AITTSMD/MTCNN-Tensorflow
A TensorFlow implementation of MTCNN for joint face detection and facial landmark alignment.
Not currently ranked — collecting fresh signals.
star history
This repository reproduces the Multi-task Cascaded Convolutional Networks (MTCNN) paper using TensorFlow. It implements a three-stage cascade of neural networks (PNet, RNet, ONet) for robust face detection and simultaneous facial landmark localization. The project includes training pipelines with data preparation scripts, hard example mining, and support for landmark detection on datasets like WIDER Face and CelebA.
Frequently asked
- What is AITTSMD/MTCNN-Tensorflow?
- A TensorFlow implementation of MTCNN for joint face detection and facial landmark alignment.
- Is MTCNN-Tensorflow open source?
- Yes — AITTSMD/MTCNN-Tensorflow is an open-source project tracked on heatdrop.
- What language is MTCNN-Tensorflow written in?
- AITTSMD/MTCNN-Tensorflow is primarily written in Python.
- How popular is MTCNN-Tensorflow?
- AITTSMD/MTCNN-Tensorflow has 1.5k stars on GitHub.
- Where can I find MTCNN-Tensorflow?
- AITTSMD/MTCNN-Tensorflow is on GitHub at https://github.com/AITTSMD/MTCNN-Tensorflow.