raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly

[FLAWLESSJade]

raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly

[FLAWLESSJade]

I have solve this problem in my other server with environment : pytorch 1.6.0 , torchvision 0.7.0 and ubuntu 16.04 OS

The method to deal this problem as follows:
When i exchange my training environment to this server, i found the same situation like someones asked before that the shape of mnist and mnist-m are not align,but this code was work in my prior server.
So, i deduce that this problem may raised by the code of dataloader part, i revised this code as follows,which help me solved this problem above.

transform = transforms.Compose([
transforms.ToTensor(),
transforms.Lambda(lambda x: x.repeat(3,1,1)), #Add this code to reshape channel from 1 to 3
transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))
])

And,a new problem is raised that the loss of target dif and source dif are always keep 0,it is abnormal.
It looks like the model do not have any back propagation.

[elmaghba]

@FLAWLESSJade I got the same issue, did you solve it?