Resource Aware Person Re-identification across Multiple Resolutions
This repository contains the code for paper "Resource Aware Person Re-identification across Multiple Resolutions" (CVPR 2018).
Citation
@inproceedings{wang2018resource,
title={Resource Aware Person Re-identification across Multiple Resolutions},
author={Wang, Yan and Wang, Lequn and You, Yurong and Zou, Xu and Chen, Vincent and Li, Serena and Huang, Gao and Hariharan, Bharath and Weinberger, Kilian Q},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={8042--8051},
year={2018}
}
Usage
Dependencies
Usage
Training Dataset Preprocessing
Use the following command to preprocess the person re-id dataset.
python create_market_dataset.py --path <root_path_of_dataset>Train
Use the following command to set up the training.
./train.sh <nettype> <GPU> <train_dataset_path> <checkpoint_name>where <nettype> can be either dare_R or dare_D
Extract Features
Use the following command to load a trained model to generate features for each image (in .mat format).
./extract_features.sh <nettype> <GPU> <dataset_path> <dataset> <checkpoint_name> <feature_path> <gen_stage_features>where <nettype> can be either dare_R or dare_D, <dataset> can be one of [MARS, Market1501, Duke, CUHK03], <feature_path> is the path to store extracted features. Toggle <gen_stage_features> to Ture to extract features from each stage.
Evaluation
Use person-re-ranking and MARS-evaluation official evaluation codes to evaluate the extracted features.
Note we use mean rather than max to aggregate the image feature vectors for video sequences.
Resource-aware Person Re-ID Simulation
Use the following command to run simulations under resource-aware person re-ID scenarios. See here for more information.
./budgeted_stream/simulation.sh <dataset_path> <feature_path>Pretrained Model
We provide several pretrained models listed below:
- Market1501 Res50
- Market1501 Dense201
- MARS Res50
- MARS Dense201
- CUHK Detected Res50
- CUHK Detected Dense201
- CUHK Labeled Res50
- CUHK Labeled Dense201
- Duke Res50
- Duke Dense201
The downloading of pretrained models has been automated with
python download_checkpoints.py --dir checkpointsLicense
MIT