mmclassification

Commit Graph

Author	SHA1	Message	Date
Yusuke Minami	e694269c59	[Enhance] Support single-label, softmax, custom eps by asymmetric loss (#609 ) Co-authored-by: Minyus <Minyus@users.noreply.github.com>	2022-01-21 11:35:14 +08:00
juanjompz	715a80b09c	[Enhance] Focal loss for single label tasks (#548 ) * Added focal loss support to single label tasks. * Updated focal loss docstring	2021-11-26 12:36:49 +08:00
Ezra-Yu	87c67a6a79	[Feature] Support positive weights in BCE. (#516 ) * add pos-weight in BCE * mv pos-weight to kwargs	2021-11-10 17:14:12 +08:00
Zhicheng Chen	6d6ce215a2	[Feature] Add seesaw loss. (#500 ) * migrate seesaw loss from mmdet * add assertion and doc string fixes * add error information * docstring fixes * minor doc update	2021-10-27 10:11:59 +08:00
Ezra-Yu	192b79eea0	[Feature] Support classwise weight in losses (#388 ) * Add classwise weight in losses:CE,BCE,softBCE * Update unit test * rm some extra code * rm some extra code * fix broadcast * fix broadcast * update unit tests * use new_tensor * fix lint	2021-08-31 10:44:12 +08:00
Ma Zerun	f9eb9b409b	[Docs] Add Copyright information. (#413 )	2021-08-17 19:52:42 +08:00
Ma Zerun	1a7cebe4b9	[Refactor] Refactor unittest (#321 ) * Refactor unit tests folder structure. * Remove label smooth and Vit test in `test_classifiers.py` * Rename test_utils in dataset to test_dataset_utils * Split test_models/test_utils/test_utils.py to multiple sub files. * Add unit tests of classifiers and heads * Use patch context manager. * Add unit test of `is_tracing`, and add warning in `is_tracing` if torch verison is smaller than 1.6.0	2021-07-08 22:49:05 +08:00

7 Commits (44e99029796e89c8a7e63217fdea8d55ef94bf50)