M3d-Cam icon indicating copy to clipboard operation
M3d-Cam copied to clipboard

Results 17 M3d-Cam issues
Sort by recently updated
recently updated
newest added

Hi, My designed network is 3D CNN followed by RNN. I am trying to use M3D-Cam to get attention maps from the last convolution layer of the proposed network however...

Add demo for Multi-Input or Multi-Output or Multi-Input&Output network.

### **This is my code:** `model = model.to("cuda") def load_image(image_path = "Normal-3000.png"): raw_image = cv2.imread(image_path) raw_image = cv2.resize(raw_image, (224,) * 2) image = transforms.Compose( [ transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229,...

Hi, you can adapt the trick mentioned [here](https://github.com/MECLabTUDA/M3d-Cam/issues/13#issuecomment-911541129) to work with either multiple inputs, outputs or both. _Originally posted by @burhr2 in https://github.com/MECLabTUDA/M3d-Cam/issues/31#issuecomment-1755152607_ Is there any other way? I don’t...

Hi, My model has multiple inputs, i.e. the forward method of the model has two arguments: fmri_input, anat_input. When I try to wrap the model with model = medcam.inject(model, ...etc),...

Is it possible to use MedCAM with nnUNetv2? If so, could you please provide detailed instructions on how to integrate and use MedCAM with nnUNetv2?