popularity=%{marker.color}", + "legendgroup": "", + "marker": { + "color": { + "bdata": "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", + "dtype": "i2" + }, + "coloraxis": "coloraxis", + "symbol": "circle" + }, + "mode": "markers", + "name": "", + "showlegend": false, + "type": "scattergl", + "x": { + "bdata": "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", + "dtype": "f4" + }, + "xaxis": "x", + "y": { + "bdata": "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", + "dtype": "f4" + }, + "yaxis": "y" + } + ], + "layout": { + "coloraxis": { + "colorbar": { + "title": { + "text": "popularity" + } + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ] + }, + "legend": { + "tracegroupgap": 0 + }, + "margin": { + "t": 60 + }, + "template": { + "data": { + "bar": [ + { + "error_x": { + "color": "#2a3f5f" + }, + "error_y": { + "color": "#2a3f5f" + }, + "marker": { + "line": { + "color": "#E5ECF6", + "width": 0.5 + }, + "pattern": { + "fillmode": "overlay", + "size": 10, + "solidity": 0.2 + } + }, + "type": "bar" + } + ], + "barpolar": [ + { + "marker": { + "line": { + "color": "#E5ECF6", + "width": 0.5 + }, + "pattern": { + "fillmode": "overlay", + "size": 10, + "solidity": 0.2 + } + }, + "type": "barpolar" + } + ], + "carpet": [ + { + "aaxis": { + "endlinecolor": "#2a3f5f", + "gridcolor": "white", + "linecolor": "white", + "minorgridcolor": "white", + "startlinecolor": "#2a3f5f" + }, + "baxis": { + "endlinecolor": "#2a3f5f", + "gridcolor": "white", + "linecolor": "white", + "minorgridcolor": "white", + "startlinecolor": "#2a3f5f" + }, + "type": "carpet" + } + ], + "choropleth": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "type": "choropleth" + } + ], + "contour": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "contour" + } + ], + "contourcarpet": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "type": "contourcarpet" + } + ], + "heatmap": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "heatmap" + } + ], + "histogram": [ + { + "marker": { + "pattern": { + "fillmode": "overlay", + "size": 10, + "solidity": 0.2 + } + }, + "type": "histogram" + } + ], + "histogram2d": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "histogram2d" + } + ], + "histogram2dcontour": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "histogram2dcontour" + } + ], + "mesh3d": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "type": "mesh3d" + } + ], + "parcoords": [ + { + "line": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "parcoords" + } + ], + "pie": [ + { + "automargin": true, + "type": "pie" + } + ], + "scatter": [ + { + "fillpattern": { + "fillmode": "overlay", + "size": 10, + "solidity": 0.2 + }, + "type": "scatter" + } + ], + "scatter3d": [ + { + "line": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatter3d" + } + ], + "scattercarpet": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scattercarpet" + } + ], + "scattergeo": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scattergeo" + } + ], + "scattergl": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scattergl" + } + ], + "scattermap": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scattermap" + } + ], + "scatterpolar": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatterpolar" + } + ], + "scatterpolargl": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatterpolargl" + } + ], + "scatterternary": [ + { + "marker": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "type": "scatterternary" + } + ], + "surface": [ + { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + }, + "colorscale": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "type": "surface" + } + ], + "table": [ + { + "cells": { + "fill": { + "color": "#EBF0F8" + }, + "line": { + "color": "white" + } + }, + "header": { + "fill": { + "color": "#C8D4E3" + }, + "line": { + "color": "white" + } + }, + "type": "table" + } + ] + }, + "layout": { + "annotationdefaults": { + "arrowcolor": "#2a3f5f", + "arrowhead": 0, + "arrowwidth": 1 + }, + "autotypenumbers": "strict", + "coloraxis": { + "colorbar": { + "outlinewidth": 0, + "ticks": "" + } + }, + "colorscale": { + "diverging": [ + [ + 0, + "#8e0152" + ], + [ + 0.1, + "#c51b7d" + ], + [ + 0.2, + "#de77ae" + ], + [ + 0.3, + "#f1b6da" + ], + [ + 0.4, + "#fde0ef" + ], + [ + 0.5, + "#f7f7f7" + ], + [ + 0.6, + "#e6f5d0" + ], + [ + 0.7, + "#b8e186" + ], + [ + 0.8, + "#7fbc41" + ], + [ + 0.9, + "#4d9221" + ], + [ + 1, + "#276419" + ] + ], + "sequential": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ], + "sequentialminus": [ + [ + 0, + "#0d0887" + ], + [ + 0.1111111111111111, + "#46039f" + ], + [ + 0.2222222222222222, + "#7201a8" + ], + [ + 0.3333333333333333, + "#9c179e" + ], + [ + 0.4444444444444444, + "#bd3786" + ], + [ + 0.5555555555555556, + "#d8576b" + ], + [ + 0.6666666666666666, + "#ed7953" + ], + [ + 0.7777777777777778, + "#fb9f3a" + ], + [ + 0.8888888888888888, + "#fdca26" + ], + [ + 1, + "#f0f921" + ] + ] + }, + "colorway": [ + "#636efa", + "#EF553B", + "#00cc96", + "#ab63fa", + "#FFA15A", + "#19d3f3", + "#FF6692", + "#B6E880", + "#FF97FF", + "#FECB52" + ], + "font": { + "color": "#2a3f5f" + }, + "geo": { + "bgcolor": "white", + "lakecolor": "white", + "landcolor": "#E5ECF6", + "showlakes": true, + "showland": true, + "subunitcolor": "white" + }, + "hoverlabel": { + "align": "left" + }, + "hovermode": "closest", + "paper_bgcolor": "white", + "plot_bgcolor": "#E5ECF6", + "polar": { + "angularaxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + }, + "bgcolor": "#E5ECF6", + "radialaxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + } + }, + "scene": { + "xaxis": { + "backgroundcolor": "#E5ECF6", + "gridcolor": "white", + "gridwidth": 2, + "linecolor": "white", + "showbackground": true, + "ticks": "", + "zerolinecolor": "white" + }, + "yaxis": { + "backgroundcolor": "#E5ECF6", + "gridcolor": "white", + "gridwidth": 2, + "linecolor": "white", + "showbackground": true, + "ticks": "", + "zerolinecolor": "white" + }, + "zaxis": { + "backgroundcolor": "#E5ECF6", + "gridcolor": "white", + "gridwidth": 2, + "linecolor": "white", + "showbackground": true, + "ticks": "", + "zerolinecolor": "white" + } + }, + "shapedefaults": { + "line": { + "color": "#2a3f5f" + } + }, + "ternary": { + "aaxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + }, + "baxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + }, + "bgcolor": "#E5ECF6", + "caxis": { + "gridcolor": "white", + "linecolor": "white", + "ticks": "" + } + }, + "title": { + "x": 0.05 + }, + "xaxis": { + "automargin": true, + "gridcolor": "white", + "linecolor": "white", + "ticks": "", + "title": { + "standoff": 15 + }, + "zerolinecolor": "white", + "zerolinewidth": 2 + }, + "yaxis": { + "automargin": true, + "gridcolor": "white", + "linecolor": "white", + "ticks": "", + "title": { + "standoff": 15 + }, + "zerolinecolor": "white", + "zerolinewidth": 2 + } + } + }, + "xaxis": { + "anchor": "y", + "domain": [ + 0, + 1 + ], + "title": { + "text": "tsne_1" + } + }, + "yaxis": { + "anchor": "x", + "domain": [ + 0, + 1 + ], + "title": { + "text": "tsne_2" + } + } + } + } + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "import plotly.express as px\n", "\n", @@ -749,7 +11240,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 44, "metadata": { "scrolled": true }, @@ -771,9 +11262,27 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 45, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m48/48\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 666us/step\n", + " 4.6: Young Guns (1988)\n", + " 4.6: Letter From Death Row, A (1998)\n", + " 4.4: Robert A. Heinlein's The Puppet Masters (1994)\n", + " 4.4: Celtic Pride (1996)\n", + " 4.3: To Kill a Mockingbird (1962)\n", + " 4.2: 20,000 Leagues Under the Sea (1954)\n", + " 4.2: Dead Man Walking (1995)\n", + " 4.1: Fly Away Home (1996)\n", + " 4.1: Legends of the Fall (1994)\n", + " 4.1: Amadeus (1984)\n" + ] + } + ], "source": [ "for title, pred_rating in recommend(5):\n", " print(\" %0.1f: %s\" % (pred_rating, title))" @@ -793,7 +11302,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 46, "metadata": { "collapsed": false }, @@ -832,11 +11341,38 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 47, "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 512us/step - loss: 2.6350 - val_loss: 1.0521\n", + "Epoch 2/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 497us/step - loss: 0.8506 - val_loss: 0.7935\n", + "Epoch 3/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 501us/step - loss: 0.7523 - val_loss: 0.7668\n", + "Epoch 4/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 473us/step - loss: 0.7242 - val_loss: 0.7540\n", + "Epoch 5/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 492us/step - loss: 0.7015 - val_loss: 0.7446\n", + "Epoch 6/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 498us/step - loss: 0.6810 - val_loss: 0.7426\n", + "Epoch 7/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 496us/step - loss: 0.6613 - val_loss: 0.7348\n", + "Epoch 8/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 482us/step - loss: 0.6389 - val_loss: 0.7383\n", + "Epoch 9/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 489us/step - loss: 0.6170 - val_loss: 0.7388\n", + "Epoch 10/10\n", + "\u001b[1m1125/1125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 494us/step - loss: 0.5913 - val_loss: 0.7348\n" + ] + } + ], "source": [ "# Training the model\n", "history = model.fit([user_id_train, item_id_train], rating_train,\n", @@ -854,7 +11390,7 @@ ], "metadata": { "kernelspec": { - "display_name": "deep-learning-env (3.13.13)", + "display_name": "deep-learning-env (3.11.14)", "language": "python", "name": "python3" }, @@ -868,7 +11404,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.13.13" + "version": "3.11.14" } }, "nbformat": 4, diff --git a/02_activities/assignments/assignment_1.ipynb b/02_activities/assignments/assignment_1.ipynb index 6a1f05814..365ef573c 100644 --- a/02_activities/assignments/assignment_1.ipynb +++ b/02_activities/assignments/assignment_1.ipynb @@ -29,10 +29,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "420c7178", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz\n", + "\u001b[1m29515/29515\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 1us/step\n", + "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz\n", + "\u001b[1m26421880/26421880\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 0us/step\n", + "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz\n", + "\u001b[1m5148/5148\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 1us/step\n", + "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz\n", + "\u001b[1m4422102/4422102\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n" + ] + } + ], "source": [ "from tensorflow.keras.datasets import fashion_mnist\n", "(X_train, y_train), (X_test, y_test) = fashion_mnist.load_data()\n", @@ -47,28 +62,69 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "id": "a6c89fe7", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "X_train shape: (60000, 28, 28)\n", + "y_train shape: (60000,)\n", + "X_test shape: (10000, 28, 28)\n", + "y_test shape: (10000,)\n", + "After one-hot encoding: [0. 0. 0. 0. 0. 0. 0. 0. 0. 1.]\n", + "After one-hot encoding: [0. 0. 0. 0. 0. 0. 0. 0. 0. 1.]\n" + ] + } + ], "source": [ "# Inspect the shapes of the datasets\n", - "\n", + "print(f'X_train shape: {X_train.shape}')\n", + "print(f'y_train shape: {y_train.shape}')\n", + "print(f'X_test shape: {X_test.shape}')\n", + "print(f'y_test shape: {y_test.shape}')\n", "\n", "# Convert labels to one-hot encoding\n", "from tensorflow.keras.utils import to_categorical\n", - "\n" + "\n", + "y_train_onehot = to_categorical(y_train, num_classes=10)\n", + "y_test_onehot = to_categorical(y_test, num_classes=10)\n", + "\n", + "y_train = to_categorical(y_train, num_classes=10)\n", + "y_test = to_categorical(y_test, num_classes=10)\n", + "print(f'After one-hot encoding: {y_train[0]}')\n", + "print(f'After one-hot encoding: {y_test[0]}')" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "id": "13e100db", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "import matplotlib.pyplot as plt\n", - "# Verify the data looks as expected\n" + "# Verify the data looks as expected\n", + "\n", + "sample_index = 0 \n", + "plt.figure(figsize=(28, 28))\n", + "plt.imshow(X_train[sample_index], cmap=plt.cm.gray_r,\n", + " interpolation='nearest')\n", + "plt.title(\"image label: %s\" % class_names[y_train[sample_index].argmax()])\n", + "plt.show()" ] }, { @@ -81,6 +137,14 @@ "**Your answer here**" ] }, + { + "cell_type": "markdown", + "id": "3ecb39cc", + "metadata": {}, + "source": [ + "Yes, the data does look like an ankle boot. THe image quality is fuzzy, but readable." + ] + }, { "cell_type": "markdown", "id": "c9e8ad60", @@ -101,10 +165,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "id": "8563a7aa", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Train loss: 0.3691\n", + "Train accuracy: 86.72%\n", + "Test loss: 0.4168\n", + "Test accuracy: 84.92%\n" + ] + } + ], "source": [ "from keras.models import Sequential\n", "from keras.layers import Dense, Flatten\n", @@ -113,11 +188,30 @@ "model = Sequential()\n", "# You can use `model.add()` to add layers to the model\n", "\n", + "model.add(Flatten())\n", + "model.add(Dense(10))\n", + "\n", + "# Hidden layer\n", + "model.add(Dense(64, activation='relu')) # 64 neurons, ReLU activation\n", + "\n", + "# Output layer\n", + "model.add(Dense(10, activation='softmax')) # 10 neurons, softmax activation\n", + "\n", "# Compile the model using `model.compile()`\n", + "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n", "\n", "# Train the model with `model.fit()`\n", + "model.fit(X_train, y_train, epochs=5, batch_size=32, validation_split=0.2, verbose=0)\n", + "\n", + "\n", + "# Evaluate the model with `model.evaluate()`\n", + "t_loss, t_acc = model.evaluate(X_train, y_train, verbose=0)\n", + "print(f\"Train loss: {t_loss:.4f}\")\n", + "print(f\"Train accuracy: {t_acc:.2%}\")\n", "\n", - "# Evaluate the model with `model.evaluate()`" + "loss, acc = model.evaluate(X_test, y_test, verbose=0)\n", + "print(f\"Test loss: {loss:.4f}\")\n", + "print(f\"Test accuracy: {acc:.2%}\")" ] }, { @@ -127,7 +221,9 @@ "source": [ "Reflection: What is the performance of the baseline model? How does it compare to what you expected? Why do you think the performance is at this level?\n", "\n", - "**Your answer here**" + "**Your answer here**\n", + "\n", + "The performance of training data was 86.72%, and test data of 84.92%. The loss for train was 0.3691, and 0.4168 for test. It's a strong result." ] }, { @@ -151,10 +247,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "id": "3513cf3d", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Train loss: 0.2981\n", + "Train accuracy: 89.39%\n", + "Test loss: 0.3605\n", + "Test accuracy: 87.25%\n" + ] + } + ], "source": [ "from keras.layers import Conv2D\n", "\n", @@ -164,10 +271,22 @@ "\n", "# Create a simple CNN model\n", "model = Sequential()\n", - "\n", + "model.add(Conv2D(filters=3, kernel_size=(5, 5), padding=\"same\", activation='relu'))\n", + "model.add(Flatten())\n", + "model.add(Dense(10, activation='softmax'))\n", + "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n", "# Train the model\n", + "model.fit(X_train, y_train, epochs=5, batch_size=32, validation_split=0.2, verbose=0)\n", + "\n", + "# Evaluate the model\n", "\n", - "# Evaluate the model" + "t_loss, t_acc = model.evaluate(X_train, y_train, verbose=0)\n", + "print(f\"Train loss: {t_loss:.4f}\")\n", + "print(f\"Train accuracy: {t_acc:.2%}\")\n", + "\n", + "loss, acc = model.evaluate(X_test, y_test, verbose=0)\n", + "print(f\"Test loss: {loss:.4f}\")\n", + "print(f\"Test accuracy: {acc:.2%}\")" ] }, { @@ -177,7 +296,9 @@ "source": [ "Reflection: Did the CNN model perform better than the baseline model? If so, by how much? What do you think contributed to this improvement?\n", "\n", - "**Your answer here**" + "**Your answer here**\n", + "\n", + "Yes, it did perform better, but only slightly. Probably the convolutional layer helped for this improvement." ] }, { @@ -204,19 +325,350 @@ "execution_count": null, "id": "99d6f46c", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Training hidden=(10,), lr=0.001...\n", + "hidden=(10,), lr=0.001: test acc = 0.717\n", + "Training hidden=(10,), lr=0.01...\n", + "hidden=(10,), lr=0.01: test acc = 0.826\n", + "Training hidden=(32,), lr=0.01...\n", + "hidden=(32,), lr=0.01: test acc = 0.854\n", + "Training hidden=(64,), lr=0.01...\n", + "hidden=(64,), lr=0.01: test acc = 0.856\n", + "Training hidden=(64,), lr=0.1...\n", + "hidden=(64,), lr=0.1: test acc = 0.890\n", + "Training hidden=(64, 32), lr=0.01...\n", + "hidden=(64, 32), lr=0.01: test acc = 0.852\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
hidden_sizeslearning_ratevalidation_accuracytest_accuracytest_loss
0(10,)0.0010.7240830.71661.094228
1(10,)0.0100.8357500.82570.517354
2(32,)0.0100.8647500.85410.420394
3(64,)0.0100.8670000.85620.401320
4(64,)0.1000.8945830.88980.324148
5(64, 32)0.0100.8581670.85200.432306
\n", + "
" + ], + "text/plain": [ + " hidden_sizes learning_rate validation_accuracy test_accuracy test_loss\n", + "0 (10,) 0.001 0.724083 0.7166 1.094228\n", + "1 (10,) 0.010 0.835750 0.8257 0.517354\n", + "2 (32,) 0.010 0.864750 0.8541 0.420394\n", + "3 (64,) 0.010 0.867000 0.8562 0.401320\n", + "4 (64,) 0.100 0.894583 0.8898 0.324148\n", + "5 (64, 32) 0.010 0.858167 0.8520 0.432306" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ - "# A. Test Hyperparameters" + "# A. Test Hyperparameters\n", + "import pandas as pd\n", + "from keras import Input, backend\n", + "from keras.models import Sequential\n", + "from keras.layers import Conv2D, Dense, Flatten\n", + "from keras.optimizers import SGD\n", + "from keras.utils import set_random_seed\n", + "\n", + "\n", + "class DeepNeuralNet:\n", + " def __init__(self, input_size, hidden_sizes, output_size):\n", + " # Every new instance creates a fresh CNN\n", + " self.model = Sequential()\n", + " self.model.add(Input(shape=input_size))\n", + " self.model.add(Conv2D(32, (3, 3), activation='relu'))\n", + " self.model.add(Flatten())\n", + "\n", + " for size in hidden_sizes:\n", + " self.model.add(Dense(size, activation='sigmoid'))\n", + "\n", + " self.model.add(Dense(output_size, activation='softmax'))\n", + "\n", + " def forward(self, X):\n", + " return self.model.predict(X, verbose=0)\n", + "\n", + " def train(self, x, y, learning_rate, epochs):\n", + " self.model.compile(\n", + " optimizer=SGD(learning_rate=learning_rate),\n", + " loss='categorical_crossentropy',\n", + " metrics=['accuracy']\n", + " )\n", + "\n", + " self.history = self.model.fit(\n", + " x, y,\n", + " epochs=epochs,\n", + " batch_size=32,\n", + " validation_split=0.2,\n", + " verbose=0\n", + " )\n", + "\n", + " def accuracy(self, X, y):\n", + " self.test_loss, acc = self.model.evaluate(X, y, verbose=0)\n", + " return acc\n", + "\n", + "\n", + "def fit_eval(net, lr, epochs=15):\n", + " net.train(X_train, y_train, lr, epochs)\n", + " return net.accuracy(X_test, y_test)\n", + "\n", + "\n", + "results = []\n", + "\n", + "for hidden, lr in [\n", + " ((10,), 0.001),\n", + " ((10,), 0.01),\n", + " ((32,), 0.01),\n", + " ((64,), 0.01),\n", + " ((64,), 0.1),\n", + " ((64, 32), 0.01)\n", + "]:\n", + " backend.clear_session()\n", + " set_random_seed(0)\n", + "\n", + " net = DeepNeuralNet(\n", + " input_size=X_train.shape[1:],\n", + " hidden_sizes=hidden,\n", + " output_size=10\n", + " )\n", + "\n", + " print(f\"Training hidden={hidden}, lr={lr}...\")\n", + " acc = fit_eval(net, lr)\n", + "\n", + " results.append({\n", + " 'hidden_sizes': hidden,\n", + " 'learning_rate': lr,\n", + " 'validation_accuracy': net.history.history['val_accuracy'][-1],\n", + " 'test_accuracy': acc,\n", + " 'test_loss': net.test_loss\n", + " })\n", + "\n", + " print(f\"hidden={hidden}, lr={lr}: test acc = {acc:.3f}\")\n", + "\n", + "display(pd.DataFrame(results))" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 25, "id": "dc43ac81", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "dropout=0.0: test accuracy = 88.87%\n", + "dropout=0.5: test accuracy = 89.18%\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
hidden_sizeslearning_ratedropout_ratevalidation_accuracytest_accuracytest_loss
0(64,)0.10.00.8949170.88870.330940
1(64,)0.10.50.8943330.89180.306884
\n", + "
" + ], + "text/plain": [ + " hidden_sizes learning_rate dropout_rate validation_accuracy \\\n", + "0 (64,) 0.1 0.0 0.894917 \n", + "1 (64,) 0.1 0.5 0.894333 \n", + "\n", + " test_accuracy test_loss \n", + "0 0.8887 0.330940 \n", + "1 0.8918 0.306884 " + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "best_dropout=0.0\n" + ] + } + ], "source": [ - "# B. Test presence or absence of regularization" + "# B. Test presence or absence of regularization\n", + "\n", + "from keras.layers import Dropout\n", + "\n", + "best_config = max(\n", + " results,\n", + " key=lambda result: result['validation_accuracy']\n", + ")\n", + "\n", + "best_hidden = best_config['hidden_sizes']\n", + "best_lr = best_config['learning_rate']\n", + "\n", + "regularization_results = []\n", + "\n", + "for dropout_rate in [0.0, 0.5]:\n", + " backend.clear_session()\n", + " set_random_seed(42)\n", + "\n", + " model = Sequential()\n", + " model.add(Input(shape=X_train.shape[1:]))\n", + " model.add(Conv2D(32, (3, 3), activation='relu'))\n", + " model.add(Flatten())\n", + "\n", + " if dropout_rate > 0:\n", + " model.add(Dropout(dropout_rate, seed=42))\n", + "\n", + " model.add(Dense(10, activation='softmax'))\n", + "\n", + " model.compile(\n", + " optimizer=SGD(learning_rate=best_lr),\n", + " loss='categorical_crossentropy',\n", + " metrics=['accuracy']\n", + " )\n", + "\n", + "\n", + " history = model.fit(X_train, y_train, epochs=15, batch_size=32, validation_split=0.2,\n", + " verbose=0)\n", + "\n", + " test_loss, test_acc = model.evaluate(X_test, y_test, verbose=0)\n", + "\n", + " regularization_results.append({\n", + " 'hidden_sizes': best_hidden,\n", + " 'learning_rate': best_lr,\n", + " 'dropout_rate': dropout_rate,\n", + " 'validation_accuracy': history.history['val_accuracy'][-1],\n", + " 'test_accuracy': test_acc,\n", + " 'test_loss': test_loss\n", + " })\n", + "\n", + " print(f\"dropout={dropout_rate}: test accuracy = {test_acc:.2%}\")\n", + "\n", + "display(pd.DataFrame(regularization_results))\n", + "\n", + "best_regularization = max(regularization_results,key=lambda result: result['validation_accuracy'])\n", + "best_dropout = best_regularization['dropout_rate']\n", + "print(f\"best_dropout={best_dropout}\")" ] }, { @@ -226,7 +678,11 @@ "source": [ "Reflection: Report on the performance of the models you tested. Did any of the changes you made improve the model's performance? If so, which ones? What do you think contributed to these improvements? Finally, what combination of hyperparameters and regularization techniques yielded the best performance?\n", "\n", - "**Your answer here**" + "**Your answer here**\n", + "\n", + "Changing the learning rate from 0.001 to 0.01 increased test accuracy. Adding 50% dropout increased test accuracy slightly. \n", + "\n", + "The best performance came with 64 neurons, learning rate of 0.1 and no dropout." ] }, { @@ -244,11 +700,54 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 26, "id": "31f926d1", "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Final learning rate: 0.1\n", + "Final dropout rate: 0.0\n", + "Final test loss: 0.3309\n", + "Final test accuracy: 88.87%\n" + ] + } + ], + "source": [ + "best_regularization = max(regularization_results, key=lambda result: result['validation_accuracy']\n", + ")\n", + "\n", + "best_lr = best_regularization['learning_rate']\n", + "best_dropout = best_regularization['dropout_rate']\n", + "\n", + "backend.clear_session()\n", + "set_random_seed(42)\n", + "\n", + "# new model\n", + "model = Sequential()\n", + "model.add(Input(shape=X_train.shape[1:]))\n", + "model.add(Conv2D(32, (3, 3), activation='relu'))\n", + "model.add(Flatten())\n", + "\n", + "if best_dropout > 0:\n", + " model.add(Dropout(best_dropout, seed=42))\n", + "\n", + "model.add(Dense(10, activation='softmax'))\n", + "\n", + "model.compile(optimizer=SGD(learning_rate=best_lr), loss='categorical_crossentropy',\n", + " metrics=['accuracy'])\n", + "\n", + "model.fit( X_train, y_train, epochs=15, batch_size=32, validation_split=0.2, verbose=0)\n", + "\n", + "final_loss, final_accuracy = model.evaluate( X_test, y_test, verbose=0)\n", + "\n", + "print(f\"Final learning rate: {best_lr}\")\n", + "print(f\"Final dropout rate: {best_dropout}\")\n", + "print(f\"Final test loss: {final_loss:.4f}\")\n", + "print(f\"Final test accuracy: {final_accuracy:.2%}\")" + ] }, { "cell_type": "markdown", @@ -257,7 +756,13 @@ "source": [ "Reflection: How does the final model's performance compare to the baseline and the CNN model? What do you think contributed to the final model's performance? If you had time, what other experiments would you run to further improve the model's performance?\n", "\n", - "**Your answer here**" + "**Your answer here**\n", + "\n", + "The final model improved test accuracy with 88.87%, which is almost 4% higher than the baseline. In regards to CNN, it only improved by about 1%.\n", + "\n", + "I would say the convolutional layer helped improve performance as it was learning visual things like curves. \n", + "\n", + "If I had more time, i would try a different convolutional layer, and different dropout rates." ] }, { @@ -283,11 +788,17 @@ "- [ ] Verify that the link is accessible in a private browser window.\n", "If you encounter any difficulties or have questions, please don't hesitate to reach out to our team via our Slack at `#cohort-7-help-ml`. Our Technical Facilitators and Learning Support staff are here to help you navigate any challenges." ] + }, + { + "cell_type": "markdown", + "id": "47d38edf", + "metadata": {}, + "source": [] } ], "metadata": { "kernelspec": { - "display_name": "deep_learning", + "display_name": "deep-learning-env (3.11.14)", "language": "python", "name": "python3" }, @@ -301,7 +812,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.12.11" + "version": "3.11.14" } }, "nbformat": 4,