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 |
||
---|---|---|
.. | ||
__init__.py | ||
base.py | ||
builder.py | ||
classifier.py | ||
detector.py | ||
face_keypoints_predictor.py | ||
feature_extractor.py | ||
hand_keypoints_predictor.py | ||
interface.py | ||
pose_predictor.py | ||
segmentation.py |