timesler/facenet-pytorch

Health v2 · maintenance only

Adoption not part of the score

5162 stars · 1000 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A PyTorch library providing pretrained face detection (MTCNN) and facial recognition (Inception ResNet V1) models, ported from the TensorFlow facenet project. It includes one of the fastest MTCNN implementations available and supports complete detection-to-embedding pipelines.

Use cases

• detect and crop faces from images
• generate face embeddings for identity matching
• build a face login or verification system
• track faces across video frames
• cluster photos by person
• finetune face recognition models on new data

When to choose

• you need pretrained face detection and recognition in PyTorch
• you want a fast, pure-PyTorch MTCNN implementation
• you need face embeddings compatible with VGGFace2/CASIA-Webface models
• you want a simple pip-installable pipeline from image to embedding

When to avoid

• you need state-of-the-art accuracy on hard faces (consider newer detectors like RetinaFace or ArcFace models)
• you work outside PyTorch (e.g., TensorFlow or ONNX-only pipelines)
• you need non-face object detection or general image recognition
• you require active large-scale development - the project is mature and changes infrequently

Facets

library · maturity stable

machine-learning computer-vision image-processing deep-learning computer-vision machine-learning image-processing artificial-intelligence python cross-platform face-recognition face-detection mtcnn inception-resnet pretrained-models pytorch facial-embeddings vggface2 gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="timesler/facenet-pytorch")