Andrews Cordolino Sobral

Hello @SylvainCorlay , All, I have the same problem here. I am on macOS Big Sur 11.2.3 with Xcode 12.4. I installed the latest Miniconda3 on my Mac, and created...

This is what I have by calling cling -v: ``` (cling) andrewssobral@macbookpro tmp % cling -v Adding library paths from 'LD_LIBRARY_PATH': Adding library paths from 'DYLD_LIBRARY_PATH': Adding library paths from...

Hi @saeedizadi , I am trying to do the same as @ZweeLe (binary segmentation), but I'm lost. When you talk about: > You must change the num_classes to 1 instead...

Hi @ZweeLe , Can you share your modifications for binary segmentation? Thanks

Thank you @ZweeLe ! When you say: > To use the nn.BCEWithLogitsLoss() you have to build Pytorch from source. For me I used nn.Sigmoid() and nn.BCELoss() but they are less...

Thank you @ZweeLe I did your tips, and now the algorithm is running, but the loss becomes negative, please see: ``` loss: 1.2735891342163086 (epoch: 1, step: 0) save: segnet-001-0000.pth (epoch:...

Hi @ZweeLe , I solved this issue by changing this: ``` input_transform = Compose([ CenterCrop(256), ToTensor(), Normalize([.485, .456, .406], [.229, .224, .225]), ]) target_transform = Compose([ CenterCrop(256), ToLabel(), Relabel(255, 21),...

@ZweeLe as I have only 126 images and I'm using Amazon EC2 with p2x.large instance (NVIDIA K80 with 12Gb of RAM), the training time is very fast (less than 5...

Hi @woaichipinngguo , you can find here an example of training binary segmentation on pytorch here: https://github.com/andrewssobral/deep-learning-pytorch/blob/master/segmentation/train_binseg.py this code was based on bodokaiser/piwise repository. However, in the code I don't...

Hi @ardashir66 , I am sorry for my delayed feedback to you, I was very busy these last days, and thanks for opening this issue, I will check it soon...