85672b1e75
add circle & arcface layer info
...
Summary: show num_features and num_classes in circle & arcface layer, like nn.Linear
2020-05-31 15:50:56 +08:00
e2761f7581
fix style in comm dataset
2020-05-30 16:56:08 +08:00
c036ac5bdd
update reduction head
2020-05-30 16:50:02 +08:00
36c04f0a9f
fix resume training problem
...
Summary: when resume training, need to reiter dataloader because we update pid_dict in dataset, but dataloader with multiprocess won't do the same update
2020-05-30 16:44:18 +08:00
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
cd69ba6ffb
update augmix augments
...
Summary: replace augmix augmentations for adapting reid
2020-05-27 22:56:31 +08:00
a1cb123cfa
fix R101 bottleneck missing problem
...
Summary: add key 101 in block dict to support R101
2020-05-26 14:48:32 +08:00
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
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
5d4758125d
support ResNet34 backbone
...
Summary: add BasicBlock to support ResNet34
2020-05-26 13:18:09 +08:00
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
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
c21de64166
fix: add linear initial method
2020-05-21 23:59:51 +08:00
e990cf3e34
style: fix some typro
2020-05-21 15:55:51 +08:00
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
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
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
579a5cf552
fix: modify re-rank typro
2020-05-18 17:05:20 +08:00
d63bf5facc
fix: add syncBN options in defaultTraine
2020-05-16 22:44:53 +08:00
b28c0032e8
fix: add monkey-patching to enable syncBN
...
add a trigger to make syncBN work
2020-05-15 13:33:33 +08:00
18a33f7962
feat: add MGN model
...
support MGN architecture and training config
2020-05-15 11:39:54 +08:00
bf18479541
fix: revise syncBN bug
2020-05-14 14:52:37 +08:00
0872a32621
feat: add syncBN support
2020-05-14 13:15:09 +08:00
0356ef8c5c
feat: add SyncBN and GroupNorm suppor
2020-05-14 11:36:28 +08:00
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
320010f2ae
feat: support re-rank in test phase
2020-05-13 11:47:52 +08:00
01d940bfdd
update vehicle dataset
...
Summary: Pull Request resolved : #49
Reviewed By: xingyu liao
2020-05-12 21:44:05 +08:00
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
640c9bfc97
Add small, medium and large vehicle test datasets
2020-05-11 01:34:19 -05:00
e059b751a6
Add modified vehicle datasets with small, medium and large test datastes
2020-05-11 01:30:56 -05:00
9b6fda3830
style: remove title in visualization
2020-05-11 14:12:29 +08:00
13bb03eb07
feat: add rank result visualization tools
...
Update visualization tools which can save rank list with AP metrics from high to low, vice versa.
In order to compute AP fast in visualizer, modify rank_cylib to get all_AP instead of mAP.
In this way, we can use Cython to compute results.
2020-05-10 23:17:10 +08:00
651e6ba9c4
feat: support multiprocess predictor
...
add asyncpredictor to support multiprocessing feature extraction with dataloader
2020-05-09 18:23:36 +08:00
4be4cacb73
fix: add a simple way to reset data prefetcher when resume training
...
use data prefetcher build-in reset function to reload it rather than
redefining a new data prefetcher, otherwise it will introduce other
problems in eval-only mode.
2020-05-09 11:58:27 +08:00
9fae467adf
feat(engine/defaults): add DefaultPredictor to get image reid features
...
Add a new predictor interface, and modify demo code to predict image features.
2020-05-08 19:24:27 +08:00
8ab0bc2455
style(backbone): make parameters loading logging more elegant
2020-05-08 12:22:06 +08:00
0b15ac4e03
feat(hooks&optim): update stochastic weight averging hooks
...
Update swa method which will do after regular training if you
set this option enabled.
2020-05-08 12:20:04 +08:00
afac8aad5d
Fix(engine): fix preciseBN dataloader bugs
...
preciseBN needs to pass data prefetcher, but now a DataLoader is passed
2020-05-06 14:26:34 +08:00
948af64fd1
feat: add swa algorithm
...
Add swa and related config options,
if it is enabled, model will do swa after regular training
2020-05-06 10:17:44 +08:00
6d96529d4c
fix(data): fix resume training bug
...
fix dataset pid dictionary loading bug when resume training,
data prefetcher will pre-load a batch of data, this will lead to
misalignment of old pid dict and updated pid dict.
We can address this problem by redefine a prefetcher in resume_or_load
2020-05-05 23:20:42 +08:00
a2dcd7b4ab
feat(layers/norm): add ghost batchnorm
...
add a get_norm fucntion to easily change normalization between batchnorm, ghost bn and group bn
2020-05-01 09:02:46 +08:00
329764bb60
refactor(heads): move num_classes out from heads
...
set parameter num_classes in meta_arch to easily modify different heads fc layer
2020-04-29 21:29:48 +08:00
d27729c5bb
refactor(preciseBN): add preciseBN datasets show
2020-04-29 21:05:53 +08:00
ec19bcc1d3
style(configs): put all config files together
...
put all config files into one place for easily control,
and add tools for put train_net.py which almost the same in
different projects
2020-04-29 16:18:54 +08:00
e38a799b63
fix(engine/defaults): fix precise bn bug
...
fix problem in precise bn, which will not use precise bn datasets, and throw some errors
2020-04-29 16:16:54 +08:00
2f3f6e3267
Add files via upload
2020-04-27 16:27:44 +08:00
5daf322ac6
fix(data/samplers): fix bug in triplet sampler
...
use drop indices to avoid two groups of same id,
but did not consider drop indices = 0, then will lead to
indentites[:0], this is a no teminal loop
2020-04-27 15:25:29 +08:00
325d9abb76
feat($solver): change scheduler call methods
...
using name of lr scheduler in config to call
2020-04-27 15:12:01 +08:00
9e3f2c1e7a
fix($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
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
Jinkai Zheng
zjk15068083791