1. 14 10月, 2019 1 次提交
  2. 29 9月, 2019 2 次提交
    • 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
    • W
      Support finetune by custom dataset (#3195) · e6e70e47
      wangguanzhong 提交于
      * Support finetune by custom dataset
      
      * add finetune args
      
      * add load finetune
      
      * reconstruct load
      
      * add transfer learning doc
      
      * add fruit demo
      
      * add quick start
      
      * add data preprocessing FAQ
      e6e70e47
  3. 23 7月, 2019 1 次提交
  4. 10 7月, 2019 1 次提交
  5. 28 6月, 2019 1 次提交