https://github.com/trsvchn/deep-textures
Unofficial Reimplementation of "Texture Synthesis Using Convolutional Neural Networks" in PyTorch [Gatys et al. 2015](http://arxiv.org/abs/1505.07376)
https://github.com/trsvchn/deep-textures
pytorch reimplementation texture-synthesis
Last synced: 11 months ago
JSON representation
Unofficial Reimplementation of "Texture Synthesis Using Convolutional Neural Networks" in PyTorch [Gatys et al. 2015](http://arxiv.org/abs/1505.07376)
- Host: GitHub
- URL: https://github.com/trsvchn/deep-textures
- Owner: trsvchn
- Created: 2021-02-02T16:47:35.000Z (about 5 years ago)
- Default Branch: main
- Last Pushed: 2021-02-04T14:00:09.000Z (about 5 years ago)
- Last Synced: 2025-03-27T21:01:52.994Z (11 months ago)
- Topics: pytorch, reimplementation, texture-synthesis
- Language: Jupyter Notebook
- Homepage:
- Size: 2.97 MB
- Stars: 6
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Deep Textures
Unofficial Reimplementation of "Texture Synthesis Using Convolutional Neural Networks" in PyTorch
(Gatys et al. [1])
## Dependencies
`python=3.8.5` `pytorch=1.7.1` `torchvision=0.8.2` `pillow=8.1.0`
## Notes
This implementation uses pretrained `vgg19` model from the `torchvision` model zoo, thus model weights are
not scaled as described in the original paper.
## References
1. Gatys, L. A., Ecker, A. S., & Bethge, M. (2015). Texture synthesis using convolutional neural networks.
arXiv preprint [arXiv:1505.07376](http://arxiv.org/abs/1505.07376)
2. [Official Caffe implementation](https://github.com/leongatys/DeepTextures)
## Disclaimer
This software is published for academic and non-commercial use only.