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.

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

add EfficientNet for torchvision #3433

Closed
WZMIAOMIAO opened this issue Feb 23, 2021 · 1 comment
Closed

add EfficientNet for torchvision #3433

WZMIAOMIAO opened this issue Feb 23, 2021 · 1 comment

Comments

@WZMIAOMIAO
Copy link
Contributor

WZMIAOMIAO commented Feb 23, 2021

🚀 Feature

Add EfficientNet models into torchvision module.

Motivation

I very love this projects.
I noticed that in 2019 it was said that efficientnet models would be added. #980
But up to now, there is no efficientnet models.
I'm looking forward to adding more new models to torchvision.

Additional context

I refer to the official efficientnet model of tensorflow implemented with keras module link and the mobilenetV3 model in torchvision link. Then I built efficientnet models Test9_efficientNet and the conversion weight script trans_weights_to_pytorch.py.
If you think it's useful a little bit, I hope you can add efficientnet models to torchvision as soon as possible.

@pmeier
Copy link
Collaborator

pmeier commented Feb 23, 2021

Hey @WZMIAOMIAO. I've skimmed #980 and as far as I understood the problem is not the implementation, but rather the training. If you have more insights or ressources, I suggest you get in touch with the other participants in the discussion.

Anyway, since there already is an issue for this, lets keep the discussion there.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants