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

48 Commits (2f29228086822cf56bdd5cdb368b56f3ed0c7dfc)

Author SHA1 Message Date
liaoxingyu 919a515eb7 fix combine all training 2020-09-09 15:28:21 +08:00
liaoxingyu 866a196d19 add more datasets support 2020-09-01 16:13:12 +08:00
liaoxingyu f06c8b2ed9 fix bug: make CJ works #239 
fix #239
 2020-08-25 11:31:49 +08:00
liaoxingyu 5ea89bf607 fix bug in sampler 
Summary: remove set, which will lead to a bug in random choice.
 2020-08-21 14:54:17 +08:00
liaoxingyu 9844760d7f fix naive sampler time-consuming problem 
Summary: list.remove has O(n) time complexity and use set instead.
 2020-08-20 15:44:26 +08:00
liaoxingyu 2c0320da1a fix bug in pid_dict 
Summary: id index will be different in different machine.
This will lead to different fc layer when training on different machine.
 2020-08-20 15:41:14 +08:00
liaoxingyu a5550d7725 fix balanced sampler bug 
Summary: fix typing error in balanced sampler with missing `len` in ret.
 2020-08-19 16:28:10 +08:00
liaoxingyu 9c667d1a0f add pretrain_path support in backbone 2020-08-14 14:00:26 +08:00
liaoxingyu e0cf8ac56e fix sampler problem #217 
Fix problem about periodic long waiting time when number of images is large.

In the old version, it will prepare the whole epoch indices when finishing one epoch.
Now it changes to prepare the current batch indices.
 2020-08-14 13:57:22 +08:00
liaoxingyu 57ebf75f83 fix bug about changing cfg values 2020-08-10 10:29:24 +08:00
liaoxingyu d516d59fb5 fix autoaug total_iter bug #219 
max_epoch does not convert to max_iter when needing to build dataloader first
add extra convert in `build_reid_train_loader`
 2020-08-09 19:43:01 +08:00
liaoxingyu d1c20cbe50 fix pre-train model bugs 
fix bugs locks when downloading pre-train model
 2020-08-04 15:56:36 +08:00
liaoxingyu 977aa4a357 update model url 2020-07-31 14:59:37 +08:00
liaoxingyu 65169b40bd support ddp testing 2020-07-30 20:15:28 +08:00
liaoxingyu 16655448c2 onnx/trt support 
Summary: change model pretrain mode and support onnx/TensorRT export
 2020-07-29 17:43:39 +08:00
liaoxingyu 3f35eb449d minor update 2020-07-14 11:58:06 +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 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 96b9ad2d99 fix docs in ToTensor 2020-06-10 19:06:03 +08:00
liaoxingyu e2761f7581 fix style in comm dataset 2020-05-30 16:56:08 +08:00
liaoxingyu cd69ba6ffb update augmix augments 
Summary: replace augmix augmentations for adapting reid
 2020-05-27 22:56:31 +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 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
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 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 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 d27729c5bb refactor(preciseBN): add preciseBN datasets show 2020-04-29 21:05:53 +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 9e3f2c1e7a fix($data/transforms): change augmix augmentation pool 
change augmentation_all from augmentation_reid in augmix
because we found AutoAugmentation using ImageNet Policy will not harm performance
 2020-04-27 15:06:27 +08:00
liaoxingyu a6bd0371e2 feat($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 bb50b6c5a7 docs($projects): update agw readme 2020-04-21 11:35:54 +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 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 23bedfce12 update version0.2 code 2020-03-25 10:58:26 +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 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