fast-reid/fastreid/layers
liaoxingyu 7ed6240e2c fix ReidEvalution too much memory cost
Move `matches` matrix computation in each iteration to reduce the extra memory cost

#420 #404
2021-06-08 15:41:43 +08:00
..
__init__.py Minor changes 2021-05-31 17:27:14 +08:00
activation.py onnx/trt support 2020-07-29 17:43:39 +08:00
any_softmax.py Minor changes 2021-05-31 17:27:14 +08:00
batch_norm.py fix ReidEvalution too much memory cost 2021-06-08 15:41:43 +08:00
context_block.py refactor(fastreid) 2020-04-20 10:59:29 +08:00
drop.py Support vision transformer backbone 2021-05-31 17:08:57 +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
helpers.py Support vision transformer backbone 2021-05-31 17:08:57 +08:00
non_local.py v0.3 update 2020-12-07 14:19:20 +08:00
pooling.py Minor changes 2021-05-31 17:27:14 +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
weight_init.py fix for lint_python 2021-05-31 17:40:33 +08:00