mirror of https://github.com/alibaba/EasyCV.git
1. The vitdet backbone implemented by d2 is about 20% faster than the vitdet backbone originally reproduced by easycv. 2. 50.57 -> 50.65 |
||
---|---|---|
.. | ||
backbones | ||
classification | ||
detection | ||
heads | ||
pose | ||
segmentation | ||
selfsup | ||
__init__.py |