Web端算法部署+流媒体服务器算法部署+Flask+AI健身+Python-web实时检测效果显示

仰卧起坐 ：选取的是12，24，26，最大角度改为30-130即可。

    angle = detector.findAngle(frame, 12, 24, 26)                    
    per = np.interp(angle, (30, 130), (0, 100))
    bar = np.interp(angle, (30, 130), (100, 550))

其他动作同理。

注：左上角为fps，左下角为次数统计。

pip install mediapipe

如果文件不全，可下载 MediaPipe源码补缺。

下载MediaPipe源码：

git clone https://github.com/google/mediapipe.git

也可通过pycharm安装：

pip install flask

ycc@ycc:~/pose/mediapipe/Live-Flask/Flask-AI健身$ python app.py 
 * Serving Flask app 'app' (lazy loading)
 * Environment: production
   WARNING: This is a development server. Do not use it in a production deployment.
   Use a production WSGI server instead.
 * Debug mode: on
 * Running on http://127.0.0.1:5000 (Press CTRL+C to quit)
 * Restarting with stat
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
 * Debugger is active!
 * Debugger PIN: 118-153-595

python flask实时播放算法处理后的实时视频流。