Skip to content

MMClassification Release V0.15.0
Compare
Choose a tag to compare
@mzr1996 mzr1996 released this 31 Aug 06:39
· 271 commits to master since this release
v0.15.0
a41cb2f
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

Highlights

  • Support hparams argument in AutoAugment and RandAugment to provide hyperparameters for sub-policies.
  • Support custom squeeze channels in SELayer.
  • Support classwise weight in losses.

New Features

  • Add hparams argument in AutoAugment and RandAugment and some other improvement. (#398)
  • Support classwise weight in losses (#388)
  • Enhence SELayer to support custom squeeze channels. (#417)

Code Refactor

  • Better result visualization (#419)
  • Use post_process function to handle pred result processing. (#390)
  • Update digit_version function. (#402)
  • Avoid albumentations to install both opencv and opencv-headless. (#397)
  • Avoid unnecessary listdir when building ImageNet. (#396)
  • Use dynamic mmcv download link in TorchServe dockerfile. (#387)

Docs Improvement

  • Add readme of some algorithms and update meta yml (#418)
  • Add Copyright information. (#413)
  • Add PR template and modify issue template (#380)

Contributors

A total of 5 developers contributed to this release.
@azad96 @Ezra-Yu @mzr1996 @mmeendez8 @sovrasov

Contributors

sovrasov, mmeendez8, and 3 other contributors
Assets 2
Loading