Generative Adversarial Text-to-Image Synthesis

This repository includes PyTorch and Tensorflow implementations of Generative Adversarial Text-to-Image Synthesis used for the final project for Artificial Neural Computation.

Instructions to run found in either folder

Requirements

PyTorch

* Python==3.6
* PyTorch==0.4.0
* TorchVision==0.2.1
* Theano
* NLTK
* tqdm

Tensorflow

- python==3.7.3
- tensorflow==1.14
- scipy==1.2.0
- numpy==1.16.4
- pillow==6.1.0
- easydict==1.9
- imageio==2.4.1
- imageio-ffmpeg==0.3.0
- pyyaml==5.1.2

Acknowledgements

* PyTorch implementation is adopted heavily from https://github.com/aelnouby/Text-to-Image-Synthesis
* Tensorflow implementation is adopted heavily from https://github.com/crisbodnar/text-to-image

References

[1] Generative Adversarial Text-to-Image Synthesis https://arxiv.org/abs/1605.05396