1. 16 10月, 2019 1 次提交
  2. 14 10月, 2019 1 次提交
  3. 29 9月, 2019 2 次提交
    • Y
      Revert to mixed precision training with manual control (#3434) · efc994ec
      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 3a2c1062.
      
      * Bug fixes and some tweaks
      efc994ec
    • W
      Support finetune by custom dataset (#3195) · 8bee6f61
      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
      8bee6f61
  4. 23 7月, 2019 1 次提交
  5. 18 7月, 2019 1 次提交
  6. 28 6月, 2019 1 次提交
  7. 26 6月, 2019 2 次提交
  8. 24 6月, 2019 3 次提交