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

pytorch version #144

Open
juneleung opened this issue Sep 25, 2024 · 1 comment
Open

pytorch version #144

juneleung opened this issue Sep 25, 2024 · 1 comment

Comments

@juneleung
Copy link

Hello, thanks for your great work.
DeepLabCut has a new pytorch version and I am unfamiliar with tf, so is there any version based on pytorch? Thank you! :)

@Mojackhak
Copy link

Hi Juneleung,

From my experience, Anipose is almost fully compatible with the PyTorch version of DeepLabCut, as the high-level API remains unchanged. However, one notable limitation of the current PyTorch version is its lack of support for exporting multiple predictions, even when num_outputs=xx is set in the config.yaml file. This issue prevents the Viterbi filter from functioning properly.

To address this, I made a minor modification to the code. If you're interested, you can try my slightly adjusted version by installing it with:

pip install git+https://github.com/Mojackhak/DeepLabCut.git@pytorch_dlc

I’ve tested this modification on single-animal tracking, and it works as expected.

Best regards!

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

No branches or pull requests

2 participants