milesial / Pytorch-UNet

PyTorch implementation of the U-Net for image semantic segmentation with high quality images
GNU General Public License v3.0
9.32k stars 2.52k forks source link

Training stuck at the end of the first epoch #505

Open XxUpUp opened 4 months ago

XxUpUp commented 4 months ago

Hi, I'm having the problem that when the last batch of my first epoch is trained, the program can't start the next epoch but stays stuck there and no error message appears, what could be the reason for this? (Note: I have made some changes to train.py, but not the main body of the code) image

zaoyueri commented 2 months ago

什么原因呢?

XxUpUp commented 2 months ago

什么原因呢?

I'm still not quite sure what the cause of this problem is.

chenshans commented 2 months ago

请问你解决了吗,我也遇到了一模一样的问题

XxUpUp commented 2 months ago

请问你解决了吗,我也遇到了一模一样的问题

Not yet.

ZafirTan commented 6 days ago

You can try use PyTorch 1.13 or later, I solve it by change pytorch verson