About the batch size. #1

Open

opened

on Nov 14, 2020

I find that both in the code of WCT and in OST, the batch size is set to 1. It limits the inference speed.
Can we set the batch size to 64? In another words, can we run the WCT and OST distributely?

to join this conversation on GitHub. Already have an account? Sign in to comment

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