LAGAN

Pytorch implementation for (PRCV 2022) LAGAN: Landmark Aided Text to Face Sketch Generation.

Overview

Data

TextCUFSF dataset has been included in data/sketches/

Training

All code was developed and tested on Ubuntu 16.04 with Python 3.7 (Anaconda) and PyTorch 1.1.

DAMSM model includes text encoder and image encoder

• Pre-train DAMSM model for TextCUFSF dataset:

python pretrain_DAMSM.py --cfg cfg/DAMSM/sketches_18_4.yml --gpu 0

LAGAN model

• Train LAGAN model for TextCUFSF dataset:

python main.py --cfg cfg/train_sketch_18_4.yml --gpu 1

*.yml files include configuration for training and testing.

Testing

• Test LAGAN model for bird dataset:

python main.py --cfg cfg/eval_sketch_18_4.yml --gpu 2

Examples generated by LAGAN

Code Structure

• code/main.py: the entry point for training and testing.
• code/trainer_mutual_self.py: creates the main networks, harnesses and reports the progress of training.
• code/model.py: defines the architecture of LAGAN.
• code/attention.py: defines the spatial and channel-wise attentions.
• code/VGGFeatureLoss.py: defines the architecture of the VGG-16.
• code/datasets.py: defines the class for loading images and captions.
• code/pretrain_DAMSM.py: creates the text and image encoders, harnesses and reports the progress of training.
• code/miscc/losses.py: defines and computes the losses.
• code/miscc/config.py: creates the option list.
• code/miscc/utils.py: additional functions.

Citiation

If you find this work helpful, please consider citing:

@inproceedings{LAGAN,
  title={LAGAN: Landmark Aided Text to Face Sketch Generation},
  author={Chao, Wentao and Chang, Liang and Xi, Fangfang and Duan, Fuqing},
  booktitle={Chinese Conference on Pattern Recognition and Computer Vision (PRCV)},
  year={2022},
  organization={Springer}
}

Acknowledgements

This code borrows heavily from ControlGAN repository. Thanks a lot.