Skip to content

Error when running with finetune backbone #14

@TalalWasim

Description

@TalalWasim

I am getting a strange error when trying to use the finetune backbone option.

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [128, 197, 768]], which is output 0 of torch::autograd::CopySlices, is at version 3; expected version 0 instead.

Do you have any idea why this might be happening?

Talal

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions