yolov7-pose-estimation

New Features

• Added Comparison Graph for FPS & Time
• How to Run Code in Google Colab
• Supports CPU & GPU
• Video/WebCam/External Camera/IP Stream Support

Steps to Run Code

• Google Colab Users: First, mount the drive:

  from google.colab import drive
  drive.mount("/content/drive")

• Clone the repository:

  git clone https://github.com/RizwanMunawar/yolov7-pose-estimation.git

• Go to the cloned folder:

  cd yolov7-pose-estimation

• Create a virtual environment (recommended):

  # Linux
  python3 -m venv psestenv
  source psestenv/bin/activate
  
  # Windows
  python3 -m venv psestenv
  cd psestenv/Scripts
  activate

• Upgrade pip:

  pip install --upgrade pip

• Install requirements:

  pip install -r requirements.txt

• Download YOLOv7 weights and move to the working directory: yolov7-w6-pose.pt

• Run the code:

  python pose-estimate.py
  
  # Options:
  python pose-estimate.py --source "your-video.mp4" --device cpu  # For CPU
  python pose-estimate.py --source 0 --view-img  # For Webcam
  python pose-estimate.py --source "rtsp://your-ip" --device 0 --view-img  # For LiveStream

• Output: The processed video will be saved as your-file-keypoint.mp4

RESULTS

Football Match	Cricket Match	FPS & Time Comparison	Live Stream

References

• YOLOv7 Repo: https://github.com/WongKinYiu/yolov7
• Ultralytics: https://github.com/ultralytics/yolov5

📖 Articles

• YOLOv7 Training Guide
• Computer Vision Roadmap