Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

flag_use_half_precision=True but uses float32 #384

Open
TZYSJTU opened this issue Sep 11, 2024 · 0 comments
Open

flag_use_half_precision=True but uses float32 #384

TZYSJTU opened this issue Sep 11, 2024 · 0 comments

Comments

@TZYSJTU
Copy link

TZYSJTU commented Sep 11, 2024

Hi，in the function warp_decode(), why is the value set to float32 when flag_use_half_precision=True?

            # float the dict
            if self.inference_cfg.flag_use_half_precision:
                for k, v in ret_dct.items():
                    if isinstance(v, torch.Tensor):
                        ret_dct[k] = v.float()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@TZYSJTU