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 support for the mish activation function #695

Merged
merged 1 commit into from
May 27, 2021

Conversation

Flova
Copy link
Collaborator

@Flova Flova commented May 27, 2021

Proposed changes

  • Implement the mish activation function, this enables inference of yolov4 models.

Necessary checks

  • Update poetry package version semantically
  • Write documentation
  • Create issues for future work
  • Test on your machine

@Flova Flova merged commit 1c03ebe into master May 27, 2021
@Flova Flova deleted the feature/mish_activation_function branch May 27, 2021 11:19
@digantamisra98
Copy link

digantamisra98 commented May 27, 2021

You can reformat this to include the version which has been recently merged to PyTorch. It will be released in 1.9. It will be faster and cheaper than the pure Pythonic implementation you're currently using.

@Flova
Copy link
Collaborator Author

Flova commented May 28, 2021

Thanks for the info! I would be happy to use the standard implementation. Our dependency tree resolution currently suggests 1.7.1 as the best PyTorch version for our dependency tree. I try to keep this in mind and update the code accordingly if we are able to use version 1.9.

@digantamisra98
Copy link

Sure, thank you for your response.

colmanAstrobotic pushed a commit to colmanAstrobotic/PyTorch-YOLOv3 that referenced this pull request Jul 2, 2021
…ish_activation_function

Add support for the mish activation function
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

Successfully merging this pull request may close these issues.

2 participants