Skip to content

This issue was moved to a discussion.

You can continue the conversation there. Go to discussion →

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

Where do I find the new ViT baseline param? #1

Closed
sayakpaul opened this issue May 5, 2022 · 5 comments
Closed

Where do I find the new ViT baseline param? #1

sayakpaul opened this issue May 5, 2022 · 5 comments

Comments

@sayakpaul
Copy link

Regarding https://github.com/google-research/big_vision#vit-baseline

@xiaohuazhai
Copy link
Collaborator

It's available here:

https://github.com/google-research/big_vision/blob/main/big_vision/configs/vit_s16_i1k.py

You can always find all our configs under configs folder.

@sayakpaul
Copy link
Author

Sorry, I should have been clearer. By param, I meant the pre-trained params. Are they available yet?

@akolesnikoff
Copy link
Collaborator

It is an oversight from our side: we will publish it soon. Leaving the issue open until then.

@sayakpaul
Copy link
Author

Thanks!

As soon as they're available I will try to port them to a TensorFlow / Keras friendly model for wider community adoption.

@xiaohuazhai xiaohuazhai reopened this May 5, 2022
@akolesnikoff
Copy link
Collaborator

Models have been landed, see

"i1k-s16-90ep": "gs://big_vision/vit_s16_i1k_90ep.npz",

Closing the issue, feel free to reopen if you have any questions.

@google-research google-research locked and limited conversation to collaborators Nov 7, 2023
@lucasb-eyer lucasb-eyer converted this issue into discussion #73 Nov 7, 2023

This issue was moved to a discussion.

You can continue the conversation there. Go to discussion →

Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants