DynaST

This is the pytorch implementation of the following ECCV 2022 paper:

DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation

Songhua Liu, Jingwen Ye, Sucheng Ren, and Xinchao Wang.

Installation

git clone https://github.com/Huage001/DynaST.git
cd DynaST
conda create -n DynaST python=3.6
conda activate DynaST
pip install -r requirements.txt

Inference

Prepare DeepFashion dataset following the instruction of CoCosNet.
Create a directory for checkpoints if there is not:
```
mkdir -p checkpoints/deepfashion/
```
Download pre-trained model from here and move the file to the directory 'checkpoints/deepfashion/'.
Edit the file 'test_deepfashion.sh' and set the argument 'dataroot' to the root of the DeepFashion dataset.
Run:
```
bash test_deepfashion.sh
```
Check the results in the directory 'checkpoints/deepfashion/test/'.

Training

Create a directory for the pre-trained VGG model if there is not:
```
mkdir vgg
```
Download pre-trained VGG model used for loss computation from here and move the file to the directory 'vgg'.
Edit the file 'train_deepfashion.sh' and set the argument 'dataroot' to the root of the DeepFashion dataset.
Run:
```
bash train_deepfashion.sh
```
Checkpoints and intermediate results are saved in the directory 'checkpoints/deepfashion/'.

Citation

If you find this project useful in your research, please consider cite:

@Article{liu2022dynast,
    author  = {Songhua Liu, Jingwen Ye, Sucheng Ren, Xinchao Wang},
    title   = {DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation},
    journal = {European Conference on Computer Vision},
    year    = {2022},
}

Acknowledgement

This code borrows heavily from CoCosNet. We also thank the implementation of Synchronized Batch Normalization.