cf091c31f1
v1.2.2
2020-05-05 12:44:08 +01:00
89bf30bd14
update few names of class methods
2020-05-05 12:43:28 +01:00
1708c008ad
add argument train_sampler_t (sampler for target train loader)
2020-05-05 11:14:08 +01:00
8e5fc471a6
1.2.1: add simple API for feature extraction
2020-05-04 12:35:45 +01:00
85c446ec97
renaming: loss_dict to loss_summary
2020-04-16 21:57:49 +01:00
b184fba029
save as attribute the vars about steps
2020-04-16 21:41:01 +01:00
b03488b475
upgrade to 1.2.0
2020-04-16 13:15:26 +01:00
36e22e8ce1
make engine more model-agnostic
2020-04-16 12:46:15 +01:00
99e719f16e
__version__=1.0.9
2019-12-10 10:49:17 +00:00
469a038d01
add scheduler to resume_from_checkpoint
2019-12-10 10:44:45 +00:00
4cc4adb54a
add space to make code clearer in transforms.py
2019-12-02 22:27:35 +00:00
188b7f321f
fixed missing import in osnet
2019-12-02 22:24:24 +00:00
08bb2cc5eb
linting and formatting code
2019-12-02 14:34:59 +00:00
42eaccea71
linting and formatting code
2019-12-02 12:34:17 +00:00
5c88e3664f
minor
2019-12-01 03:35:09 +00:00
58e6841a33
update relative import
2019-12-01 03:31:32 +00:00
ac7bd67484
import data, engine, etc. in torchreid/__init__.py
2019-12-01 02:39:29 +00:00
6b8fe56638
linting and formatting code
2019-12-01 02:35:44 +00:00
2095ee05c5
[1.0.8] load_unlabeled_targets -> load_train_targets
2019-11-27 21:20:04 +00:00
7d8431cf49
bug fix for load_unlabeled_targets
2019-11-27 18:19:06 +00:00
41b1e485ec
1.0.7
2019-11-27 17:20:48 +00:00
7e71f72846
give self.writer as argument to engine.train()
2019-11-27 16:52:58 +00:00
86012a4571
add compute_mean_std tool
2019-11-27 16:49:29 +00:00
307e38e519
add use_unlabeled_targets
2019-11-27 16:35:54 +00:00
5c9bac5e75
minor modification
2019-11-27 11:09:13 +00:00
2689fc0c57
rm type-checking for self.model in engine.py
2019-11-24 13:42:46 +00:00
53784903e3
add SequentialSampler
2019-11-24 13:40:54 +00:00
aebb6033e0
add ibn-net
2019-11-10 21:31:28 +00:00
45091f4f85
add __homepage__
2019-11-04 10:47:49 +00:00
db00cf5fc3
Fix bugs about dataset of cuhk02.py
...
Fix bugs about dataset of cuhk02.py.
2019-10-29 10:58:39 +08:00
cab4a342cc
v1.0.6
2019-10-23 17:20:34 +01:00
a136384a6a
rm unused imports/variables; fixed minor bugs
2019-10-23 17:15:37 +01:00
9397956920
update version number to 1.0.5
2019-10-22 23:06:25 +01:00
edf0b73e21
add OSNet-AIN code
2019-10-22 22:48:53 +01:00
fad38231c1
add radam optimizer
2019-10-22 22:47:08 +01:00
894de59bff
add new ref to osnet.py
2019-10-22 22:46:30 +01:00
1a5db72550
update annotation in RandomPatch
2019-10-22 22:45:48 +01:00
17887c05fd
version=1.0.3
2019-10-04 12:15:32 +01:00
cf553d367f
bug fix: pass video-specific args to dataset.__add__
2019-10-04 12:09:28 +01:00
7a73dca4ac
bug fix: img_path->path
2019-09-13 23:23:13 +01:00
0a60d2c6a7
version=1.0.2
2019-09-01 15:04:14 +01:00
0ec14d9afc
add random patch data augmentation
2019-09-01 15:03:42 +01:00
9131c537d5
[upgrade to 1.0.1] add cuhk02
2019-08-29 17:05:29 +01:00
5507b38c86
update v0.9.4 to v1.0.0
2019-08-26 13:26:10 +01:00
5365619606
add config
2019-08-26 10:34:31 +01:00
046ff13c07
minor change
2019-08-23 22:09:35 +01:00
d9cdb584e2
0.9.4
2019-08-23 22:05:09 +01:00
f4451e5ea9
fix visrank bug for video reid
2019-08-23 22:04:36 +01:00
2383698d52
Fix Visual Rank Video Reid Error
...
Fix video reid error while making sure it still works for image reid.
When trying to save visual ranks for video reid. It crashes on statement `qdir = osp.join(save_dir, osp.basename(osp.splitext(qimg_path)[0]))` that is because qimg_path can be a tuple or list for video reid. Hence, osp.splittext gives error when input is not a str. To fix this I make sure that osp.splitext always gets pass an str regardless if we doing video or image reid.
Let me know if you have any questions.
2019-08-23 12:12:32 -07:00
a23817173c
upgrade to 0.9.3
2019-08-22 23:32:23 +01:00
KaiyangZhou
Yao Lu
KaiyangZhou
Abner Ayala-Acevedo