Closed mrk1992 closed 4 years ago
I have the same problem. It seems that something is wrong with torch Dataloader's multiprocessing. At least setting num_workers=0
for both train_queue
and valid_queue
makes the script work properly for me. But this crutch can not be considered as a satisfactory solution.
I run this command
python train_search.py
and get a these results
Is it right ?