Xingyu Liao
31d99b793f
Fix weight url in resnest ( #609 )
...
Co-authored-by: wsqshiqing <wzuchen@gmail.com>
2021-12-26 16:15:42 +08:00
Cathesilta
fb1027de4c
Debugged a torchvision version problem ( #600 )
...
Co-authored-by: wangshen <aibee@wangshen.local>
2021-12-03 10:30:52 +08:00
l1aoxingyu
9208930c11
Merge branch 'master' of https://github.com/JDAI-CV/fast-reid
2021-11-20 11:12:27 +08:00
l1aoxingyu
581bddbbdc
register mobilenetv3
2021-11-20 10:52:06 +08:00
Sherlock
c45d9b2498
add interpreter project
2021-10-29 11:46:12 +08:00
l1aoxingyu
43da387b77
feat: let compile evaluation cython automatically
2021-10-21 14:41:38 +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
liaoxingyu
2d2279be6a
refactor freeze training condition
2021-06-02 15:55:35 +08:00
liaoxingyu
764fa67fe9
Align bagtricks config with v1.2
2021-06-01 11:51:22 +08:00
liaoxingyu
3c2eeb865d
update readme
2021-05-31 18:33:48 +08:00
liaoxingyu
0572765085
fix for lint_python
2021-05-31 17:40:33 +08:00
liaoxingyu
54f96ba78a
fix for lint_python
2021-05-31 17:36:56 +08:00
liaoxingyu
6300bd756e
Bugfix for cls_layer
...
In `any_softmax`, all operations are in-place, so pass into the `logits.clone()` to prevent outside logits changed.
2021-05-31 17:32:24 +08:00
liaoxingyu
c3ac4f504c
Support amp and resume training in fastface
...
AMP in partial-fc needs to be done only on backbone; In order to impl `resume training`, need to save & load different part of classifier weight in each GPU.
2021-05-31 17:30:43 +08:00
liaoxingyu
91ff631184
Minor changes
...
Some minor changes, such as class name changing, remove extra blank line, etc.
2021-05-31 17:27:14 +08:00
liaoxingyu
8ab3554958
Support self-distill with EMA updated model
2021-05-31 17:17:24 +08:00
liaoxingyu
256721cfde
Impl freezebb in optimizer's step()
...
Make impl. of `freezebb` consistent with impl. of grad clip, and both are implemented through step() in optimizer
2021-05-31 17:15:26 +08:00
liaoxingyu
07b8251ccb
Support gradient clip
...
Follow detectron2's instruction and add gradient clip in step function of optimizer
2021-05-31 17:11:37 +08:00
liaoxingyu
2cabc3428a
Support vision transformer backbone
2021-05-31 17:08:57 +08:00
liaoxingyu
2b65882447
change way of layer freezing
...
Remove `find_unused_parameters` in DDP and add a new step function in optimizer for freezing backbone. It will accelerate training speed in this way.
2021-05-25 15:57:09 +08:00
liaoxingyu
dbf1604231
fix model deploy problems
2021-05-25 15:55:43 +08:00
Sherlock Liao
ff8a958fff
bugfix for plain_train_net.py and lr scheduler step ( #484 )
2021-05-11 15:46:17 +08:00
Xingyu Liao
46b0681313
fix randompatch ( #470 )
2021-04-21 17:08:16 +08:00
liaoxingyu
0c8e3d9805
update imbalanced sampler
...
Summary: add a new sampler, which is useful for imbalanced or long-tail dataset. This refers to ufoym/imbalanced-dataset-sampler.
2021-04-21 17:05:10 +08:00
Xingyu Liao
bb6ddbf8b1
bugfix for visualize and demo ( #468 )
...
Summary minor bugs for visualize and demo caused by revised DataLoader
2021-04-21 16:24:34 +08:00
Darren
37ccd3683d
unify gen_wts.py and inference.cpp dummy test value. ( #457 )
...
Reviewed by: @L1aoXingyu
2021-04-19 10:23:15 +08:00
Darren
8276ccf4fd
[v005] set INT8 calibrate set via cmake ( #459 )
...
Reviewed by: @L1aoXingyu
2021-04-19 10:22:48 +08:00
liaoxingyu
e124a9afd3
fix lint_python
2021-04-12 15:08:39 +08:00
Darren
e0ad8c70bc
update dockerfile in fastrt ( #437 )
...
Reviewed by: @L1aoXingyu
2021-04-12 15:06:13 +08:00
