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

[Feature] [CodeCamp #68] Add EfficientnetV2 Backbone #1253

Merged
merged 140 commits into from
Dec 30, 2022
Merged

[Feature] [CodeCamp #68] Add EfficientnetV2 Backbone #1253

merged 140 commits into from
Dec 30, 2022

Conversation

qingtian5
Copy link
Contributor

@qingtian5 qingtian5 commented Dec 9, 2022

Motivation

Add the EfficientnetV2 backbone and the convert weights.
paper: https://arxiv.org/abs/2104.00298
code: https://github.com/google/automl/tree/master/efficientnetv2

related to #1108 #1231

Modification

添加模型文件与配置文件

TODO

  • 对齐推理精度
    • 完成EfficientnetV2 框架搭设,
    • 对齐推理的transforms
    • 完成b0/b1/b2/b3架构设置,对齐推理精度
  • Code Review 以及重构代码
  • 完成单元测试以及Doc

训练精度对齐,不在这个PR中完成,但可以在对齐推理精度后测试
0. 跑一下源码和自己的配置,看下精度能否复现,(这里因为tf与torch的差异,可以跑timm的b0训练)

  1. 对齐训练transfroms
  2. 固定输入对齐前向loss
  3. 对齐反向梯度

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here and update the documentation.

Checklist

Before PR:

  • Pre-commit or other linting tools are used to fix the potential lint issues.
  • Bug fixes are fully covered by unit tests, the case that causes the bug should be added in the unit tests.
  • The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
  • The documentation has been modified accordingly, like docstring or example tutorials.

After PR:

  • If the modification has potential influence on downstream or other related projects, this PR should be tested with those projects, like MMDet or MMSeg.
  • CLA has been signed and all committers have signed the CLA in this PR.

@CLAassistant
Copy link

CLAassistant commented Dec 9, 2022

CLA assistant check
All committers have signed the CLA.

@Ezra-Yu Ezra-Yu changed the title CodeCamp #62 #EfficientnetV2 [WIP] [Feature] [CodeCamp #68] Add EfficientnetV2 Backbone Dec 9, 2022
Copy link
Collaborator

@Ezra-Yu Ezra-Yu left a comment

Choose a reason for hiding this comment

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

  1. Please change to efficientnet-v2-s?
  2. add metafile and readme in configs/efficientnet_v2/

mmcls/models/backbones/efficientnet_v2.py Outdated Show resolved Hide resolved
mmcls/models/backbones/efficientnet_v2.py Outdated Show resolved Hide resolved
mmcls/models/backbones/efficientnet_v2.py Outdated Show resolved Hide resolved
mmcls/models/backbones/efficientnet_v2.py Outdated Show resolved Hide resolved
mmcls/models/backbones/efficientnet_v2.py Outdated Show resolved Hide resolved
mmcls/models/backbones/efficientnet_v2.py Outdated Show resolved Hide resolved
mmcls/models/backbones/efficientnet_v2.py Outdated Show resolved Hide resolved
mmcls/models/backbones/efficientnet_v2.py Outdated Show resolved Hide resolved
mmcls/models/backbones/efficientnet_v2.py Show resolved Hide resolved
mmcls/models/backbones/efficientnet_v2.py Outdated Show resolved Hide resolved
Copy link
Collaborator

@Ezra-Yu Ezra-Yu left a comment

Choose a reason for hiding this comment

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

LGTM.

@mzr1996 mzr1996 merged commit 74743ef into open-mmlab:dev-1.x Dec 30, 2022
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.

None yet

5 participants