lanmengyiyu/yolov5-deepmar

本项目是行人轨迹和属性分析的解决方案，检测采用的是yolov5, 跟踪采用的是deepsort，属性分析采用的是deepmar,效果demo

Requirements

Python 3.7 or later with all requirements.txt dependencies installed, including torch >= 1.5. To install run:

$ pip install -U -r requirements.txt

weights

Google drive link:

https://drive.google.com/drive/folders/11qr6Y2c62NzM3BN_011oXLHietiw5tbi?usp=sharing https://drive.google.com/drive/folders/1r08uwmB3QeOnwkhOupZ0UCC1TIaGybOK?usp=sharing https://drive.google.com/drive/folders/1KRoWa-VJwgOxWXgywuzwFaq95wDd0QnJ?usp=sharing

Tutorials

• yolov5-deepmar-Notebook

Inference

Inference can be run on most common media formats. Results are saved to ./inference/output.To run inference on examples in the ./inference/images folder

python detect.py --weights "/content/drive/My Drive/yolo weight/yolov5x.pt" 
                 --img 416 
                 --conf 0.4 
                 --source ./inference/images/ 
                 --deepsort ./config/deep_sort.yaml

Contact

Issues should be raised directly in the repository. email Zhang Jie at 545277714@qq.com.