Run cnn_mnist Error

[weizhou-geek]

Hi,
I follow the blog written on the website "http://blog.csdn.net/z49434574/article/details/52654293". 准备数据和初始化神经网络之后，进行训练网络，但是出现了以下错误：

cnn_mnist
警告: 名称不存在或不是目录: E:\MATCONVNET-master\MATCONVNET-master\matconvnet\matlab\mex
In path (line 109)
In addpath (line 88)
In vl_setupnn (line 13)
In run (line 96)
In cnn_mnist (line 4)
警告: MatConvNet is not compiled. Consider running vl_compilenn.
In vl_setupnn (line 24)
In run (line 96)
In cnn_mnist (line 4)
layer| 0| 1| 2| 3| 4| 5| 6| 7| 8|
type|input| conv| mpool| conv| mpool| conv| relu| conv|softmxl|
name| n/a|layer1|layer2|layer3|layer4|layer5|layer6|layer7| layer8|
----------|-----|------|------|------|------|------|------|------|-------|
support| n/a| 5| 2| 10| 2| 10| 1| 1| 1|
filt dim| n/a| 3| n/a| 20| n/a| 50| n/a| 500| n/a|
filt dilat| n/a| 1| n/a| 1| n/a| 1| n/a| 1| n/a|
num filts| n/a| 20| n/a| 50| n/a| 500| n/a| 4| n/a|
stride| n/a| 1| 2| 1| 2| 1| 1| 1| 1|
pad| n/a| 0| 0| 0| 0| 0| 0| 0| 0|
----------|-----|------|------|------|------|------|------|------|-------|
rf size| n/a| 5| 6| 24| 26| 62| 62| 62| 62|
rf offset| n/a| 3| 3.5| 12.5| 13.5| 31.5| 31.5| 31.5| 31.5|
rf stride| n/a| 1| 2| 2| 4| 4| 4| 4| 4|
----------|-----|------|------|------|------|------|------|------|-------|
data size| 64| 60| 30| 21| 10| 1| 1| 1| 1|
data depth| NaN| 20| 20| 50| 50| 500| 500| 4| 1|
data num| 200| 200| 200| 200| 200| 200| 200| 200| 1|
----------|-----|------|------|------|------|------|------|------|-------|
data mem| NaN| 55MB| 14MB| 17MB| 4MB| 391KB| 391KB| 3KB| 4B|
param mem| n/a| 6KB| 0B| 391KB| 0B| 10MB| 0B| 8KB| 0B|

parameter memory|10MB (2.6e+06 parameters)|
data memory| NaN (for batch size 200)|

train: epoch 01: 1/ 1:尝试将 SCRIPT vl_nnconv 作为函数执行:
E:\MATCONVNET-master\MATCONVNET-master\matconvnet\matlab\vl_nnconv.m

出错 vl_simplenn (line 300)
res(i+1).x = vl_nnconv(res(i).x, l.weights{1}, l.weights{2}, ...

出错 cnn_train>processEpoch (line 316)
res = vl_simplenn(net, im, dzdy, res, ...

出错 cnn_train (line 132)
[net, state] = processEpoch(net, state, params, 'train') ;

出错 cnn_mnist (line 48)
[net, info] = trainfn(net, imdb, getBatch(opts), ...

[YunpengZhai]

Hello,check whether you've compiled the matconvnet correctly. you can compile it following my [http://blog.csdn.net/z49434574/article/details/52445199] if you were doing that under windows system.
best regards

[weizhou-geek]

@YunpengZhai ,Thanks for your reply. Now I can run the code successfully, but how does the file "cnn_mnist_experiments.m" use?

[YunpengZhai]

sorry not to reply you earlier,just running it is OK.