mmpretrain/tests
Ma Zerun 84a939f858
Refactor LabelSmoothLoss ()
* Refector label smooth loss, now support mode `original`, `classy_vision`
and `multi_label`.

* Add unittests for label smooth loss.

* Improve docstring of LSR
2021-06-12 21:32:18 +08:00
..
data Add RandomCrop, RandomResizedCrop, RandomGrayscale, impad 2020-07-12 00:06:55 +08:00
test_backbones [WIP] Refactoring weights initialization () 2021-06-10 10:54:34 +08:00
test_pipelines [Feature] Add an argument `efficientnet_style` to `RandomResizedCrop` and `CenterCrop` () 2021-05-31 14:10:57 +08:00
test_classifiers.py [Feature]Modify Parameters Passing in models.heads () 2021-05-10 14:56:55 +08:00
test_dataset.py [Feature] Add heads and config for multilabel task () 2021-01-25 18:10:14 +08:00
test_eval_hook.py [Fix] Use MMCV's EvalHook in MMClassification () 2021-03-25 17:38:51 +08:00
test_heads.py [Feature]Modify Parameters Passing in models.heads () 2021-05-10 14:56:55 +08:00
test_losses.py Refactor LabelSmoothLoss () 2021-06-12 21:32:18 +08:00
test_metrics.py Add evaluation metrics for multilabel task () 2021-01-04 12:25:33 +08:00
test_neck.py GlabelAveragePooling support 1d, 2d and 3d by param, and add neck test () 2021-05-10 15:00:50 +08:00