Probabilistic-Unet-Pytorch
Probabilistic-Unet-Pytorch copied to clipboard
A Probabilistic U-Net for segmentation of ambiguous images implemented in PyTorch
1. The value of loss does not converge  2. I use the trained weight file for prediction ![Uploading image.png…]()
Hello - I've been getting this issue consistently while running the code as is, with the LIDC-IDRI data (downloaded from the provided link). This error is caught at the line...
Hello, I downloaded a dataset in pickle format from the author's link, but encountered an error indexing a non-existent index value while training the network. I have not encountered this...
Hi Stefan, thanks for this nice PyTorch implementation. I have a question regarding the `sample` function in the `probabilistic_unet.py` file. In line [222](https://github.com/stefanknegt/Probabilistic-Unet-Pytorch/blob/master/probabilistic_unet.py#L222) (while training), wouldn't we want to sample...