happynear/AMSoftmax
A simple yet effective loss function for face verification.
This project provides an improved method for training face recognition systems to more accurately identify individuals. It takes raw facial images and outputs a more refined set of face recognition models, enhancing the ability to distinguish between similar faces. It would be used by researchers and engineers developing high-precision face verification systems for security, access control, or identity management.
491 stars. No commits in the last 6 months.
Use this if you are building or improving a face verification system and need to maximize accuracy, especially when differentiating between many similar faces.
Not ideal if you are looking for a complete, out-of-the-box face recognition application rather than a core component for training one.
Stars
491
Forks
126
Language
Matlab
License
MIT
Category
Last pushed
Aug 03, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/happynear/AMSoftmax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
open-mmlab/mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
Xilinx/brevitas
Brevitas: neural network quantization in PyTorch
fastmachinelearning/qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
google/qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
tensorflow/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization...