Text-to-Image Generation

This project is aimed at developing a better model for text to image generation.
This was done as part of the group project for CSE 291G (Deep Learning for Sequences) course at UCSD.
Contributors: Anurag Paul, Harshul Gupta and Aashi Jain.

Getting Started

Dependencies

Install python3 and pytorch.
install other requirements using

pip install -r requirements.txt

Name		Name	Last commit message	Last commit date
Latest commit History 91 Commits
attnGan		attnGan
config		config
damsm		damsm
data		data
self_attn		self_attn
.gitignore		.gitignore
FreeMono.ttf		FreeMono.ttf
LICENSE		LICENSE
README.md		README.md
base_model.py		base_model.py
data_loader.py		data_loader.py
data_preprocess.py		data_preprocess.py
get_dataset.sh		get_dataset.sh
get_flickr_dataset.sh		get_flickr_dataset.sh
inception_score.py		inception_score.py
losses.py		losses.py
networks.py		networks.py
requirements.txt		requirements.txt
test_model.py		test_model.py
train_attn_gan.py		train_attn_gan.py
train_damsm.py		train_damsm.py
train_self_attn_gan.py		train_self_attn_gan.py
utils.py		utils.py

License

anurag1paul/TransformerGen

Folders and files

Latest commit

History

Repository files navigation

Text-to-Image Generation

Getting Started

Dependencies

About

Resources

License

Stars

Watchers

Forks

Languages