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

482 Commits (bb6ddbf8b15520bae9090827f0ab3dc8cf3b1337)
 

Author SHA1 Message Date
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
Lingxiao He 7f753027c5
update dsr evaluation 2020-06-10 18:10:30 +08:00
Lingxiao He fa0728a0c7
dsr_head 2020-06-10 17:43:56 +08:00
liaoxingyu 27c48c8f02 update pytorchtocaffe tool 
Summary: update pytorch to caffe toolchain to support model layers and bash scripts
 2020-06-09 14:45:27 +08:00
liaoxingyu 3732f94405 update osnet 2020-06-09 14:38:49 +08:00
liaoxingyu 6ee38cd562 add cite bibtex 2020-06-07 18:45:28 +08:00
liaoxingyu dd050c43eb update blog url 2020-06-06 22:55:10 +08:00
liaoxingyu 25a7f82df7 change style in baseline 2020-06-05 11:23:11 +08:00
liaoxingyu bc221cb05f fix mgn multi-gpu training problem 
Summary: norm_type in pool_reduce will not change when use syncBN
 2020-06-05 11:11:50 +08:00
Jinkai Zheng db8cb19ac4
Fix the typing error 
Fix the typing error about "BOT(R50-ibn)" to "SBS(R50-ibn)" on VeRi.
 2020-06-04 21:04:30 +08:00
liaoxingyu 94d85fe11c fix convert caffe model problem 2020-06-04 16:39:12 +08:00
Xingyu Liao 12ee19d6ed
fix python syntax error 
Reviewed by: l1aoxingyu
 2020-06-04 13:56:50 +08:00
Christian Clauss d7cf32a652
Fix a Python syntax error discovered by #77 2020-06-03 14:32:46 +02:00
Christian Clauss 1ce7e67175
GitHub Action to lint Python code 2020-06-03 14:29:42 +02:00
liaoxingyu e7156e1cfa fix mgn not registered problem 2020-06-03 11:46:28 +08:00
liaoxingyu 69e4ba901e update acknowledgement in deploy 2020-06-02 18:12:57 +08:00
liaoxingyu 2f6d999469 add pytorch to caffe converting 
Summary: update deployment README and support pytorch to caffe converting for basemodel
 2020-06-02 18:11:02 +08:00
liaoxingyu 6ed6d25c6c Merge branch 'master' of github.com:L1aoXingyu/fast-reid 2020-06-02 10:19:25 +08:00
liaoxingyu a9e3ffa257 update readme and install 2020-06-02 10:19:20 +08:00
Xingyu Liao 7064ce1d83
Update PartialReID README.md 
Reviewed by: l1aoxingyu
 2020-06-01 10:45:14 +08:00
Lingxiao He 29f318c609
Update README.md 
Update the details of datasets
 2020-06-01 10:42:33 +08:00
liaoxingyu 9c09a424c4 update zhihu article url in readme 2020-05-31 23:32:49 +08:00
liaoxingyu 85672b1e75 add circle & arcface layer info 
Summary: show num_features and num_classes in circle & arcface layer, like nn.Linear
 2020-05-31 15:50:56 +08:00
liaoxingyu e2761f7581 fix style in comm dataset 2020-05-30 16:56:08 +08:00
liaoxingyu c036ac5bdd update reduction head 2020-05-30 16:50:02 +08:00
liaoxingyu 449ec7e701 Merge branch 'master' of github.com:L1aoXingyu/fast-reid 2020-05-30 16:44:24 +08:00
liaoxingyu 36c04f0a9f fix resume training problem 
Summary: when resume training, need to reiter dataloader because we update pid_dict in dataset, but dataloader with multiprocess won't do the same update
 2020-05-30 16:44:18 +08:00