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

200 Commits (0da5917064c1f09f33753a7aeae2b71a9adb4410)

Author SHA1 Message Date
liaoxingyu ea8a3cc534 fix typro 2020-07-10 16:26:35 +08:00
grimoire 76afdd8d66 fix bugs of rank_cylib 2020-07-07 11:12:46 +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 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 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 8879db3fba update training instruction 
Summary: update dataset configuration and training instruction
 2020-06-16 19:43:36 +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
liaoxingyu 3732f94405 update osnet 2020-06-09 14:38:49 +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
liaoxingyu 94d85fe11c fix convert caffe model problem 2020-06-04 16:39:12 +08:00
liaoxingyu e7156e1cfa fix mgn not registered problem 2020-06-03 11:46:28 +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 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
liaoxingyu 5528d17ace refactor code 
Summary: change code style and refactor code, add avgmax pooling layer in gem_pool
 2020-05-28 13:49:39 +08:00
liaoxingyu cd69ba6ffb update augmix augments 
Summary: replace augmix augmentations for adapting reid
 2020-05-27 22:56:31 +08:00
liaoxingyu a1cb123cfa fix R101 bottleneck missing problem 
Summary: add key 101 in block dict to support R101
 2020-05-26 14:48:32 +08:00
liaoxingyu d4b71de3aa switch between soft and hard margin when inf 
Summary: Add a mechnism to automatic switch triplet loss with soft margin to hard margin when loss becomes inf.
 2020-05-26 14:36:33 +08:00
liaoxingyu 5982f90920 support loading various pretrained weights 
Summary: Support loading pretrained model by custom path. With this function, we can load infoMin weights.
 2020-05-26 14:33:18 +08:00
liaoxingyu 5d4758125d support ResNet34 backbone 
Summary: add BasicBlock to support ResNet34
 2020-05-26 13:18:09 +08:00
liaoxingyu 84c733fa85 fix: remove prefetcher, put normalizer in model 
1. remove messy data prefetcher which will cause  confusion
2. put normliazer in model to accelerate training via GPU computing
 2020-05-25 23:39:11 +08:00
liaoxingyu 94c86579a3 fix(heads): fix bug in reduce head 
add neck_feat from config, add inplace in leakyrelu for memory save
 2020-05-23 10:41:13 +08:00
liaoxingyu c21de64166 fix: add linear initial method 2020-05-21 23:59:51 +08:00
liaoxingyu e990cf3e34 style: fix some typro 2020-05-21 15:55:51 +08:00
liaoxingyu 2ac55a7601 feat: update roc curve and TPR@FPR metric 
support plot multiple ROC curves with different model
 2020-05-20 14:29:33 +08:00
liaoxingyu e344eae1cc feat: support plotting roc curve and compute auc score 
ROC curve and AUC score will be help for thresholds
 2020-05-19 20:45:26 +08:00
liaoxingyu fd90555e19 feat: add multi-dataset joint training 
new feature that can support joint training, and find some bugs in funtion combine_all of datasets/bases.py that assume person id in dataset has been relabeld from 0 to num_class.
Another bug appears in msmt17 which trainset and testset person id both begin from 0, and we should change testset id from num_class of trainset.
 2020-05-18 20:06:04 +08:00
liaoxingyu 579a5cf552 fix: modify re-rank typro 2020-05-18 17:05:20 +08:00
liaoxingyu d63bf5facc fix: add syncBN options in defaultTraine 2020-05-16 22:44:53 +08:00
liaoxingyu b28c0032e8 fix: add monkey-patching to enable syncBN 
add a trigger to make syncBN work
 2020-05-15 13:33:33 +08:00
liaoxingyu 18a33f7962 feat: add MGN model 
support MGN architecture and training config
 2020-05-15 11:39:54 +08:00
liaoxingyu bf18479541 fix: revise syncBN bug 2020-05-14 14:52:37 +08:00
liaoxingyu 0872a32621 feat: add syncBN support 2020-05-14 13:15:09 +08:00
liaoxingyu 0356ef8c5c feat: add SyncBN and GroupNorm suppor 2020-05-14 11:36:28 +08:00
liaoxingyu 5ae3d4fecf feat: add aqe support in test phase 
query expansion will combine the retrived topk nearest neighbors with the original query feature,
it will enhance mAP by a large margin.feat:
 2020-05-13 16:27:22 +08:00
liaoxingyu 320010f2ae feat: support re-rank in test phase 2020-05-13 11:47:52 +08:00
Xingyu Liao 01d940bfdd
update vehicle dataset 
Summary: Pull Request resolved: #49 

Reviewed By: xingyu liao
 2020-05-12 21:44:05 +08:00
liaoxingyu 9addfb0ae2 feat: support visualizing label list 
add features to support label list visualization, which can be used
for label correction or check the hardest sample
 2020-05-12 21:35:33 +08:00
Jinkai Zheng 640c9bfc97
Add small, medium and large vehicle test datasets 2020-05-11 01:34:19 -05:00
Jinkai Zheng e059b751a6
Add modified vehicle datasets with small, medium and large test datastes 2020-05-11 01:30:56 -05:00
liaoxingyu 9b6fda3830 style: remove title in visualization 2020-05-11 14:12:29 +08:00
liaoxingyu 13bb03eb07 feat: add rank result visualization tools 
Update visualization tools which can save rank list with AP metrics from high to low, vice versa.
In order to compute AP fast in visualizer, modify rank_cylib to get all_AP instead of mAP.
In this way, we can use Cython to compute results.
 2020-05-10 23:17:10 +08:00
liaoxingyu 651e6ba9c4 feat: support multiprocess predictor 
add asyncpredictor to support multiprocessing feature extraction with dataloader
 2020-05-09 18:23:36 +08:00
liaoxingyu 4be4cacb73 fix: add a simple way to reset data prefetcher when resume training 
use data prefetcher build-in reset function to reload it rather than
redefining a new data prefetcher, otherwise it will introduce other
problems in eval-only mode.
 2020-05-09 11:58:27 +08:00
liaoxingyu 9fae467adf feat(engine/defaults): add DefaultPredictor to get image reid features 
Add a new predictor interface, and modify demo code to predict image features.
 2020-05-08 19:24:27 +08:00
liaoxingyu 8ab0bc2455 style(backbone): make parameters loading logging more elegant 2020-05-08 12:22:06 +08:00
liaoxingyu 0b15ac4e03 feat(hooks&optim): update stochastic weight averging hooks 
Update swa method which will do after regular training if you
set this option enabled.
 2020-05-08 12:20:04 +08:00
liaoxingyu afac8aad5d Fix(engine): fix preciseBN dataloader bugs 
preciseBN needs to pass data prefetcher, but now a DataLoader is passed
 2020-05-06 14:26:34 +08:00
liaoxingyu 948af64fd1 feat: add swa algorithm 
Add swa and related config options,
if it is enabled, model will do swa after regular training
 2020-05-06 10:17:44 +08:00
liaoxingyu 6d96529d4c fix(data): fix resume training bug 
fix dataset pid dictionary loading bug when resume training,
data prefetcher will pre-load a batch of data, this will lead to
misalignment of old pid dict and updated pid dict.
We can address this problem by redefine a prefetcher in resume_or_load
 2020-05-05 23:20:42 +08:00
liaoxingyu a2dcd7b4ab feat(layers/norm): add ghost batchnorm 
add a get_norm fucntion to easily change normalization between batchnorm, ghost bn and group bn
 2020-05-01 09:02:46 +08:00
liaoxingyu 329764bb60 refactor(heads): move num_classes out from heads 
set parameter num_classes in meta_arch to easily modify different heads fc layer
 2020-04-29 21:29:48 +08:00
liaoxingyu d27729c5bb refactor(preciseBN): add preciseBN datasets show 2020-04-29 21:05:53 +08:00
liaoxingyu ec19bcc1d3 style(configs): put all config files together 
put all config files into one place for easily control,
and add tools for put train_net.py which almost the same in
different projects
 2020-04-29 16:18:54 +08:00
liaoxingyu e38a799b63 fix(engine/defaults): fix precise bn bug 
fix problem in precise bn, which will not use precise bn datasets, and throw some errors
 2020-04-29 16:16:54 +08:00
zjk15068083791 2f3f6e3267
Add files via upload 2020-04-27 16:27:44 +08:00
liaoxingyu 5daf322ac6 fix(data/samplers): fix bug in triplet sampler 
use drop indices to avoid two groups of same id,
but did not consider drop indices = 0, then will lead to
indentites[:0], this is a no teminal loop
 2020-04-27 15:25:29 +08:00
liaoxingyu 325d9abb76 feat($solver): change scheduler call methods 
using name of lr scheduler in config to call
 2020-04-27 15:12:01 +08:00
liaoxingyu 9e3f2c1e7a fix($data/transforms): change augmix augmentation pool 
change augmentation_all from augmentation_reid in augmix
because we found AutoAugmentation using ImageNet Policy will not harm performance
 2020-04-27 15:06:27 +08:00
liaoxingyu 4d3e5fd378 refactor(evaluation): add feature l2 norm in evaluation 
change the l2 norm function from inference function in Module to reid evaluation.
because sometimes we need to use the original features generated by model rather than normalized ones.
 2020-04-27 14:51:39 +08:00
liaoxingyu 9910bb9158 fix($modeling/heads): fix targets missing bug 
fix bug in heads about return outputs without targets.
 2020-04-27 14:49:58 +08:00
liaoxingyu 2efbc6d371 fix($modeling/heads/bnneck_head): fix heads outputs bug 
fix bug of heads outputs, which will lead to no targets return.
 2020-04-27 11:48:21 +08:00
liaoxingyu a6bd0371e2 feat($data): add autoaugment 
add auto augmentation support with ImageNet policy and CIFAR10 policy.
modify codes in transforms and config for adapting to this augmentation.
 2020-04-27 11:41:12 +08:00
liaoxingyu 8abd3bab03 feat($layers): add new act func 
add mish, gelu supported
 2020-04-24 12:17:00 +08:00
liaoxingyu 3984f0c91d refactor($modeling/meta): refactor heads output 
without intermediate variables generated by reid heads, make it more flexible
 2020-04-24 12:16:18 +08:00
liaoxingyu e3ae03cc58 feat($modeling/backbones): add new backbones 
add osnet, resnext and resnest backbone supported
 2020-04-24 12:14:56 +08:00
liaoxingyu b098b194ba refactor($modeling/meta_arch): remove bdb_network 2020-04-21 11:44:29 +08:00
liaoxingyu 6c9af664dc refactor($modeling/meta_arch): remove useless parts 
remove useless meta_archs and backbones
 2020-04-21 11:42:14 +08:00
liaoxingyu bb50b6c5a7 docs($projects): update agw readme 2020-04-21 11:35:54 +08:00
liaoxingyu 95a3c62ad2 refactor(fastreid) 
refactor architecture
 2020-04-20 10:59:29 +08:00
liaoxingyu 9684500a57 chagne arch 
1. change dataset show to trainset show and testset show seperately
2. add cls layer to easily plug in circle loss and arcface
 2020-04-19 12:54:01 +08:00
liaoxingyu be9faa5605 update focal loss 
update dataset info display
update seperate lr
update adaptive label smooth regularization
 2020-04-17 13:46:10 +08:00
liaoxingyu 9cf222e093 refactor bn_no_bias 2020-04-08 21:04:09 +08:00
liaoxingyu 4d2fa28dbb update freeze layer 
update preciseBN
update circle loss with metric learning and cross entropy loss form
update loss call methods
 2020-04-06 23:34:27 +08:00
liaoxingyu 6a8961ce48 1. upload circle loss and arcface 
2. finish freeze training
3. update augmix data augmentation
 2020-04-05 23:54:26 +08:00
liaoxingyu c6e0176c53 Upload demo.py and example 2020-04-03 15:07:27 +08:00
liaoxingyu eacee874aa fix merge 2020-03-25 11:06:39 +08:00
liaoxingyu 91dc9bc71f Merge branch 'master' of github.com:L1aoXingyu/fast-reid 
 Conflicts:
	fastreid/config/defaults.py
	fastreid/layers/gem_pool.py
	fastreid/modeling/backbones/resnet.py
	fastreid/modeling/heads/__init__.py
	fastreid/modeling/heads/build.py
	fastreid/modeling/losses/build.py
	fastreid/modeling/meta_arch/__init__.py
	fastreid/modeling/meta_arch/abd_network.py
	fastreid/modeling/meta_arch/baseline.py
	fastreid/modeling/meta_arch/bdb_network.py
	fastreid/modeling/meta_arch/mf_network.py
	projects/StrongBaseline/configs/Base-Strongbaseline.yml
	projects/StrongBaseline/configs/baseline_dukemtmc.yml
	projects/StrongBaseline/train_net.py
 2020-03-25 11:05:28 +08:00
liaoxingyu 23bedfce12 update version0.2 code 2020-03-25 10:58:26 +08:00
L1aoXingyu b1058118ca update BDB-net code 
update MF-net code
 2020-03-19 12:23:41 +08:00
L1aoXingyu acf363c181 1. Change loss function as a build-in attributes of heads 
2. Update agw and bagtricks result
 2020-03-16 15:23:09 +08:00
L1aoXingyu bab602dfd2 Fix minor bug in build criterion, it will replace by multiple call 
Refactor resnet pretrain
 2020-02-28 21:20:41 +08:00
L1aoXingyu b020c7f0ae Fix data prefetcher minor bug 2020-02-27 12:16:57 +08:00
L1aoXingyu 12957f66aa Change architecture: 
1. delete redundant preprocess
2. add data prefetcher to accelerate data loading
3. fix minor bug of triplet sampler when only one image for one id
 2020-02-18 21:01:23 +08:00
L1aoXingyu e01d9b241f Update AGW baseline result 2020-02-13 20:37:08 +08:00
L1aoXingyu 327d74ffbb Update strong baseline result 
Change data sampler
 2020-02-13 00:19:15 +08:00
L1aoXingyu a2f69d0537 Update StrongBaseline results for market1501 and dukemtmc 2020-02-11 22:38:40 +08:00
L1aoXingyu 8a9c0ccfad Finish first version for fastreid 2020-02-10 22:13:04 +08:00
L1aoXingyu db6ed12b14 Update sampler code 2020-02-10 07:38:56 +08:00
liaoxingyu 71950d2c09 1. Fix evaluation code 
2. Finish multi-dataset evaluation
3. Decouple image preprocess and output postprocess with model forward for DataParallel training
4. Finish build backbone registry
5. Fix dataset sampler
 2020-01-21 20:24:26 +08:00
liaoxingyu b761b656f3 Finish basic training loop and evaluation results 2020-01-20 21:33:37 +08:00