sirius-ai/MobileFaceNet_TF
A TensorFlow implementation of MobileFaceNet, an efficient CNN optimized for accurate real-time face verification on mobile devices.
Not currently ranked — collecting fresh signals.
star history
This repository provides a TensorFlow implementation of MobileFaceNet, a compact convolutional neural network designed for efficient face recognition on mobile devices. The model is trained using large-margin cosine loss and achieves 99.4%+ accuracy on the LFW benchmark. It supports training on standard face datasets including MS1M and VGGFace2, and includes pre-trained model checkpoints for inference.
Frequently asked
- What is sirius-ai/MobileFaceNet_TF?
- A TensorFlow implementation of MobileFaceNet, an efficient CNN optimized for accurate real-time face verification on mobile devices.
- Is MobileFaceNet_TF open source?
- Yes — sirius-ai/MobileFaceNet_TF is open source, released under the Apache-2.0 license.
- What language is MobileFaceNet_TF written in?
- sirius-ai/MobileFaceNet_TF is primarily written in Python.
- How popular is MobileFaceNet_TF?
- sirius-ai/MobileFaceNet_TF has 481 stars on GitHub.
- Where can I find MobileFaceNet_TF?
- sirius-ai/MobileFaceNet_TF is on GitHub at https://github.com/sirius-ai/MobileFaceNet_TF.