mirrors
/
fast-reid
mirror of https://github.com/JDAI-CV/fast-reid.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
fast-reid/fastreid/layers
History
Xingyu Liao 883fd4aede
add configurable decorator & linear loss decouple (#441) 
Summary: Add configurable decorator which can call `Baseline` with `Baseline(cfg)` or `Baseline(cfg, heads=heads, ...)`
Decouple linear and loss computation for partial-fc support.

Reviewed By: l1aoxingyu
 		2021-03-23 12:10:06 +08:00
..
__init__.py add configurable decorator & linear loss decouple (#441) 2021-03-23 12:10:06 +08:00
activation.py onnx/trt support 2020-07-29 17:43:39 +08:00
any_softmax.py add configurable decorator & linear loss decouple (#441) 2021-03-23 12:10:06 +08:00
batch_drop.py refactor(fastreid) 2020-04-20 10:59:29 +08:00
batch_norm.py update fastreid V1.0 2021-01-18 11:36:38 +08:00
context_block.py refactor(fastreid) 2020-04-20 10:59:29 +08:00
frn.py refactor(fastreid) 2020-04-20 10:59:29 +08:00
gather_layer.py fix triplet loss backward propagation on multi-gpu training (#82) 2020-09-28 17:16:51 +08:00
non_local.py v0.3 update 2020-12-07 14:19:20 +08:00
pooling.py add configurable decorator & linear loss decouple (#441) 2021-03-23 12:10:06 +08:00
se_layer.py refactor(fastreid) 2020-04-20 10:59:29 +08:00
splat.py v0.3 update 2020-12-07 14:19:20 +08:00