• 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
retinanet.py 3.0 KB