mirrors
/
fast-reid
mirror of https://github.com/JDAI-CV/fast-reid.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
508 Commits
1 Branch
4 Tags
15 MiB
Commit Graph

508 Commits (d792a69f3f69159ba3ca6341a8be0e6da2b31633)
 

Author SHA1 Message Date
Lingxiao He 64de63a9ff
Update partial_market.yml 2020-07-12 13:52:39 +08:00
Lingxiao He ddc9dbf501
Update partial_market.yml 2020-07-12 13:44:22 +08:00
Lingxiao He 115de22532
Update dsr_distance.py 2020-07-12 13:31:21 +08:00
liaoxingyu f8d468647c resnet expansion add 2020-07-10 22:40:07 +08:00
liaoxingyu e81b13798c change way of loss function 
Summary: move loss computation from meta_arch to run_step considering distillation loss
 2020-07-10 16:28:53 +08:00
liaoxingyu dcd6f72235 partialreid bugfix #161 2020-07-10 16:27:22 +08:00
liaoxingyu ea8a3cc534 fix typro 2020-07-10 16:26:35 +08:00
liaoxingyu ab4afdb3c1 Merge branch 'master' of github.com:L1aoXingyu/fast-reid 2020-07-09 12:10:54 +08:00
liaoxingyu 59a74de240 update vehicle reid config 2020-07-09 12:10:38 +08:00
Christian Clauss 91d6b72e84
Let’s see how write_json was resolved 2020-07-07 06:55:30 +02:00
Xingyu Liao b01bc12a00
Fix the typing error in VeRi 
reviewed by: l1aoxingyu
 2020-07-07 11:30:15 +08:00
grimoire 76afdd8d66 fix bugs of rank_cylib 2020-07-07 11:12:46 +08:00
liaoxingyu 6cbca133a8 update readme 2020-07-06 17:16:44 +08:00
liaoxingyu 13bb8d5b1c update readme 2020-07-06 17:04:21 +08:00
liaoxingyu fec7abc461 finish v0.2 ddp training 2020-07-06 16:57:43 +08:00
liaoxingyu 5ae2cff47e fix circle/arcface pred_logits 
fix #136
 2020-07-06 16:57:03 +08:00
liaoxingyu b7a2b1c21a support DDP sampler and augment 2020-07-06 16:55:23 +08:00
liaoxingyu c851c7edc8 fix dataset prefix #76 2020-07-06 16:54:54 +08:00
liaoxingyu 825da4dca0 update all config files 2020-07-06 16:48:14 +08:00
Lingxiao He ec3aed26af
Update partial_market.yml 2020-07-06 14:19:09 +08:00
Xingyu Liao 9fa6e0f606
add UDA strong baseline 
Reviewed by: l1aoxingyu
 2020-07-03 10:54:18 +08:00
zkcloud d7b7523d25
Update README.md 2020-07-03 10:43:36 +08:00
zkcloud fe9e087ac3
Update README.md 2020-07-03 10:38:09 +08:00
zkcloud 73405f07b3
Update README.md 2020-07-03 10:37:29 +08:00
Lingxiao He df8916f1e6
Update dsr_distance.py 2020-06-29 16:41:58 +08:00
Lingxiao He d4153d4deb
Update README.md 2020-06-29 14:50:48 +08:00
Lingxiao He 7e1f232b37
Update README.md 2020-06-29 14:50:23 +08:00
Lingxiao He a325ee8ff7
Update partial_market.yml 2020-06-29 14:40:05 +08:00
Lingxiao He 0f9661f7b7
Update dsr_evaluation.py 2020-06-29 14:39:18 +08:00
Lingxiao He daa9dbbae2
Update partial_market.yml 2020-06-29 14:36:53 +08:00
Lingxiao He 8b06b95ab1
Update partial_market.yml 2020-06-29 13:53:54 +08:00
Lingxiao He 970bbb1679
Update dsr_distance.py 2020-06-29 13:50:52 +08:00
Lingxiao He beb5029576
Update README.md 2020-06-29 13:47:42 +08:00
Lingxiao He 706b9a3ec5
Update README.md 2020-06-26 23:19:35 +08:00
Lingxiao He 2a4c0726f8
Update README.md 2020-06-26 23:18:47 +08:00
liaoxingyu 4cc157a12f add lars optimizer 
Summary: support lars optimizer refer to https://arxiv.org/abs/1708.03888 which can make large batch training stable
 2020-06-22 12:12:19 +08:00
liaoxingyu f10ce253f1 refactor arcface and circle loss 
#111
 2020-06-22 11:56:39 +08:00
liaoxingyu 07159000ac add unitest for feature alignment 
Summary: test for converted caffe model and pytorch model feature alignment
 2020-06-22 11:48:14 +08:00
liaoxingyu 3840f3f79a fix arcface NaN problem 
Summary: fix classifier init bugs, which will not initialize classifier weights when use arcface or circle loss.
In this way, it will lead loss NaN problem.
 2020-06-18 12:05:44 +08:00
liaoxingyu 6623bff187 update training help options 2020-06-17 09:49:00 +08:00
liaoxingyu 2123cddb96 update training command line 2020-06-16 19:45:58 +08:00
liaoxingyu 8879db3fba update training instruction 
Summary: update dataset configuration and training instruction
 2020-06-16 19:43:36 +08:00
Lingxiao He 727a746831
Update README.md 2020-06-16 11:46:22 +08:00
Lingxiao He 47cc3c6ead
Update README.md 2020-06-16 11:46:03 +08:00
liaoxingyu eebc71b7c8 update config 
Summary: remove use_cosine_dist in config which is equivalent to euclidean distance with norm feature
 2020-06-16 11:14:58 +08:00
liaoxingyu ecc2b1a790 update naive sampler 
Summary: update naive sampler which will introduce unbalanced sampling
 2020-06-15 20:50:25 +08:00
liaoxingyu 56a1ab4a5d update fast global avgpool 
Summary: update fast pool according to https://arxiv.org/pdf/2003.13630.pdf
 2020-06-12 16:34:03 +08:00
liaoxingyu cbdc01a1c3 update pairwise circle loss 
Summary: add param of pairwise circle loss to config, and update pairwise circle loss version
 2020-06-10 19:07:29 +08:00
liaoxingyu 96b9ad2d99 fix docs in ToTensor 2020-06-10 19:06:03 +08:00
Lingxiao He 896933bf5e
Update DSR Evaluation 2020-06-10 18:16:58 +08:00