AI denoiser

.github/copilot-instructions.md

@@ -1,2 +1,4 @@
 * Ask questions about the prompt to clarify any uncertainties.
 * Ensure that new code compiles without warnings or errors.
+* Prioritize making new code efficient and compact
+* Prefer file scoped namespaces

.gitignore

@@ -13,4 +13,5 @@ PhotoLocatorSetup/*.pfx
 PhotoLocatorSetup/AppPackages/
 PhotoLocatorSetup/BundleArtifacts/
 TestResults/
+__pycache__/
 publish.bat

.vscode/launch.json

@@ -6,9 +6,9 @@
             "name": "C#: PhotoLocator Debug",
             "type": "coreclr",
             "request": "launch",
-            "program": "${workspaceFolder}/PhotoLocator/bin/Debug/net8.0-windows/PhotoLocator.exe",
+            "program": "${workspaceFolder}/PhotoLocator/bin/Debug/net10.0-windows/PhotoLocator.exe",
             "args": [],
-            "cwd": "${workspaceFolder}/PhotoLocator/bin/Debug/net8.0-windows/",
+            "cwd": "${workspaceFolder}/PhotoLocator/bin/Debug/net10.0-windows/",
             "stopAtEntry": false,
             "preLaunchTask": "build"
         }  

PhotoLocator/AI/create_minimal_denoise_test_model.py

@@ -0,0 +1,41 @@
+from pathlib import Path
+
+import onnx
+from onnx import TensorProto, helper, numpy_helper
+
+
+def create_identity_model(output_path: Path):
+	input_tensor = helper.make_tensor_value_info("input", TensorProto.FLOAT, ["batch", "channels", "height", "width"])
+	output_tensor = helper.make_tensor_value_info("output", TensorProto.FLOAT, ["batch", "channels", "height", "width"])
+
+	identity_node = helper.make_node(
+		"Identity",
+		inputs=["input"],
+		outputs=["output"],
+		name="identity_test",
+	)
+
+	graph = helper.make_graph(
+		[identity_node],
+		"minimal_denoise_test_graph",
+		[input_tensor],
+		[output_tensor],
+	)
+
+	model = helper.make_model(graph, producer_name="PhotoLocatorTest")
+	model.opset_import[0].version = 17
+	model.ir_version = 13
+
+	output_path.parent.mkdir(parents=True, exist_ok=True)
+	onnx.save(model, str(output_path))
+	print(f"Saved minimal ONNX smoke-test model to {output_path}")
+
+
+def main():
+	repo_root = Path(__file__).resolve().parents[2]
+	output_path = repo_root / "PhotoLocatorTest" / "TestData" / "dncnn_test.onnx"
+	create_identity_model(output_path)
+
+
+if __name__ == "__main__":
+	main()

PhotoLocator/AI/denoise_dncnn.py

@@ -0,0 +1,41 @@
+import argparse
+from pathlib import Path
+
+import cv2
+import torch
+
+from train_dncnn import DnCNN, checkpoint_model_state, denoise_image
+
+
+def main():
+	parser = argparse.ArgumentParser(description="Denoise an image using a trained PyTorch DnCNN checkpoint.")
+	parser.add_argument("--model", type=str, required=True, help="Path to the trained PyTorch checkpoint (.pt)")
+	parser.add_argument("--input", type=str, required=True, help="Path to the image to denoise")
+	parser.add_argument("--output", type=str, required=True, help="Path for the denoised image")
+	parser.add_argument("--channels", type=int, default=3, choices=[1, 3], help="Model input channels")
+	parser.add_argument("--tile-size", type=int, default=512, help="Maximum tile width and height")
+	parser.add_argument("--overlap", type=int, default=64, help="Overlap between adjacent inference tiles")
+	parser.add_argument("--device", type=str, default="cuda" if torch.cuda.is_available() else "cpu", help="Inference device, e.g. cpu or cuda")
+	args = parser.parse_args()
+
+	image = cv2.imread(args.input, cv2.IMREAD_UNCHANGED)
+	if image is None:
+		raise FileNotFoundError(f"Unable to read input image: {args.input}")
+
+	model = DnCNN(channels=args.channels).to(args.device)
+	checkpoint = torch.load(args.model, map_location=args.device)
+	model.load_state_dict(checkpoint_model_state(checkpoint))
+	print(f"Inference device: {args.device}")
+	result = denoise_image(model, image, args.channels, args.device, args.tile_size, args.overlap)
+	if result.shape[2] == 1:
+		result = result[:, :, 0]
+
+	output_path = Path(args.output)
+	output_path.parent.mkdir(parents=True, exist_ok=True)
+	if not cv2.imwrite(str(output_path), result):
+		raise OSError(f"Unable to save denoised image: {output_path}")
+	print(f"Saved denoised image to {output_path}")
+
+
+if __name__ == "__main__":
+	main()

PhotoLocator/AI/export_dncnn_onnx.py

@@ -0,0 +1,57 @@
+import argparse
+import os
+
+import onnx
+import torch
+
+from train_dncnn import DnCNN, checkpoint_model_state
+
+
+def main():
+	parser = argparse.ArgumentParser(description="Export a trained DnCNN denoiser to a single-file embedded ONNX model.")
+	parser.add_argument("--model", type=str, default="dncnn_model.pt", help="Path to the saved PyTorch weights (.pt)")
+	parser.add_argument("--output", type=str, default="dncnn_model.onnx", help="Path for the ONNX model")
+	parser.add_argument("--channels", type=int, default=3, choices=[1, 3], help="Input image channels")
+	parser.add_argument("--height", type=int, default=256, help="Example input height")
+	parser.add_argument("--width", type=int, default=256, help="Example input width")
+	parser.add_argument("--opset", type=int, default=17, help="ONNX opset version")
+	args = parser.parse_args()
+
+	model = DnCNN(channels=args.channels)
+	checkpoint = torch.load(args.model, map_location="cpu")
+	model.load_state_dict(checkpoint_model_state(checkpoint))
+	model.eval()
+
+	dummy_input = torch.randn(1, args.channels, args.height, args.width)
+	temp_path = args.output + ".tmp"
+	torch.onnx.export(
+		model,
+		(dummy_input,),
+		temp_path,
+		export_params=True,
+		opset_version=args.opset,
+		do_constant_folding=True,
+		input_names=["input"],
+		output_names=["output"],
+		dynamic_axes={
+			"input": {0: "batch_size", 2: "height", 3: "width"},
+			"output": {0: "batch_size", 2: "height", 3: "width"},
+		},
+	)
+
+	model_onnx = onnx.load(temp_path)
+	onnx.save_model(
+		model_onnx,
+		args.output,
+		save_as_external_data=False,
+		all_tensors_to_one_file=True,
+	)
+
+	os.remove(temp_path)
+	os.remove(temp_path + ".data")
+
+	print(f"Exported ONNX model to {args.output}")
+
+
+if __name__ == "__main__":
+	main()