Error when run train.py

[ccuiyuhan]

I met the error:
RuntimeError: unsupported operation: more than one element of the written-to tensor refers to a single memory location. Please clone() the tensor before performing the operation.
How to solve this problem
Hope an answer!Thanks!

[deepglugs]

set pin_memory to false (and possibly workers to 1) in your preset.json

[YunfeiChenMY]

            loss = cl_loss + reconstruction_loss * config['training']['lambda2']
          repeat:
            loss = cl_loss.item() + reconstruction_loss * config['training']['lambda2']