Skip to content

I find a bug in your source code. #96

@shoutOutYangJie

Description

@shoutOutYangJie
Image

In your default setting, "gpu_trans" is True. but training preprocessor uses "gpu_trans=True" and eval preprocessor uses "gpu_trans=False".
So data' range is different from training phrase and eval

By the way, model.forward has no operation to normalize data range for training phrase, so is is a big bug

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions