8000 Handling of nested dictionary (multiple outputs) as model outputs · Issue #24 · yxlee245/pytorch2tf · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
< 8000 div id="js-flash-container" class="flash-container" data-turbo-replace>

Handling of nested dictionary (multiple outputs) as model outputs #24

New issue

9CD2 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
Open
rose-jinyang opened this issue Feb 26, 2022 · 1 comment
Open

Handling of nested dictionary (multiple outputs) as model outputs #24

rose-jinyang opened this issue Feb 26, 2022 · 1 comment

Comments

@rose-jinyang
Copy link

Hello
Thanks for contributing to this project.
I have a PyTorch model with a nested dictionary as output.
The output is:

{'losses':
{'loss_rec': float values},
'output':
{'pred_rec': int values,
'pred_rec_score': float values
}
}
How can I convert this PyTorch model to ONNX model?
@yxlee245
Copy link
Owner

Hi Rose, for your case, you may want to try something like torch.onnx.export(..., output_nqmes=["pred_rec", "pred_rec_score"]). Let me know how it goes, as it's something quite new for me too

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
2 participants
@yxlee245 @rose-jinyang
0