Zizhao Zhang, Yuanpu Xie, Lin Yang, "Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network", CVPR (2018) * indicates contribution
Visual results (Left: compared against StackGAN; Right: multi-resolution generator outputs)
Download preprocessed data in /Data.
device=0 sh train_birds.sh
device=0 sh train_flower.sh
device=0,1 sh train_coco.sh
To use multiple GPUs, simply set device='0,1,..' as a set of gpu ids.
python -m visdom.server -port 43426
(keep the same port id with _port defined in plot_utils.py). Then access http://localhost:43426 from the browser.sh test_birds.sh
for birdssh test_flowers.sh
for flowersh test_coco.sh
for cocoWe provide multiple evaluation tools to ease test. Evaluation needs the sampled results obtained in Testing and saved in ./Results.
Inception score
sh compute_inception_score.sh
MS-SSIM
sh compute_ms_ssim.sh
VS-Similarity
sh compute_neudist_score.sh
We provide pretrained models for birds, flowers, and coco.
If you find HDGAN useful in your research, please cite:
@inproceedings{zhang2018hdgan,
Author = {Zizhao Zhang and Yuanpu Xie and Lin Yang},
Title = {Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network},
Year = {2018},
booktitle = {CVPR},
}
MIT