wchen342
/
SketchyGAN
1
0
Fork 0
Code Releases Activity
Code for paper "SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis"
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
4 Commits
1 Branch
0 Tags
1.1 MiB
 
 
Tree: 85d4ece789
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '85d4ece789'
${ noResults }
wchen342 85d4ece789
Add comments 		5 years ago
data_processing Initial Commit 5 years ago
inception_v4_model Add incpetion folder 5 years ago
src_single Add comments 5 years ago
Readme.md Add Readme 5 years ago
main_single.py Add Readme 5 years ago

Readme.md

SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis

Code for "SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis".

Prerequisites

  • Python, NumPy, SciPy
  • Tensorflow(>=1.4.0)
  • A recent NVIDIA GPU

Preparations

  • The path to data files needs to be specified in input_pipeline.py. The dataset will be released shortly.
  • You need to download "Inception-V4 model", unzip it and put the checkpoint under inception_v4_model.

Configurations

The model can be trained out of the box, by running main_single.py. But there are several places you can change configurations:

  • Commandline options in main_single.py
  • Some global options in config.py
  • Activation/Normalization functions in models_mru.py

Others

  • The model will be saved periodically. If you wish to resume, just use commandline switch resume_from.
  • If you wish to test the model, change mode from train to test and fill in resume_from.