Miguel Monteiro

Hi, I did not benchmark on 2D image segmentation. I did add noise to the output of the convolutional part of the network (with 3D images) to see if the...

Interesting... It shouldn't really matter if the images are normalized or not provided you scale theta appropriately. Did you try the GPU or CPU version? If you used the GPU...

The values seem right. Those tests are just examples on how to use it. They aren't supposed to do anything really, since the inputs/outputs have little meaning. It is easier...

I have sent you some emails, it seems the issue is the choice of theta

Thank you for testing this. I have some questions that might help us get to the problem. 1) Did you train all models from random initialization? Or did you use...

So here is one big issue: The CRF **does have** trainable parameters that must be optmised for within the training loop. When you load their model you are loading their...

Where did you get the pretrained weights from? If they are the ones sadeepj made available then they include the CRF's weights and you they are pretrained and not random...

Can you manually check that they are sampled from the random distribution of the initialisation or if they have been trained?

No problem, also thinks for doing this. If you manage to get some nice trained 2D RGB weights for my version of the model let me know. I can add...

No problem, we all have other work to deal with :)