AITTSMD/MTCNN-Tensorflow

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1502 stars · 703 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A TensorFlow reproduction of MTCNN (Multi-task Cascaded Convolutional Networks) for joint face detection and facial landmark alignment. It includes the full training pipeline for the three-stage PNet, RNet, and ONet networks using WIDER Face and landmark datasets.

Use cases

• detect faces in images with a cascaded CNN
• reproduce MTCNN training from the original paper
• train a face detection model on WIDER Face
• detect facial landmarks with TensorFlow
• generate hard examples for multi-stage face detector training
• run face detection and alignment in one pipeline

When to choose

• you need to train or fine-tune MTCNN yourself rather than just run inference
• you want a faithful TensorFlow 1.x implementation of the MTCNN paper
• you need both face detection and landmark alignment from one model
• you are researching cascaded multi-task detection networks

When to avoid

• you only need pretrained face detection inference with a modern maintained library
• your project uses TensorFlow 2.x or PyTorch
• you cannot provide CUDA GPUs for training
• you need production support or an active maintenance schedule

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning image-processing python mtcnn face-detection facial-landmarks tensorflow cascaded-networks wider-face celeba linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="AITTSMD/MTCNN-Tensorflow")