mirror of https://github.com/alibaba/EasyCV.git
Support Objects365 pretrain and Adding the DINO++ model can achieve an accuracy of 63.4mAP at a model scale of 200M(Under the same scale, the accuracy is the best) |
||
---|---|---|
.. | ||
set_criterion | ||
__init__.py | ||
cross_entropy_loss.py | ||
det_db_loss.py | ||
face_keypoint_loss.py | ||
focal_loss.py | ||
iou_loss.py | ||
l1_loss.py | ||
mse_loss.py | ||
ocr_rec_multi_loss.py | ||
pytorch_metric_learning.py | ||
utils.py |