GaitSet is a flexible, effective and fast network for cross-view gait recognition. The paper has been published on IEEE TPAMI.
The input of GaitSet is a set of silhouettes.
There are NOT ANY constrains on an input, which means it can contain any number of non-consecutive silhouettes filmed under different viewpoints with different walking conditions.
As the input is a set, the permutation of the elements in the input will NOT change the output at all.
It achieves Rank@1=95.0% on CASIA-B and Rank@1=87.1% on OU-MVLP, excluding identical-view cases.
With 8 NVIDIA 1080TI GPUs, it only takes 7 minutes to conduct an evaluation on OU-MVLP which contains 133,780 sequences and average 70 frames per sequence.
The code and checkpoint for OUMVLP dataset have been released. See OUMVLP for details.
Noted that our code is tested based on PyTorch 0.4
Download CASIA-B Dataset
!!! ATTENTION !!! ATTENTION !!! ATTENTION !!!
Before training or test, please make sure you have prepared the dataset by this two steps:
your_dataset_path/subject_ids/walking_conditions/views
.
E.g. CASIA-B/001/nm-01/000/
.pretreatment.py
.
(See pretreatment for details.)
Welcome to try different ways of pretreatment but note that
the silhouettes after pretreatment MUST have a size of 64x64.Futhermore, you also can test our code on OU-MVLP Dataset. The number of channels and the training batchsize is slightly different for this dataset. For more detail, please refer to our paper.
pretreatment.py
uses the alignment method in
this paper.
Pretreatment your dataset by
python pretreatment.py --input_path='root_path_of_raw_dataset' --output_path='root_path_for_output'
--input_path
(NECESSARY) Root path of raw dataset.--output_path
(NECESSARY) Root path for output.--log_file
Log file path. #Default: './pretreatment.log'--log
If set as True, all logs will be saved.
Otherwise, only warnings and errors will be saved. #Default: False--worker_num
How many subprocesses to use for data pretreatment. Default: 1In config.py
, you might want to change the following settings:
dataset_path
(NECESSARY) root path of the dataset
(for the above example, it is "gaitdata")WORK_PATH
path to save/load checkpointsCUDA_VISIBLE_DEVICES
indices of GPUsTrain a model by
python train.py
--cache
if set as TRUE all the training data will be loaded at once before the training start.
This will accelerate the training.
Note that if this arg is set as FALSE, samples will NOT be kept in the memory
even they have been used in the former iterations. #Default: TRUEEvaluate the trained model by
python test.py
--iter
iteration of the checkpoint to load. #Default: 80000--batch_size
batch size of the parallel test. #Default: 1--cache
if set as TRUE all the test data will be loaded at once before the transforming start.
This might accelerate the testing. #Default: FALSEIt will output Rank@1 of all three walking conditions.
Note that the test is parallelizable.
To conduct a faster evaluation, you could use --batch_size
to change the batch size for test.
Since the huge differences between OUMVLP and CASIA-B, the network setting on OUMVLP is slightly different.
./work/OUMVLP_network
. Use them to replace the corresponding files in ./model/network
../config.py
, modify 'batch_size': (8, 16)
into 'batch_size': (32,16)
.GaitSet is authored by Hanqing Chao, Yiwei He, Junping Zhang and JianFeng Feng from Fudan Universiy. Junping Zhang is the corresponding author. The code is developed by Hanqing Chao and Yiwei He. Currently, it is being maintained by Hanqing Chao and Kun Wang.
Please cite these papers in your publications if it helps your research:
@ARTICLE{chao2019gaitset,
author={Chao, Hanqing and Wang, Kun and He, Yiwei and Zhang, Junping and Feng, Jianfeng},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set},
year={2021},
pages={1-1},
doi={10.1109/TPAMI.2021.3057879}}
Link to paper:
GaitSet is freely available for free non-commercial use, and may be redistributed under these conditions. For commercial queries, contact Junping Zhang.