#########################################################
This is repository contains the code for the paper:
Learning convolutional multi-level transformers for image-based person re-identification
(https://doi.org/10.1007/s44267-023-00025-8)
#########################################################
pip install -r requirements.txt(we use /torch 1.10.1 /torchvision 0.11.2 /timm 0.4.9 for training and evaluation.）
For using the codes, please download the public Market-1501 and Duke datasets.
Please download the ImageNet pretrained resnet50 model.
Run the train.py and test.py with your GPUs. You can get the same results in the above paper.
if you use this code for your research, please cite our paper:
Yan, P., Liu, X., Zhang, P. et al. Learning convolutional multi-level transformers for image-based person re-identification. Vis. Intell. 1, 24 (2023). https://doi.org/10.1007/s44267-023-00025-8
If you have any problems. Please concat