HumberMe 1214df083d

[Enhance] Use PyTorch official one_hot to implement convert_to_one_hot. (#696) ...

* some change to mmcls/models/losses/utils.py:convert_to_one_hot()

* fixed problem: line too long

* fixed wrong output shape

* fixed lint PEP8 E128

* fix lint

* fix lint

* add unit tests

Co-authored-by: Ezra-Yu <1105212286@qq.com>

2022-02-28 10:20:31 +08:00

..

__init__.py

[Feature] Add seesaw loss. (#500)

2021-10-27 10:11:59 +08:00

accuracy.py

[Fix] Fix cal_acc bug caused by the return type of accuracy.

2021-12-14 16:21:25 +08:00

asymmetric_loss.py

[Enhance] Support single-label, softmax, custom eps by asymmetric loss (#609)

2022-01-21 11:35:14 +08:00

cross_entropy_loss.py

[Feature] Support positive weights in BCE. (#516)

2021-11-10 17:14:12 +08:00

focal_loss.py

[Enhance] Focal loss for single label tasks (#548)

2021-11-26 12:36:49 +08:00

label_smooth_loss.py

[Refactor] Remove deprecation. (#633)

2022-02-10 09:30:18 +08:00

seesaw_loss.py

[Feature] Add seesaw loss. (#500)

2021-10-27 10:11:59 +08:00

utils.py

[Enhance] Use PyTorch official one_hot to implement convert_to_one_hot. (#696)

2022-02-28 10:20:31 +08:00