A PyTorch implementation of Neural Style Transfer (NST)
Project description
pastiche
A PyTorch-based Python implementation of Neural Style Transfer [1].
Features
- Support for saving intermediate images during optimization
- An option for preserving colors from the content image
Installation
Requirements
- Python 3.6 or greater
Install
$ pip3 install pastiche
Update
$ pip3 install --upgrade pastiche
Usage
The program is intended to be used from the command line.
The general command line usage is shown below.
$ pastiche CONTENT STYLE OUTPUT
CONTENT
is the path to the content image, STYLE
is the path to the style image, and OUTPUT
is the path to save
the synthesized pastiche PNG file.
If the launcher script was not installed within a directory on your PATH, pastiche can be launched by passing its module name to Python.
$ python3 -m pastiche CONTENT STYLE OUTPUT
There are various options, including but not limited to:
- Device (CPU versus GPU)
- Number of optimization iterations
- VGG layers to utilize
- Loss function term weights
For the full list of options and the corresponding documentation, see the source code or use --help
.
$ pastiche --help
Example
The image above was generated by applying the style from Vincent van Gogh's The Starry Night
to a photo I took in
Boston in 2015. The high-resolution image was generated incrementally, with increasing resolution, using the
coarse-to-fine approach described in [2]. The commands are shown below. Depending on GPU memory availability, the
commands may necessitate execution on a CPU (--device cpu
).
$ pastiche \
--num-steps 2000 \
boston.jpg \
vangogh_starry_night.jpg \
pastiche0.png
$ pastiche \
--size 1024 \
--num-steps 1000 \
--init pastiche0.png \
boston.jpg \
vangogh_starry_night.jpg \
pastiche1.png
$ pastiche \
--size 2048 \
--num-steps 500 \
--init pastiche1.png \
boston.jpg \
vangogh_starry_night.jpg \
pastiche2.png
$ pastiche \
--size 4096 \
--num-steps 100 \
--init pastiche2.png \
boston.jpg \
vangogh_starry_night.jpg \
pastiche3.png
$ convert pastiche3.png pastiche.jpg # requires ImageMagick
The --preserve-color
option can be used to retain colors from the content image. The image below was generated
using the same commands as above (up to --size 2048
), with the addition of --preserve-color
.
License
The source code has an MIT License.
See LICENSE.
References
[1] Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "A Neural Algorithm of Artistic Style." ArXiv:1508.06576 [Cs, q-Bio], August 26, 2015. http://arxiv.org/abs/1508.06576.
[2] Gatys, Leon A., Alexander S. Ecker, Matthias Bethge, Aaron Hertzmann, and Eli Shechtman. "Controlling Perceptual Factors in Neural Style Transfer." ArXiv:1611.07865 [Cs], November 23, 2016. http://arxiv.org/abs/1611.07865.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.