milesial
milesial
B&W means black & white. With PIL you can convert to greyscale https://pillow.readthedocs.io/en/stable/reference/Image.html#PIL.Image.Image.convert .
With 50 training data and no data augmentation I don't think you can expect good generalization results. The line you added seems fine if you have binary labels, you need...
@Quebradawill > how many images does the training set need? It depends on the difficulty of your task and the data augmentation you're willing to do. For Carvana the training...
To help me debug the DICE issue, could you please give me a sample of what your `self.inter` and `self.union` values look like in https://github.com/milesial/Pytorch-UNet/blob/84f8392b619940bd542dc670761a0a7a1357001d/dice_loss.py#L11-L12 ? Also, how many images...
Thank you for the detailed explaination of your problem. From the loss value and the loss plot it seems that your learning rate is way too high, have you tried...
I think your learning rate is too high. For the full carvana dataset I used 2e-6 as a LR
There was a lot of small tweaks in recent commits, but nothing that should affect the convergence I think. Are you using transposed conv or the bilinear route (default)? The...
@juliagong Thanks for your investigation ! It is indeed a big mistake that is there from a long time ago and needs a fix. But do the `train` and `eval`...
Hi all, I modified to switch back to train mode in https://github.com/milesial/Pytorch-UNet/commit/773ef215d41c1f36dc0ed4159c12df89d792fbc3
Hi, can you try the latest master? I improved the support for custom datasets.