YOLOv3,DeepSort and Flask Run On The Web Page
Computer terminal
Mobile terminal
Introduction
Combined with yolov3, deep sort and flask, it is a target detection and multi-target tracking platform that can run on Web pages. You can upload pictures or videos. When the image is uploaded, target detection is carried out. When the video is uploaded, multi-target tracking is carried out (the default is pedestrian, which can be changed to other objects). The mobile terminal provides an online shooting interface for real-time target detection and multi-target tracking.
Dependencies
- torch
- torchvision
- numpy
- opencv-python==4.1.2.30
- lxml
- tqdm
- flask
- seaborn
- pillow
- vizer
- numba
Quick Start
1. Check all dependencies installed
pip install -r requirements.txt
2. Download YOLOv3 parameters
cd deepsort/detector/YOLOv3/weight/
wget https://pjreddie.com/media/files/yolov3.weights
cd ../../../
3. Download deepsort parameters ckpt.t7
cd deep_sort/deep/checkpoint
# download ckpt.t7 from
https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6 to this folder
cd ../../../
4. Or download the weight file through baidu network disk
yolov3.weight put in deepsort/detector/YOLOv3/weight/
ckpt.t7 put in deep_sort/deep/checkpoint
5. Compile nms module
cd detector/YOLOv3/nms
sh build.sh
cd ../../../
or
cd detector/YOLOv3/nms/ext
python build.py build_ext develop
cd ../../../../
6. Run
python app.py
阿里云ECS部署python,flask项目,简单易懂,无需nginx和uwsgi
7. If you want to configure to run on the server, please visit my blog8. You can use yolov3 demo
python detector.py
References
- code: ZQPei/deep_sort_pytorch