Note:
This code is only used for academic purposes, people cannot use this code for anything that might be considered commercial use.

OpenGait

OpenGait is a flexible and extensible gait recognition project provided by the Shiqi Yu Group and supported in part by WATRIX.AI. Just the pre-beta version is released now, and more documentations as well as the reproduced methods will be offered as soon as possible.

Highlighted features:

Multiple Models Support: We reproduced several SOTA methods, and reached the same or even better performance.
DDP Support: The officially recommended Distributed Data Parallel (DDP) mode is used during the training and testing phases.
AMP Support: The Auto Mixed Precision (AMP) option is available.
Nice log: We use tensorboard and logging to log everything, which looks pretty.

Model Zoo

Model	NM	BG	CL	Configuration	Input Size	Inference Time	Model Size
Baseline	96.3	92.2	77.6	baseline.yaml	64×44	12s	3.78M
GaitSet(AAAI2019)	95.8(95.0)	90.0(87.2)	75.4(70.4)	gaitset.yaml	64×44	11s	2.59M
GaitPart(CVPR2020)	96.1(96.2)	90.7(91.5)	78.7(78.7)	gaitpart.yaml	64×44	22s	1.20M
GLN*(ECCV2020)	96.1(95.6)	92.5(92.0)	80.4(77.2)	gln_phase1.yaml, gln_phase2.yaml	128×88	14s	9.46M / 15.6214M
GaitGL(ICCV2021)	97.5(97.4)	95.1(94.5)	83.5(83.6)	gaitgl.yaml	64×44	31s	3.10M

The results in the parentheses are mentioned in the papers

Note:

All the models were tested on CASIA-B (Rank@1, excluding identical-view cases).
The shown result of GLN is implemented without compact block.
Only 2 RTX6000 are used during the inference phase.
The results on OUMVLP will be released soon.
It’s inference process just cost about 90 secs(Baseline & 8 RTX6000).

Get Started

Installation

clone this repo.

git clone https://github.com/ShiqiYu/OpenGait.git

Install dependenices:

pytorch >= 1.6
torchvision
pyyaml
tensorboard
opencv-python
tqdm

Install dependenices by Anaconda:

conda install tqdm pyyaml tensorboard opencv
conda install pytorch==1.6.0 torchvision -c pytorch

Or, Install dependenices by pip:

pip install tqdm pyyaml tensorboard opencv-python
pip install torch==1.6.0 torchvision==0.7.0

Prepare dataset

See prepare dataset.

Train

Train a model by

CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 lib/main.py --cfgs ./config/baseline.yaml --phase train

python -m torch.distributed.launch Our implementation uses DistributedDataParallel.
--nproc_per_node The number of gpu to use, it must equal the length of CUDA_VISIBLE_DEVICES.
--cfgs The path of config file.
--phase Specified as train.
--iter You can specify a number of iterations or use restore_hint in the configuration file and resume training from there.
--log_to_file If specified, log will be written on disk simultaneously.

You can run commands in train.sh for training different models.

Test

Use trained model to evaluate by

CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 lib/main.py --cfgs ./config/baseline.yaml --phase test

--phase Specified as test.
--iter You can specify a number of iterations or or use restore_hint in the configuration file and restore model from there.

Tip: Other arguments are the same as train phase.

You can run commands in test.sh for testing different models.

Customize

If you want customize your own model, see here.

Warning

Some models may not be compatible with AMP, you can disable it by setting enable_float16 False.
In DDP mode, zombie processes may occur when the program terminates abnormally. You can use this command kill $(ps aux | grep main.py | grep -v grep | awk '{print $2}') to clear them.
We implemented the functionality of testing while training, but it slightly affected the results. None of our published models use this functionality. You can disable it by setting with_test False.