Good morning,
When running your model, during the second for loops I get the following error (line 78 in train.py).
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [256, 8]], which is output 0 of AsStridedBackward0, is at version 2; expected version 1 instead.
Do you have any idea of the why? Thanks in advance :)
Good morning, When running your model, during the second for loops I get the following error (line 78 in train.py).
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [256, 8]], which is output 0 of AsStridedBackward0, is at version 2; expected version 1 instead.
Do you have any idea of the why? Thanks in advance :)