torchvision/models/detection/_utils.py · 8df3f29a5ffe875e783474e899e51a0d30b2c17b · OpenDAS / vision

Replace L1 loss with beta smooth L1 loss to achieve better performance (#2113) · 8df3f29a

Potter Hsu authored Apr 25, 2020

* For detection model, replace L1 loss with beta smooth L1 loss to achieve better performance.

* Add type annotations for torchscript

* Resolve E226

8df3f29a

_utils.py 13.9 KB

Replace _utils.py