Skip to content

Error on training using single gpu #1

@arslanamin14

Description

@arslanamin14

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument weight in method wrapper__nll_loss2d_forward)
I am trying to train the model using single gpu but I am getting this error. Is there anyway to resolve this

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