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

599 Commits (c576948ec56b904c66173b9d33f35388f9c384d8)
 

Author SHA1 Message Date
zuchen.wang ae842114c7 update dataset config in trainer.py 2021-10-21 10:50:38 +08:00
zuchen.wang 863cb288f7 Merge branch 'master' into wzc/shoe 2021-10-20 18:46:50 +08:00
zuchen.wang 63233fecb0 add Cython in requirments 2021-10-20 18:46:39 +08:00
zuchen.wang 0dd493b7b4 make pair dataset negative sample from full set 2021-10-20 17:04:27 +08:00
zuchen.wang 20ffecebe4 Merge branch 'master' into wzc/shoe 2021-10-19 19:54:09 +08:00
zuchen.wang 4fbcdf6a7b requirments.txt 2021-10-19 19:53:55 +08:00
zuchen.wang ac5ac68621 Merge branch 'wzc/shoe' of gitlab.tools.vipshop.com:vsus_vision/fast-reid into wzc/shoe 2021-10-18 21:13:07 +08:00
zuchen.wang 5770a8963b fix 2021-10-18 21:12:26 +08:00
zuchen.wang 6ab4ac9784 modify logger 2021-10-18 17:38:08 +08:00
zuchen.wang e4c46cbfed add r101-se-ibn.yaml 2021-10-18 17:37:41 +08:00
zuchen.wang 3788c5484b add excel data set 2021-10-18 15:37:25 +08:00
zuchen.wang 3e753612a9 change pair evaluator 2021-10-18 15:36:54 +08:00
zuchen.wang 7190348568 fix pair_dataset random seed in val and test mode 
add ce loss
 2021-10-16 21:42:32 +08:00
zuchen.wang 1feda07ce6 evaluation success 2021-10-16 21:24:16 +08:00
zuchen.wang 786c442391 add bughook in train_net.py 2021-10-16 20:56:01 +08:00
zuchen.wang d87f4a8419 add evaluator in fastshoe trainner 2021-10-16 00:03:00 +08:00
zuchen.wang d162c5fc4e add PairHead 2021-10-15 21:26:16 +08:00
zuchen.wang 8a746acb01 set find_unused_parameters=True 2021-10-13 20:05:08 +08:00
zuchen.wang ef46486804 train contrastive loss 2021-10-13 20:05:08 +08:00
zuchen.wang 8c09ec0d3d update forward 2021-10-13 20:05:08 +08:00
zuchen.wang d2ee44d503 change cls_target to clas_target 2021-10-13 20:05:08 +08:00
zuchen.wang 1bd41a79fc add cls target in pair dataset 2021-10-13 20:05:07 +08:00
zuchen.wang 8b309b0f4e add contrastive loss 2021-10-13 20:05:07 +08:00
zuchen.wang 7201a82840 add pair collator_fn 2021-10-13 20:05:07 +08:00
zuchen.wang bced0d04ff override some method in dataset 2021-10-13 20:05:07 +08:00
zuchen.wang e9cd5311f5 add some paths 2021-10-13 20:05:07 +08:00
zuchen.wang 46c1ce83a7 add fastshoe 2021-10-13 20:05:07 +08:00
zuchen.wang 045b1a88bc fix import error in fastclas 
add bughook.py
 2021-10-13 18:07:44 +08:00
xyliao 10a5f38aaa
fix(dataloader): delete background threading when dataloader is freed (#583) 2021-10-01 16:14:36 +08:00
l1aoxingyu 100830e5ef feat: add wechat QR code 
close #354
 2021-09-23 20:54:49 +08:00
l1aoxingyu d9d6e19b2c fix: fix bugs about import of torch version 2021-09-21 21:42:00 +08:00
l1aoxingyu f4551a128b feat(projects): Add DG-ReID project 2021-09-08 23:10:47 +08:00
xiaomingzhid ee3818e706
Add Semi-Supervised Domain Generalizable Person Re-Identification 2021-09-08 21:11:32 +08:00
Sherlock 00ffa10d3f add workflow for inactive issue auto-close 2021-09-02 14:40:16 +08:00
ViokingTung 2cac19ce31
fix num_vis type error bug in visualizer.py (#566) 2021-09-02 14:30:18 +08:00
Sherlock ced654431b fix bug in attribute evaluation 
# 535
 2021-08-12 14:17:44 +08:00
liaoxingyu 7e652fea2a feat: Add contiguous parameters support 
Support contiguous parameters to train faster. It can split parameters into different contiguous groups by freeze_layer, lr and weight decay.
 2021-07-05 11:10:37 +08:00
keith 44d1e04e9a
Added: mobilenetv3 backbone (#525) 2021-06-30 14:49:28 +08:00
liaoxingyu 7c1269d6c3 minor fix for configs 
#519
 2021-06-24 14:26:51 +08:00
liaoxingyu 2fee8327fa minor fix for configs 
#519
 2021-06-23 17:49:35 +08:00
liaoxingyu 10b04b75ff Support lazy loading in dataset 
Add an option for lazy loading, which will parse the data when using it. Specifically, when calling `dataset.query`, it will start to parse the query data, and `train` and `gallery` will not be parsed in advanced. This is useful when you want to run on test dataset but train dataset is large.

See examples in market1501.py
 2021-06-17 16:59:02 +08:00
liaoxingyu d792a69f3f bugfix for veriwild and vehicleid 
Change `camids` from string to int when evaluation, otherwise, it will raise AttributeError

#497
 2021-06-17 16:52:47 +08:00
liaoxingyu ac6256887c Merge branch 'master' of github.com:L1aoXingyu/fast-reid 2021-06-17 16:07:17 +08:00
liaoxingyu 62ad5e1a8b bugfix for cuda tensor to numpy 
Move cuda tensor to host memory in predictor which can be used for following process.
 2021-06-17 16:05:45 +08:00
Sherlock Liao 4ce04e7cc2
fix typro 2021-06-14 11:34:36 +08:00
Jinkai Zheng f2286e7f55
Updated the way of reading VERI-Wild's TXT files (#507) 
Reviewed by: @L1aoXingyu
 2021-06-11 13:46:46 +08:00
liaoxingyu 4f90197336 add logger for pretrain model downloading 2021-06-08 15:57:47 +08:00
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
liaoxingyu de81b3dbaa fix ClasEvalution too much memory cost 
Compute total number of correct predictions on each batch avoiding keeping all predicted logits, which will cost too much memory when the number of classes is large

#503
 2021-06-07 15:48:47 +08:00
liaoxingyu 8f8cbf9411 fix lr scheduler warning when amp training 
Skip lr scheduler when this iteration creates NaN gradients
 2021-06-02 16:35:46 +08:00