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

UE #1

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

UE #1

wants to merge 7 commits into from

Conversation

una-dinosauria
Copy link
Contributor

@una-dinosauria una-dinosauria commented Jun 13, 2024

Universal encoder written by @leochli and @jerrybai1995. Reposted by Julieta after resetting the repo.

Copy link
Contributor Author

@una-dinosauria una-dinosauria left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you add an overall overview of how this code is used?

Ie, what are the inputs, outputs, what should run first, etc?

data/headset_dataset.py Outdated Show resolved Hide resolved
data/headset_dataset.py Outdated Show resolved Hide resolved
ddp-train-ue.py Outdated Show resolved Hide resolved
ddp-train-ue.py Outdated Show resolved Hide resolved
ddp-train-ue.py Show resolved Hide resolved
models/headset_encoders/loss.py Outdated Show resolved Hide resolved
Comment on lines 121 to 124
if __name__ == "__main__":
num_conds = 1
hmc_cond_imgs = torch.rand((2, num_views, num_conds, in_chans, 400, 400), dtype=torch.float32)
expression_encoder = UniversalEncoder(
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we remove this main?

tests/test_headset_encoder.py Show resolved Hide resolved
@leochli leochli self-requested a review June 14, 2024 23:00
jerrybai1995 pushed a commit that referenced this pull request Jun 14, 2024
* replace internal extensions with oss ones

* instructions on how to compile extensions

* test only with oss extensions

* completely remove old kernels

* remove oss sufixes

* put templates' channels last in the decoders themselves

Co-authored-by: julietamartinez <julietamartinez@meta.com>
jerrybai1995 pushed a commit that referenced this pull request Jun 14, 2024
…ing_file_exists

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

Successfully merging this pull request may close these issues.

4 participants