1. 30 12月, 2019 1 次提交
  2. 19 12月, 2019 1 次提交
    • Q
      Polish reader to simplify preprocessing logic. (#112) · 8192c758
      qingqing01 提交于
      * Polish Reader to simplify preprocessing logic.
      #  sample_transforms-> make batch -> batch_transforms in Reader.
      * Clean some code
      * Imporve yolov3_r50vd_dcn_obj365_pretrained_coco 41.4 to 41.8.
      * Update all configs.
      8192c758
  3. 29 9月, 2019 1 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
  4. 26 8月, 2019 1 次提交
  5. 12 8月, 2019 1 次提交
  6. 29 7月, 2019 1 次提交
  7. 11 7月, 2019 1 次提交
  8. 28 6月, 2019 1 次提交