StackGAN-Pytorch-Python3

A port of the PyTorch implementation of StackGAN to Python 3. Verified working on Windows 10 with Python 3.7 and the provided COCO data. Note the additional requirement for tensorboardX. Original StackGAN-Pytorch repo here.

Dependencies

• Python 3.7

• Pytorch

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

• tensorboard
• tensorboardX
• python-dateutil
• easydict
• pandas
• torchfile

The remaining steps are essentially the same:

Data

1. Download our preprocessed char-CNN-RNN text embeddings for training coco and evaluating coco, save them to data/coco.

• [Optional] Follow the instructions reedscot/icml2016 to download the pretrained char-CNN-RNN text encoders and extract text embeddings.

2. Download the coco image data. Extract them to data/coco/.

Training

• The steps to train a StackGAN model on the COCO dataset using our preprocessed embeddings.
  • Step 1: train Stage-I GAN (e.g., for 120 epochs) python main.py --cfg cfg/coco_s1.yml --gpu 0
  • Step 2: train Stage-II GAN (e.g., for another 120 epochs) python main.py --cfg cfg/coco_s2.yml --gpu 0
• *.yml files are example configuration files for training/evaluating our models.
• If you want to try your own datasets, here are some good tips about how to train GAN. Also, we encourage to try different hyper-parameters and architectures, especially for more complex datasets.

Pretrained Model

• StackGAN for coco. Download and save it to models/coco.
• Our current implementation has a higher inception score(10.62±0.19) than reported in the StackGAN paper

Evaluating

• Run python main.py --cfg cfg/coco_eval.yml --gpu 0 to generate samples from captions in COCO validation set.

Examples for COCO:

Save your favorite pictures generated by our models since the randomness from noise z and conditioning augmentation makes them creative enough to generate objects with different poses and viewpoints from the same description 😃

Citing StackGAN

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

@inproceedings{han2017stackgan,
Author = {Han Zhang and Tao Xu and Hongsheng Li and Shaoting Zhang and Xiaogang Wang and Xiaolei Huang and Dimitris Metaxas},
Title = {StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks},
Year = {2017},
booktitle = {{ICCV}},
}

Our follow-up work

• StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
• AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks [supplementary][code]

References

• Generative Adversarial Text-to-Image Synthesis Paper Code
• Learning Deep Representations of Fine-grained Visual Descriptions Paper Code