/Implementation-of-the-paper-Diversified-Arbitrary-Style-Transfer-via-Deep-Feature-Perturb

Primary LanguagePythonMIT LicenseMIT

Universal Style Transfer

This is the Pytorch Implementation-of-the-paper-Diversified-Arbitrary-Style-Transfer-via-Deep-Feature-Perturb.

Prerequisites

  • Pytorch
  • torchvision
  • Pretrained encoder and decoder models for image reconstruction only (download and uncompress them under models/)
  • CUDA + CuDNN

Prepare images

Simply put content and image pairs in images/content and images/style respectively. Note that correspoding conternt and image pairs should have same names.

Style Transfer

python WCT.py --cuda

Reference

Li Y, Fang C, Yang J, et al. Universal Style Transfer via Feature Transforms[J]. arXiv preprint arXiv:1705.08086, 2017.