SoutaTakanashi / face-inpainting

Inpainting of portraits using neural networks

Allows CNN inpainting in portraits of people, i.e. filling in face features painted over with green color. Using a TensorFlow implementation of Image-to-Image Translation Using Conditional Adversarial Networks that learns a mapping from input images to output images.

Setup

Prerequisites

• Linux
• Python with numpy
• NVIDIA GPU + CUDA 8.0 + CuDNNv5.1
• TensorFlow 0.11

Getting Started

• Clone this repo:

git clone [e-mail]:petee_d/face-inpainting.git
cd pix2pix-tensorflow

• Download the dataset:

bash ./download_dataset.sh

• Train the model

python main.py --phase train

• Test the model:

python main.py --phase test

Results

TODO

Acknowledgments

Code is an extension of pix2pix-tensorflow, which borrows heavily from pix2pix and DCGAN-tensorflow. Thanks for their excellent work!

License

MIT