auroua/InsightFace_TF
A TensorFlow-based face recognition system implementing InsightFace with various backbone networks and margin-based losses.
Not currently ranked — collecting fresh signals.
star history
This repository provides a TensorFlow implementation of InsightFace, a deep learning-based face recognition system. It supports multiple backbone architectures including VGG16, VGG19, ResNet, ResNet-SE, and ResNeXt, and implements face recognition losses such as Additive Angular Margin Loss and CosineFace Loss. The project includes training code with multi-GPU support, validation during training, and evaluation on standard face recognition benchmarks.
Frequently asked
- What is auroua/InsightFace_TF?
- A TensorFlow-based face recognition system implementing InsightFace with various backbone networks and margin-based losses.
- Is InsightFace_TF open source?
- Yes — auroua/InsightFace_TF is open source, released under the MIT license.
- What language is InsightFace_TF written in?
- auroua/InsightFace_TF is primarily written in Python.
- How popular is InsightFace_TF?
- auroua/InsightFace_TF has 700 stars on GitHub.
- Where can I find InsightFace_TF?
- auroua/InsightFace_TF is on GitHub at https://github.com/auroua/InsightFace_TF.