liaoxingyu
9e3f2c1e7a
fix($data/transforms): change augmix augmentation pool
...
change augmentation_all from augmentation_reid in augmix
because we found AutoAugmentation using ImageNet Policy will not harm performance
2020-04-27 15:06:27 +08:00
liaoxingyu
4d3e5fd378
refactor(evaluation): add feature l2 norm in evaluation
...
change the l2 norm function from inference function in Module to reid evaluation.
because sometimes we need to use the original features generated by model rather than normalized ones.
2020-04-27 14:51:39 +08:00
liaoxingyu
9910bb9158
fix($modeling/heads): fix targets missing bug
...
fix bug in heads about return outputs without targets.
2020-04-27 14:49:58 +08:00
liaoxingyu
2efbc6d371
fix($modeling/heads/bnneck_head): fix heads outputs bug
...
fix bug of heads outputs, which will lead to no targets return.
2020-04-27 11:48:21 +08:00
liaoxingyu
a6bd0371e2
feat($data): add autoaugment
...
add auto augmentation support with ImageNet policy and CIFAR10 policy.
modify codes in transforms and config for adapting to this augmentation.
2020-04-27 11:41:12 +08:00
liaoxingyu
8abd3bab03
feat($layers): add new act func
...
add mish, gelu supported
2020-04-24 12:17:00 +08:00
liaoxingyu
3984f0c91d
refactor($modeling/meta): refactor heads output
...
without intermediate variables generated by reid heads, make it more flexible
2020-04-24 12:16:18 +08:00
liaoxingyu
e3ae03cc58
feat($modeling/backbones): add new backbones
...
add osnet, resnext and resnest backbone supported
2020-04-24 12:14:56 +08:00
liaoxingyu
b098b194ba
refactor($modeling/meta_arch): remove bdb_network
2020-04-21 11:44:29 +08:00
liaoxingyu
6c9af664dc
refactor($modeling/meta_arch): remove useless parts
...
remove useless meta_archs and backbones
2020-04-21 11:42:14 +08:00
liaoxingyu
bb50b6c5a7
docs($projects): update agw readme
2020-04-21 11:35:54 +08:00
liaoxingyu
95a3c62ad2
refactor(fastreid)
...
refactor architecture
2020-04-20 10:59:29 +08:00
liaoxingyu
9684500a57
chagne arch
...
1. change dataset show to trainset show and testset show seperately
2. add cls layer to easily plug in circle loss and arcface
2020-04-19 12:54:01 +08:00
liaoxingyu
be9faa5605
update focal loss
...
update dataset info display
update seperate lr
update adaptive label smooth regularization
2020-04-17 13:46:10 +08:00
liaoxingyu
9cf222e093
refactor bn_no_bias
2020-04-08 21:04:09 +08:00
liaoxingyu
4d2fa28dbb
update freeze layer
...
update preciseBN
update circle loss with metric learning and cross entropy loss form
update loss call methods
2020-04-06 23:34:27 +08:00
liaoxingyu
6a8961ce48
1. upload circle loss and arcface
...
2. finish freeze training
3. update augmix data augmentation
2020-04-05 23:54:26 +08:00
liaoxingyu
c6e0176c53
Upload demo.py and example
2020-04-03 15:07:27 +08:00
liaoxingyu
eacee874aa
fix merge
2020-03-25 11:06:39 +08:00
liaoxingyu
91dc9bc71f
Merge branch 'master' of github.com:L1aoXingyu/fast-reid
...
Conflicts:
fastreid/config/defaults.py
fastreid/layers/gem_pool.py
fastreid/modeling/backbones/resnet.py
fastreid/modeling/heads/__init__.py
fastreid/modeling/heads/build.py
fastreid/modeling/losses/build.py
fastreid/modeling/meta_arch/__init__.py
fastreid/modeling/meta_arch/abd_network.py
fastreid/modeling/meta_arch/baseline.py
fastreid/modeling/meta_arch/bdb_network.py
fastreid/modeling/meta_arch/mf_network.py
projects/StrongBaseline/configs/Base-Strongbaseline.yml
projects/StrongBaseline/configs/baseline_dukemtmc.yml
projects/StrongBaseline/train_net.py
2020-03-25 11:05:28 +08:00
liaoxingyu
23bedfce12
update version0.2 code
2020-03-25 10:58:26 +08:00
L1aoXingyu
b1058118ca
update BDB-net code
...
update MF-net code
2020-03-19 12:23:41 +08:00
L1aoXingyu
acf363c181
1. Change loss function as a build-in attributes of heads
...
2. Update agw and bagtricks result
2020-03-16 15:23:09 +08:00
L1aoXingyu
bab602dfd2
Fix minor bug in build criterion, it will replace by multiple call
...
Refactor resnet pretrain
2020-02-28 21:20:41 +08:00
L1aoXingyu
b020c7f0ae
Fix data prefetcher minor bug
2020-02-27 12:16:57 +08:00
L1aoXingyu
12957f66aa
Change architecture:
...
1. delete redundant preprocess
2. add data prefetcher to accelerate data loading
3. fix minor bug of triplet sampler when only one image for one id
2020-02-18 21:01:23 +08:00
L1aoXingyu
e01d9b241f
Update AGW baseline result
2020-02-13 20:37:08 +08:00
L1aoXingyu
327d74ffbb
Update strong baseline result
...
Change data sampler
2020-02-13 00:19:15 +08:00
L1aoXingyu
a2f69d0537
Update StrongBaseline results for market1501 and dukemtmc
2020-02-11 22:38:40 +08:00
L1aoXingyu
8a9c0ccfad
Finish first version for fastreid
2020-02-10 22:13:04 +08:00
L1aoXingyu
db6ed12b14
Update sampler code
2020-02-10 07:38:56 +08:00
liaoxingyu
71950d2c09
1. Fix evaluation code
...
2. Finish multi-dataset evaluation
3. Decouple image preprocess and output postprocess with model forward for DataParallel training
4. Finish build backbone registry
5. Fix dataset sampler
2020-01-21 20:24:26 +08:00
liaoxingyu
b761b656f3
Finish basic training loop and evaluation results
2020-01-20 21:33:37 +08:00
