Code for "SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis".
input_pipeline.py
. See below for detailed information on data files.inception_v4_model
.Pre-built tfrecord files are available for out of the box training.
Note: The webite hosting the dataset is no longer available. Please use the script under data_processing
folder to crawl your own images.
If you want to build tfrecord files from images, run flickr_to_tfrecord.py
or sketchy_to_tfrecord.py
for the respective dataset.
If you wish to get the image files:
extract_images.py
under data_processing
to extract images from tfrecord files. You need to specify input and output paths. The extracted images will be sorted by class names.edge_detection/batch_hed.py
-> edge_detection/PostprocessHED.m
-> `flickr_to_tfrecord.py
to create your own dataset.The model can be trained out of the box, by running main_single.py
. But there are several places you can change configurations:
main_single.py
config.py
models_mru.py
resume_from
.mode
from train
to test
and fill in resume_from
.If you use our work for your research, please cite our paper
@InProceedings{Chen_2018_CVPR,
author = {Chen, Wengling and Hays, James},
title = {SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}