[Paper]
MirrorGAN — Simple TensorFlow Implementation: Learning Text-to-image Generation by Redescription
Requirements
- tensorflow >= 1.15
Dataset
Text
Image
Usage
├── dataset
└── YOUR_DATASET_NAME
├── images
├── domain1 (domain folder)
├── xxx.jpg (domain1 image)
├── yyy.png
├── ...
├── domain2
├── aaa.jpg (domain2 image)
├── bbb.png
├── ...
├── domain3
├── ...
├── text
├── captions.pickle
├── filenames_train.pickle
├── filenames_test.pickle
Train
python main.py --dataset birds --phase train
Test
python main.py --dataset birds --phase test