liaoxingyu 3d1bae9f13 fix triplet loss backward propagation on multi-gpu training (#82) ... Summary: fix torch.distributed.all_gather has no gradient when performing all_gather operation on the provided tensors, instead using `GatherLayer`.		2020-09-28 17:16:51 +08:00
..
config	refactor reid head	2020-09-10 10:57:37 +08:00
data	support finetuning from trained models	2020-09-28 17:10:10 +08:00
engine	support finetuning from trained models	2020-09-28 17:10:10 +08:00
evaluation	refactor evaluation code	2020-09-23 19:32:40 +08:00
layers	fix triplet loss backward propagation on multi-gpu training (#82)	2020-09-28 17:16:51 +08:00
modeling	fix triplet loss backward propagation on multi-gpu training (#82)	2020-09-28 17:16:51 +08:00
solver	refactor evaluation code	2020-09-23 19:32:40 +08:00
utils	fix typro	2020-09-10 11:04:59 +08:00
__init__.py	feat: add SyncBN and GroupNorm suppor	2020-05-14 11:36:28 +08:00