Skip to content

How to train from searching stage? #5

@lizhenstat

Description

@lizhenstat

Hi, How can we resume training in the converging stage?

I know there are 200 epochs in the searching stage and 300 epochs in the converging stage by default.
Suppose we already get the model_converging_best.pt under the "model" directory.
I tried to load the pre-trained model using --save, --load and --pretrain, but all not working.
Thanks

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