Skip to content

Error when Running train.py #2

@strmojo

Description

@strmojo

@iamyufan
I am encountering an error while attempting to run train.py with a reduced batch size. The original batch size was set to 100, but I have now reduced it to either 64 or 32. Unfortunately, I am receiving the following error message:

UserWarning: Using a target size (torch.Size([64, 1, 64, 64])) that is different from the input size (torch.Size([384, 1, 64, 64])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.
  return F.l1_loss(input, target, reduction=self.reduction)

RuntimeError: The size of tensor a (384) must match the size of tensor b (64) at non-singleton dimension 0.

The confusing part is that sometimes the input size is shown as 384, while other times it is displayed as 192. I am unsure why it is happening.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions