woozzu / dong_iccv_2017

A PyTorch implementation of the paper "Semantic Image Synthesis via Adversarial Learning" in ICCV 2017
MIT License
145 stars 25 forks source link

Semantic Image Synthesis via Adversarial Learning

This is a PyTorch implementation of the paper Semantic Image Synthesis via Adversarial Learning.

Model architecture

Requirements

Pretrained word vectors for fastText

Download a pretrained English word vectors. You can see the list of pretrained vectors on this page.

Datasets

The caption data is from this repository. After downloading, modify CONFIG file so that all paths of the datasets point to the data you downloaded.

Run

Results

Flowers

Birds

Acknowledgements

We would like to thank Hao Dong, who is one of the first authors of the paper Semantic Image Synthesis via Adversarial Learning, for providing helpful advice for the implementation.