KaiyangZhou
|
454fe67abe
|
avoid huge memory consumption at eval
|
2021-01-22 16:20:51 +08:00 |
|
KaiyangZhou
|
7c2ee1e6c6
|
update printing in triplet engine (taking into account weight_t & weight_x)
|
2020-08-12 11:03:24 +01:00 |
|
KaiyangZhou
|
de42729f41
|
v1.3.1: record results (rank1 & mAP) of each target dataset
|
2020-08-10 22:06:15 +01:00 |
|
KaiyangZhou
|
5656aaba85
|
bug fix in VideoTripletEngine
|
2020-08-03 16:17:49 +01:00 |
|
KaiyangZhou
|
069356a6e4
|
update comment
|
2020-08-03 16:03:31 +01:00 |
|
KaiyangZhou
|
b075bd3f4b
|
show lr of last group of params (typically new layers) as default
|
2020-06-23 18:17:10 +01:00 |
|
KaiyangZhou
|
aefe335d68
|
use dict as return of dataloader
|
2020-06-23 13:59:57 +01:00 |
|
KaiyangZhou
|
6081989d7e
|
change fetch_qg() to fetch_test_loaders()
|
2020-05-05 16:45:22 +01:00 |
|
KaiyangZhou
|
5ce43185b1
|
linting code
|
2020-05-05 15:58:00 +01:00 |
|
KaiyangZhou
|
d60ca7f224
|
minor changes
|
2020-05-05 12:48:58 +01:00 |
|
KaiyangZhou
|
89bf30bd14
|
update few names of class methods
|
2020-05-05 12:43:28 +01:00 |
|
KaiyangZhou
|
85c446ec97
|
renaming: loss_dict to loss_summary
|
2020-04-16 21:57:49 +01:00 |
|
KaiyangZhou
|
b184fba029
|
save as attribute the vars about steps
|
2020-04-16 21:41:01 +01:00 |
|
KaiyangZhou
|
36e22e8ce1
|
make engine more model-agnostic
|
2020-04-16 12:46:15 +01:00 |
|
KaiyangZhou
|
469a038d01
|
add scheduler to resume_from_checkpoint
|
2019-12-10 10:44:45 +00:00 |
|
KaiyangZhou
|
08bb2cc5eb
|
linting and formatting code
|
2019-12-02 14:34:59 +00:00 |
|
KaiyangZhou
|
42eaccea71
|
linting and formatting code
|
2019-12-02 12:34:17 +00:00 |
|
KaiyangZhou
|
58e6841a33
|
update relative import
|
2019-12-01 03:31:32 +00:00 |
|
KaiyangZhou
|
6b8fe56638
|
linting and formatting code
|
2019-12-01 02:35:44 +00:00 |
|
KaiyangZhou
|
7e71f72846
|
give self.writer as argument to engine.train()
|
2019-11-27 16:52:58 +00:00 |
|
KaiyangZhou
|
307e38e519
|
add use_unlabeled_targets
|
2019-11-27 16:35:54 +00:00 |
|
KaiyangZhou
|
5c9bac5e75
|
minor modification
|
2019-11-27 11:09:13 +00:00 |
|
KaiyangZhou
|
2689fc0c57
|
rm type-checking for self.model in engine.py
|
2019-11-24 13:42:46 +00:00 |
|
KaiyangZhou
|
a136384a6a
|
rm unused imports/variables; fixed minor bugs
|
2019-10-23 17:15:37 +01:00 |
|
kaiyangzhou
|
cf553d367f
|
bug fix: pass video-specific args to dataset.__add__
|
2019-10-04 12:09:28 +01:00 |
KaiyangZhou
|
5365619606
|
add config
|
2019-08-26 10:34:31 +01:00 |
|
KaiyangZhou
|
92f1ea215a
|
add tensorboard
|
2019-08-22 22:41:21 +01:00 |
|
KaiyangZhou
|
1558389f37
|
osnet.py: rename residual->identity; engine: add num_batches=len(dloader)
|
2019-08-21 23:02:05 +01:00 |
|
KaiyangZhou
|
a20f8a66bd
|
output_featuremaps_only -> return_featuremaps
|
2019-08-05 14:01:39 +01:00 |
|
KaiyangZhou
|
e4fb577693
|
update docs for visrank and visactmap
|
2019-08-03 23:12:37 +01:00 |
|
KaiyangZhou
|
84249ad412
|
[update visactmap] change channel order
|
2019-08-03 23:01:21 +01:00 |
|
KaiyangZhou
|
a08a85d8e4
|
[update visactmap] use cv2.imwrite instead of pyplot
|
2019-08-03 21:42:50 +01:00 |
|
KaiyangZhou
|
7e0249a084
|
add output_featuremaps_only to foward() in osnet
|
2019-08-03 18:25:34 +01:00 |
|
KaiyangZhou
|
3d64d9eaed
|
add default font size to visactmap
|
2019-08-03 18:07:51 +01:00 |
|
KaiyangZhou
|
27d4f2f093
|
add visactmap code; upgrade visrank to plot single figure
|
2019-08-03 17:35:06 +01:00 |
|
KaiyangZhou
|
fb4d585127
|
(epoch+1)>=start_eval
|
2019-06-13 23:11:07 +01:00 |
|
kaiyangzhou
|
f57d88decf
|
move fixbase into train
|
2019-05-24 15:36:10 +01:00 |
|
KaiyangZhou
|
79abbacb1c
|
add print msg
|
2019-05-09 23:21:04 +01:00 |
|
KaiyangZhou
|
3e10dc60dc
|
add --normalize-feature to args parser
|
2019-05-09 23:11:10 +01:00 |
|
KaiyangZhou
|
5839a026c3
|
add person reranking
|
2019-05-09 22:47:55 +01:00 |
|
KaiyangZhou
|
024913f73c
|
update readme
|
2019-05-06 10:48:03 +01:00 |
|
KaiyangZhou
|
4b93121496
|
minor
|
2019-04-19 11:52:02 +01:00 |
|
KaiyangZhou
|
4a033659b0
|
do not decay lr while fixbase=True
|
2019-03-29 11:40:23 +00:00 |
|
KaiyangZhou
|
4cf18f0830
|
print domain info while doing evaluation
|
2019-03-27 22:30:08 +00:00 |
|
KaiyangZhou
|
1e9d466f42
|
move scheduler.step() to train()
|
2019-03-27 13:01:39 +00:00 |
|
KaiyangZhou
|
1e7bbc3668
|
add \n
|
2019-03-25 16:27:39 +00:00 |
|
KaiyangZhou
|
a0e54ede32
|
add scripts
|
2019-03-24 11:06:12 +00:00 |
|
KaiyangZhou
|
d0fe37c558
|
finalize docs
|
2019-03-23 23:09:39 +00:00 |
|
KaiyangZhou
|
aa98ef5a7b
|
add docstrings to losses, metrics, models, utils, optim
|
2019-03-22 00:14:41 +00:00 |
|
KaiyangZhou
|
46a0d5c27d
|
update dataset and docs
|
2019-03-21 12:53:21 +00:00 |