pytorch-image-models/tests
Ross Wightman 372ad5fa0d Significant model refactor and additions:
* All models updated with revised foward_features / forward_head interface
* Vision transformer and MLP based models consistently output sequence from forward_features (pooling or token selection considered part of 'head')
* WIP param grouping interface to allow consistent grouping of parameters for layer-wise decay across all model types
* Add gradient checkpointing support to a significant % of models, especially popular architectures
* Formatting and interface consistency improvements across models
* layer-wise LR decay impl part of optimizer factory w/ scale support in scheduler
* Poolformer and Volo architectures added
2022-02-28 13:56:23 -08:00
..
__init__.py Basic forward pass test for all registered models 2020-05-07 00:20:58 -04:00
test_layers.py Fix #661, move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present. 2021-05-26 15:28:42 -07:00
test_models.py Significant model refactor and additions: 2022-02-28 13:56:23 -08:00
test_optim.py Merge branch 'master' into attn_update 2021-09-13 16:51:10 -07:00
test_utils.py Fix ordering of tests 2021-10-02 16:10:11 +01:00