1adrianb/facealignment-torch repository overview

Ubuntu Core 14.04 + CUDA 7.5⁠ + cuDNN v5⁠ + Torch7⁠ (including iTorch)

⁠Requirements

• NVIDIA Docker⁠

⁠Usage

Use NVIDIA Docker: nvidia-docker run -it kaixhin/cuda-torch.

For more information regarding the method and the code see this⁠ For more information on CUDA on Docker, see this⁠

To use Jupyter/iTorch open up the appropriate port. For example, use nvidia-docker run -it -p 8888:8888 1adrianb/facealignment-torch. Then run jupyter notebook --ip="0.0.0.0" --no-browser to open a notebook on localhost:8888.

⁠Description

This repository implements a demo of the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.

Code available at: https://github.com/1adrianb/2D-and-3D-face-alignment⁠ Project page: https://www.adrianbulat.com/face-alignment⁠

⁠Acknowledgement

Docker image based on cuda-torch⁠ by @kaixhin