AttnGAN + CLIP (Python 3, Pytorch 1.0)

Model modify

full project in : https://drive.google.com/drive/folders/1NwNOofAvyBEN6VtaNJ4N_-qX2vd-0Ugg?usp=sharing

Dependencies

python 3.6+

Pytorch 1.0+

In addition, please add the project folder to PYTHONPATH and pip install the following packages:

• python-dateutil
• easydict
• pandas
• torchfile
• nltk
• scikit-image

Data

1. Download our preprocessed metadata for birds coco and save them to data/
2. Download the birds image data. Extract them to data/birds/
3. Download coco dataset and extract the images to data/coco/

Training and validate

• Using note book: AttnGAN-Project3.ipynb

Citing AttnGAN

If you find AttnGAN useful in your research, please consider citing:

@article{Tao18attngan,
  author    = {Tao Xu, Pengchuan Zhang, Qiuyuan Huang, Han Zhang, Zhe Gan, Xiaolei Huang, Xiaodong He},
  title     = {AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks},
  Year = {2018},
  booktitle = {{CVPR}}
}

Reference

• StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks [code]
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks [code]