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

415 Commits (b5c3c0a24ded247bc6309c9b25f3ae8ca615d234)
 

Author SHA1 Message Date
liaoxingyu b5c3c0a24d update docs 2021-01-22 21:11:19 +08:00
liaoxingyu 274cd81dab update docs 2021-01-22 21:06:30 +08:00
liaoxingyu 6ab40bd43a change CrossDomainReID repo name 2021-01-22 11:19:14 +08:00
liaoxingyu e26182e6ec make lr warmup by iter 
Summary: change warmup way by iter not by epoch, which will make it more flexible when training small epochs
 2021-01-22 11:17:21 +08:00
liaoxingyu fdaa4b1a84 update readme 2021-01-18 13:51:02 +08:00
liaoxingyu 7e83d3175f update README.md 
Summary: add information about fastreid V1.0
 2021-01-18 11:44:55 +08:00
liaoxingyu 15e1729a27 update fastreid V1.0 2021-01-18 11:36:38 +08:00
Xingyu Liao 15213dde4b
add workflow to lint Python code 
Summary: merge PR about linting Python code
 2021-01-16 11:25:49 +08:00
liaoxingyu c49414bb9f fix SE layer of basicblock in resnet (#375) 
Summary: SE layer defined in `__init__` but not used in `forward`

close #375
 2021-01-04 10:46:54 +08:00
liaoxingyu 63c952f3cf remove extra file 2020-12-31 10:53:24 +08:00
liaoxingyu ce86c6959d upload fastreid logo 2020-12-30 16:15:06 +08:00
liaoxingyu 2c17847980 feat: freeze FC 
Summary: update freeze FC in the last stages of training
 2020-12-28 14:46:28 +08:00
liaoxingyu fe2e46d40e fix arcSoftmax fp16 training problem 
Summary: fixup fp16 training when using arcSoftmax by aligning the data type
 2020-12-28 14:45:26 +08:00
liaoxingyu 20a01f2545 fix grayscale image input problem 
Summary: handle grayscale images mixed in RGB images by adding the image channels
 2020-12-28 14:45:09 +08:00
liaoxingyu 8083547613 add kwargs for convenient dataset parameters passing (#290) 
Summary: make it more easy for passing dataset kwargs through `build_reid_train_loader`
 2020-12-28 14:39:08 +08:00
liaoxingyu 0e1b91f74a fix checkpoint bug in ddp training 
Summary: change pytorch ddp to apex ddp in checkpoint
 2020-12-28 14:35:02 +08:00
liaoxingyu f56ca8345e fix keywords error 
Summary: add `freeze_fc` and `flip_test` keywords
 2020-12-28 14:34:18 +08:00
Xingyu Liao 0428a270e3
update veri dataset 
Summary: update veri dataset reference information

Reviewed By: l1aoxingyu
 2020-12-22 18:01:37 +08:00
liaoxingyu 766f309d03 feat: update pairwise cosface and pairwise circle loss 2020-12-22 15:51:49 +08:00
liaoxingyu 66941cf27a feat: support flip testing 2020-12-22 15:50:50 +08:00
liaoxingyu bb7a00e615 feat: add save best model checkpoint 2020-12-22 15:50:23 +08:00
liaoxingyu 5469e8ce76 feat: add save best model mechanism 2020-12-22 15:49:46 +08:00
liaoxingyu 04fe9fb2d8 add saivt dataset 2020-12-22 15:47:08 +08:00
liaoxingyu e8739a667e update AirportALERT dataset 
Summary: add more IDs from the single camera
 2020-12-22 15:36:50 +08:00
Xinchen Liu 218a007b6a
Update veri.py 2020-12-21 16:19:06 +08:00
liaoxingyu 130199fdce remove invalid config 2020-12-07 14:23:43 +08:00
liaoxingyu a327a70f0d v0.3 update 
Summary:
1. change DPP training in apex way;
2. make warmup scheduler by iter and lr scheduler by epoch;
3. replace random erasing with torchvision implementation;
4. naming modification in config file
 2020-12-07 14:19:20 +08:00
liaoxingyu 1b9799f601 fix demo eval bug (#345) 
Summary: Fix bug in demo.py when computing cmc and mAP in `evaluate_rank`. This is because after changing eval function, the passing params in demo are not changed.

close #345
 2020-12-04 11:14:18 +08:00
Christian Clauss 96aadfa707
Update lint_python.yml 2020-11-26 14:28:52 +01:00
liaoxingyu 2724515fd9 save class number to config (#281) 
Summary: Save the class number calculated based on datasets to the config file. If you hard-code the class number, make it unchanged.
 2020-11-06 16:07:37 +08:00
liaoxingyu 7e9a4775da fixup finetune problem 
Summary: support finetune from the other model with different number of classes, and simplify calling way (#325)

close #325

close #325
 2020-11-06 15:58:22 +08:00
liaoxingyu f496193f17 change cross_entroy_loss input name 
Summary: change `pred_class_logits` to `pred_class_outputs` to prevent misleading. (#318)

close #318
 2020-11-06 14:16:31 +08:00
liaoxingyu2 a00e50d37f fix triplet ddp training 
Summary: fixup precision alignment when triplet loss with ddp
 2020-11-06 11:01:10 +08:00
liaoxingyu2 64bf78afee update rank_cylib 2020-11-06 11:00:13 +08:00
liaoxingyu2 3bd2fad9a5 support faiss-based rerank 
Summary: accelerate rerank with faiss-gpu
 2020-11-06 10:59:53 +08:00
liaoxingyu2 42cadaeebc update backbone and config 
Summary: update resnet backbone for adaptation caffe export; modify effnet loading keyword
 2020-11-06 10:58:38 +08:00
liaoxingyu a5dac37bea update bohb search space 2020-10-12 20:21:47 +08:00
liaoxingyu e5c3ff3b5b fix typro in hpo training 2020-10-10 18:55:32 +08:00
liaoxingyu 8d55a0bbd4 add more hpo search algorithms 
Summary: support hyperopt, bohb and population based training
 2020-10-10 17:35:25 +08:00
liaoxingyu bd395917a8 fix splat layer problem (#297) 
Summary: fix get_norm problem in splat.py
 2020-10-09 11:21:36 +08:00
liaoxingyu caf11b5cc6 add checkpoint in hpo 2020-10-01 18:12:51 +08:00
liaoxingyu 008e4f700a Merge remote-tracking branch 'origin/master' 2020-10-01 18:10:19 +08:00
liaoxingyu 85cebe311f support hpo project 
Summary: support BOHB search algorithm for reid.
 2020-10-01 18:10:02 +08:00
liaoxingyu 4629172a90 update distill reid readme 2020-10-01 18:09:18 +08:00
Xingyu Liao ad9046c46e
add conda install (#259) 
support quick set up with conda
 2020-10-01 11:23:32 +08:00
liaoxingyu bd5aaf386a add student model load path 2020-09-30 16:45:46 +08:00
liaoxingyu 69f4407267 update distill reid project (#287) 
Summary: refactor distill reid code and config files
 2020-09-30 16:05:58 +08:00
liaoxingyu 3d1bae9f13 fix triplet loss backward propagation on multi-gpu training (#82) 
Summary: fix torch.distributed.all_gather has no gradient when performing all_gather operation on the provided tensors, instead using `GatherLayer`.
 2020-09-28 17:16:51 +08:00
liaoxingyu 10cbaab155 support finetuning from trained models 
Summary: add a flag for supporting finetuning model from the trained weights, and it's very useful when performing across domain reid
 2020-09-28 17:10:10 +08:00
liaoxingyu 3024cea3a3 add more datasets 
Summary: add wildtracker.py datasets and cuhk_sysu.py datasets.
 2020-09-28 17:05:40 +08:00