DREAM block for Pose-Robust Face Recognition

This is the implementation of our CVPR 2018 accepted paper Pose-Robust Face Recognition via Deep Residual Equivariant Mapping paper on arxiv.

The code is written by Yu Rong and Kaidi Cao

Prerequisites

• Linux or macOS
• Python 3 or Python 2 (Python 3 is prefered)
• NVIDIA GPU + CUDA CuDNN or CPU (GPU is prefered)

Getting Started

Installation

• Install Anaconda
  • Anaconda3-4.2.0 for Python 3
  • Anaconda2-4.2.0 for Python 2
• Install Pytorch and torchvision through Anaconda (Please follow the guide in Pytorch)
• Clone this repo

git clone [email protected]:penincillin/DREAM.git
cd DREAM

Run the Code and Model

Code and models are coming soon.