Skip to content

Interactive Notebooks

Run UniFace examples directly in your browser with Google Colab, or download and run locally with Jupyter.

Available Notebooks

Notebook Colab Kaggle Description
Face Detection Open In Colab Open in Kaggle Detect faces and 5-point landmarks
Face Alignment Open In Colab Open in Kaggle Align faces for recognition
Face Verification Open In Colab Open in Kaggle Compare faces for identity
Face Search Open In Colab Open in Kaggle Find a person in group photos
Face Analyzer Open In Colab Open in Kaggle Unified face analysis
Face Parsing Open In Colab Open in Kaggle Semantic face segmentation
Face Anonymization Open In Colab Open in Kaggle Privacy-preserving blur
Gaze Estimation Open In Colab Open in Kaggle Gaze direction estimation
Face Segmentation Open In Colab Open in Kaggle Face segmentation with XSeg
Face Vector Store Open In Colab Open in Kaggle FAISS-backed face database
Head Pose Estimation Open In Colab Open in Kaggle 3D head orientation estimation
Face Recognition Open In Colab Open in Kaggle Standalone face recognition pipeline
Portrait Matting Open In Colab Open in Kaggle Portrait matting with MODNet
Face Attributes Open In Colab Open in Kaggle Face states (eyes, glasses, sunglasses, mask)
Face Mesh Open In Colab Open in Kaggle 468 / 478-point dense 3D mesh

Running Locally

Download and run notebooks on your machine:

# Clone the repository
git clone https://github.com/yakhyo/uniface.git
cd uniface

# Install dependencies
pip install "uniface[cpu]" jupyter   # or uniface[gpu] for CUDA

# Launch Jupyter
jupyter notebook examples/

Running on Google Colab

Click any "Open in Colab" badge above. The notebooks automatically:

  1. Install UniFace via pip
  2. Clone the repository to access test images
  3. Set up the correct working directory

GPU Acceleration

In Colab, go to Runtime → Change runtime type → GPU for faster inference.

Next Steps