search

facebookresearch / ClassyVision

An end-to-end PyTorch framework for image and video classification
https://classyvision.ai
MIT License
1.59k stars 278 forks source link

Remove unnecessary Conv2dSamePadding in EfficientNet #732

Closed mannatsingh closed 3 years ago

mannatsingh commented 3 years ago

Summary: Conv2dSamePadding added unnecessary logic in EfficientNets. When the kernel size is odd, the padding is symmetric and we don't need this fancy logic.

Differential Revision: D27641829

facebook-github-bot commented 3 years ago

This pull request was exported from Phabricator. Differential Revision: D27641829

facebook-github-bot commented 3 years ago

This pull request was exported from Phabricator. Differential Revision: D27641829

facebook-github-bot commented 3 years ago

This pull request was exported from Phabricator. Differential Revision: D27641829

facebook-github-bot commented 3 years ago

This pull request has been merged in facebookresearch/ClassyVision@6c667f9db67def2d20d4e1dd2d0bb691cd2142a7.