1. 31 8月, 2022 1 次提交
  2. 26 1月, 2022 1 次提交
    • B
      add implementation of RetinaNet (#5140) · ae621055
      Blake 提交于
      * add implementation of RetinaNet
      
      * * add README.md and model zoo
      * rename FOCSFeat -> RetianFeat
      * add mstrain model to model zoo
      * refactor DeltaBBoxCoder
      
      * update link for model and log
      ae621055
  3. 27 7月, 2021 1 次提交
  4. 07 7月, 2021 2 次提交
  5. 15 5月, 2021 1 次提交
    • F
      [MOT] add FairMOT (#2994) · 277bc13f
      FlyingQianMM 提交于
      * add fairmot
      
      * rename pretrain_weights
      
      * add comments; reuse focal loss and convnorm
      
      * update comments
      277bc13f
  6. 11 5月, 2021 1 次提交
  7. 26 4月, 2021 1 次提交
  8. 22 3月, 2021 1 次提交
  9. 20 1月, 2021 1 次提交
    • F
      [Dygraph] add TTFNet (#2099) · 93e2a447
      Feng Ni 提交于
      * ttfnet infer
      
      * fix ttfnet deploy
      
      * clean code
      
      * add comment, fix config
      
      * add comment, update modelzoo
      
      * fix norm resize, update modelzoo
      93e2a447
  10. 13 1月, 2021 1 次提交
  11. 11 1月, 2021 1 次提交
  12. 19 12月, 2020 1 次提交
  13. 18 12月, 2020 1 次提交
  14. 29 9月, 2019 2 次提交
    • Y
      Add missing license header (#3447) · fcafd420
      Yang Zhang 提交于
      fcafd420
    • Y
      Revert to mixed precision training with manual control (#3434) · 58994aa3
      Yang Zhang 提交于
      * Place mixed precision inside PaddleDetection
      
      roll back to the monkey patch version as a temporary measure, before it is
      merged into paddle
      
      * Add command flag for `loss_scale`
      
      * Fix a stupid indentation error
      
      optimizer should be in the mixed precision context
      
      * Initial FP16 training
      
      * Add mixed precision training to rest of the detection models
      
      * Revert "Add support for mixed precision training (#3406)"
      
      This reverts commit 3a2c106271885071db7c0d85587540a8f83c24db.
      
      * Bug fixes and some tweaks
      58994aa3