caogule/domain-transfer-network

TensorFlow Implementation of "Unsupervised Cross-Domain Image Generation"

Domain Transfer Network (DTN)

TensorFlow implementation of Unsupervised Cross-Domain Image Generation.

Requirements

• Python 2.7
• TensorFlow 0.12
• Pickle
• SciPy

Usage

Clone the repository

$ git clone https://github.com/yunjey/dtn-tensorflow.git
$ cd dtn-tensorflow

Download the dataset

$ chmod +x download.sh
$ ./download.sh

Resize MNIST dataset to 32x32

$ python prepro.py

Pretrain the model f

$ python main.py --mode='pretrain'

Train the model G and D

$ python main.py --mode='train'

Transfer SVHN to MNIST

$ python main.py --mode='eval'

Results

From SVHN to MNIST

From Photos to Emoji (in paper)