liaoxingyu
06f22b9674
update model config url
2020-05-29 10:10:43 +08:00
liaoxingyu
8cbc1ed83f
update readme and instruction
2020-05-28 20:01:20 +08:00
liaoxingyu
5528d17ace
refactor code
...
Summary: change code style and refactor code, add avgmax pooling layer in gem_pool
2020-05-28 13:49:39 +08:00
liaoxingyu
d63a3ce47c
update partialreid code
...
Summary: update partialreid training config and code
2020-05-28 11:14:13 +08:00
liaoxingyu
cd69ba6ffb
update augmix augments
...
Summary: replace augmix augmentations for adapting reid
2020-05-27 22:56:31 +08:00
liaoxingyu
5120f77230
Merge branch 'master' of github.com:L1aoXingyu/fast-reid
2020-05-27 22:54:45 +08:00
liaoxingyu
9bef814155
update visulize logger
2020-05-27 22:53:27 +08:00
Xingyu Liao
adbc8185db
update cross-domain results
...
Reviewed by: l1aoxingyu
2020-05-27 22:44:50 +08:00
liaoxingyu
fbbd76b21f
update readme in DSR
2020-05-27 22:43:20 +08:00
liaoxingyu
2e09f424a5
fix typro
...
Summary: fix typro in HAA
2020-05-27 22:41:12 +08:00
liaoxingyu
90b0140497
update DSR projects
...
Summary: update DSR README and experiment results
2020-05-27 22:39:21 +08:00
zkcys001
4f03f384d3
Upload Readme in cross-domain person re-ID
2020-05-27 22:35:17 +08:00
Xingyu Liao
66a24d2cbe
add HAA projects README
...
Reviewed by: l1aoxingyu
2020-05-27 22:32:20 +08:00
xbq1994
11f388781c
Create Readme.md
2020-05-27 22:27:33 +08:00
Xingyu Liao
41f7bb772a
update veri result
...
Reviewed By: l1aoxingyu
2020-05-27 13:22:06 +08:00
Jinkai Zheng
e0d29324db
Update VeRi's results
...
Update VeRi's results
2020-05-27 13:05:15 +08:00
liaoxingyu
a1cb123cfa
fix R101 bottleneck missing problem
...
Summary: add key 101 in block dict to support R101
2020-05-26 14:48:32 +08:00
liaoxingyu
d4b71de3aa
switch between soft and hard margin when inf
...
Summary: Add a mechnism to automatic switch triplet loss with soft margin to hard margin when loss becomes inf.
2020-05-26 14:36:33 +08:00
liaoxingyu
5982f90920
support loading various pretrained weights
...
Summary: Support loading pretrained model by custom path. With this function, we can load infoMin weights.
2020-05-26 14:33:18 +08:00
liaoxingyu
5d4758125d
support ResNet34 backbone
...
Summary: add BasicBlock to support ResNet34
2020-05-26 13:18:09 +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
Xingyu Liao
72cebec08f
Merge pull request #61 from JinkaiZheng/patch-3
...
add 10-fold cross-validation result in VehicleID
2020-05-25 16:44:47 +08:00
Jinkai Zheng
0f9e29224e
Change VehilcleID results
...
Replace VehicleID results with those under 10-fold cross-validation.
2020-05-25 16:36:08 +08:00
liaoxingyu
8458bece5e
Merge branch 'master' of github.com:L1aoXingyu/fast-reid
2020-05-23 10:42:31 +08:00
liaoxingyu
1eea244afb
chore(model_zoo): update mgn metrics
2020-05-23 10:42:24 +08:00
liaoxingyu
94c86579a3
fix(heads): fix bug in reduce head
...
add neck_feat from config, add inplace in leakyrelu for memory save
2020-05-23 10:41:13 +08:00
Xingyu Liao
e7b2675606
Merge pull request #60 from JinkaiZheng/update VehicleID's results
2020-05-22 13:49:35 +08:00
Jinkai Zheng
b6547635a9
Fix VehicleID's results and update VeRi's results
...
Fix VehicleID's results and update VeRi's results
2020-05-22 13:43:34 +08:00
liaoxingyu
c21de64166
fix: add linear initial method
2020-05-21 23:59:51 +08:00
liaoxingyu
95e8a02b2a
feat: partial reid first commit
2020-05-21 23:58:35 +08:00
liaoxingyu
e990cf3e34
style: fix some typro
2020-05-21 15:55:51 +08:00
liaoxingyu
2ac55a7601
feat: update roc curve and TPR@FPR metric
...
support plot multiple ROC curves with different model
2020-05-20 14:29:33 +08:00
liaoxingyu
e344eae1cc
feat: support plotting roc curve and compute auc score
...
ROC curve and AUC score will be help for thresholds
2020-05-19 20:45:26 +08:00
liaoxingyu
e20eb0394b
fix: modify open_layers in BoT config file
...
modify open_layers to list type to be compatible with default config
2020-05-19 14:46:35 +08:00
liaoxingyu
9e40194669
fix: change config of sbs
...
change weight decay and bias_lr in config of SBS, which can boost performance slightly.
2020-05-18 20:16:38 +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
liaoxingyu
579a5cf552
fix: modify re-rank typro
2020-05-18 17:05:20 +08:00
liaoxingyu
d63bf5facc
fix: add syncBN options in defaultTraine
2020-05-16 22:44:53 +08:00
liaoxingyu
b28c0032e8
fix: add monkey-patching to enable syncBN
...
add a trigger to make syncBN work
2020-05-15 13:33:33 +08:00
liaoxingyu
18a33f7962
feat: add MGN model
...
support MGN architecture and training config
2020-05-15 11:39:54 +08:00
liaoxingyu
3041a52aef
fix: revise config file in stronger baseline
2020-05-14 14:55:30 +08:00
liaoxingyu
bf18479541
fix: revise syncBN bug
2020-05-14 14:52:37 +08:00
liaoxingyu
0872a32621
feat: add syncBN support
2020-05-14 13:15:09 +08:00
liaoxingyu
cd7a4e9be7
add projects folder
2020-05-14 12:52:50 +08:00
liaoxingyu
0356ef8c5c
feat: add SyncBN and GroupNorm suppor
2020-05-14 11:36:28 +08:00
liaoxingyu
5ae3d4fecf
feat: add aqe support in test phase
...
query expansion will combine the retrived topk nearest neighbors with the original query feature,
it will enhance mAP by a large margin.feat:
2020-05-13 16:27:22 +08:00
liaoxingyu
320010f2ae
feat: support re-rank in test phase
2020-05-13 11:47:52 +08:00
liaoxingyu
e502fadba9
docs: update README
2020-05-12 23:00:15 +08:00
Xingyu Liao
01d940bfdd
update vehicle dataset
...
Summary: Pull Request resolved : #49
Reviewed By: xingyu liao
2020-05-12 21:44:05 +08:00
liaoxingyu
9addfb0ae2
feat: support visualizing label list
...
add features to support label list visualization, which can be used
for label correction or check the hardest sample
2020-05-12 21:35:33 +08:00
