Skip to content

Continue training from previous weights with TimeGAN #341

@MarigoldDrift

Description

@MarigoldDrift

Hello, I modified the TimeGAN code in the 'examples' folder to train with my own dataset.
The results are quite good, but every time I train I had to start from scratch.
Is there any way to continue training from the weights of the last session?

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