Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
deropty dc8dbdf73d | 2 years ago | |
---|---|---|
config | 2 years ago | |
configs | 2 years ago | |
datasets | 2 years ago | |
loss | 2 years ago | |
model | 2 years ago | |
processor | 2 years ago | |
solver | 2 years ago | |
thop | 2 years ago | |
utils | 2 years ago | |
LICENSE | 2 years ago | |
README.md | 2 years ago | |
train.py | 2 years ago | |
vis.py | 2 years ago |
Implementation of the proposed PiT. For the preprint version, please refer to [Arxiv].
Here is a brief instruction for installing the experimental environment.
# install virtual envs
$ conda create -n PiT python=3.6 -y
$ conda activate PiT
# install pytorch 1.8.1/1.6.0 (other versions may also work)
$ pip install timm scipy einops yacs opencv-python tensorboard pandas
The pre-trained vit model can be downloaded in this link and should be put in the /home/[USER]/.cache/torch/checkpoints/
directory.
For iLIDS-VID, please refer to this issue.
# This command below includes the training and testing processes.
$ python train.py --config_file configs/MARS/pit.yml MODEL.DEVICE_ID "('0')"
# For testing only, the parameter TEST.WEIGHT in yml file should be the directory of model weights. Otherwise, it should be None.
The results of MARS and iLIDS-VID are trained using one 24G NVIDIA GPU and provided below. You can change the parameter DATALOADER.P
in yml file to decrease the GPU memory cost.
Model | Rank-1@MARS | Rank-1@iLIDS-VID |
---|---|---|
PiT | 90.22 (code:wqxv) | 92.07 (code: quci) |
You can download these models and put them in the ../logs/[DATASET]_PiT_1x210_3x70_105x2_6p
directory. Then use the command below to evaluate them.
$ python test.py --config_file configs/MARS/pit.yml MODEL.DEVICE_ID "('0')"
This repository is built upon the repository TranReID.
If you find this project useful for your research, please kindly cite:
@ARTICLE{9714137,
author={Zang, Xianghao and Li, Ge and Gao, Wei},
journal={IEEE Transactions on Industrial Informatics},
title={Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval},
year={2022},
volume={},
number={},
pages={1-1},
doi={10.1109/TII.2022.3151766}
}
This repository is released under the GPL-2.0 License as found in the LICENSE file.
Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval.
Python
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》