Zhiliang Peng 18f6bb0b10 [Feature] Implement the conformer backbone. (#494) ... * implement the conformer * format code style * format code style * reuse the TransformerEncoderLayer in the vision_transformer.py * Modify variable name * delete unused params * Remove warning info in Conformer head since it already exists in Conformer. * Rename some variables * Add unit tests * Use `getattr` instead of `get_submodule`. * Remove some useless layers * Refactor conformer and add configs * Update configs and add metafile. * Fix unit tests * Update README Co-authored-by: mzr1996 <mzr1996@163.com>		2021-12-07 14:00:17 +08:00
..
data	[Feature] Add a tool to visualize learning rate in each iterations (#498)	2021-11-03 10:48:56 +08:00
test_data	[Fix] Fix bug when using `ClassBalancedDataset` (#555)	2021-11-26 09:40:00 +08:00
test_downstream	[Enhance] Improve downstream repositories compatibility (#421)	2021-09-08 10:38:57 +08:00
test_metrics	[Enhance] Focal loss for single label tasks (#548)	2021-11-26 12:36:49 +08:00
test_models	[Feature] Implement the conformer backbone. (#494)	2021-12-07 14:00:17 +08:00
test_runtime	[Docs] Add Copyright information. (#413)	2021-08-17 19:52:42 +08:00
test_utils	[Refactor] Use new API of matplotlib to handle blocking input in visualization. (#568)	2021-12-02 17:46:40 +08:00