Metadata-Version: 2.1
Name: pastiche
Version: 1.2.0
Summary: A PyTorch implementation of Neural Style Transfer (NST)
Home-page: https://github.com/dstein64/pastiche
Author: Daniel Steinberg
Author-email: ds@dannyadam.com
License: MIT
Keywords: gatys,style-transfer,neural-style-transfer
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Artistic Software
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: Unix
Classifier: Operating System :: POSIX :: Linux
Classifier: Operating System :: MacOS
Classifier: Operating System :: Microsoft :: Windows
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: h5py
Requires-Dist: pillow
Requires-Dist: torch
Requires-Dist: torchvision
Provides-Extra: dev
Requires-Dist: kmeans1d ; extra == 'dev'

[![Build Status](https://github.com/dstein64/pastiche/workflows/build/badge.svg)](https://github.com/dstein64/pastiche/actions)

pastiche
========

A PyTorch-based Python implementation of Neural Style Transfer [1].

<div align="center">
 <img src="https://github.com/dstein64/pastiche/blob/master/example/vangogh_starry_night.jpg?raw=true" height="256"/>
 <img src="https://github.com/dstein64/pastiche/blob/master/example/boston.jpg?raw=true" height="256"/>
 <br>
 <img src="https://github.com/dstein64/pastiche/blob/master/example/pastiche.jpg?raw=true" width="710"/>
</div>

Features
--------

- Support for saving intermediate images during optimization
- An option for preserving colors from the content image
- Multiple-device computation (`--supplemental-device`)
- Style transfers utilizing multiple style images

Installation
------------

#### Requirements

- Python 3.6 or greater

#### Install

```sh
$ pip3 install pastiche
```

#### Update

```sh
$ pip3 install --upgrade pastiche
```

Usage
-----

The program is intended to be used from the command line.

The general command line usage is shown below.

```sh
$ pastiche --content CONTENT --styles STYLE [STYLE ...] --output 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.

```sh
$ python3 -m pastiche --content CONTENT --styles STYLE [STYLE ...] --output OUTPUT
```

There are various options, including but not limited to:
- Devices (GPU, CPU, and/or a multi-device assortment)
- 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`.

```sh
$ pastiche --help
```

Example
-------

<img src="https://github.com/dstein64/pastiche/blob/master/example/pastiche.jpg?raw=true" width="384"/>

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]. Example commands are shown below. Depending on GPU memory availability, the
commands may necessitate execution partially on a CPU (e.g., `--device cuda:0 --supplemental-device cuda:1 10
--supplemental-device cpu 20` would configure GPU 0 for layers 0 through 9, GPU 1 for layers 10 through 19, and the
CPU for layers 20 through 36).

```sh
$ pastiche                            \
    --device cuda                     \
    --num-steps 2000                  \
    --content boston.jpg              \
    --styles vangogh_starry_night.jpg \
    --output pastiche0.png

$ pastiche                            \
    --device cuda                     \
    --size 1024                       \
    --num-steps 1000                  \
    --init pastiche0.png              \
    --content boston.jpg              \
    --styles vangogh_starry_night.jpg \
    --output pastiche1.png

# Split the computation across a GPU (layers 0 through 5 and 10 through 19), another GPU (layers 6
# through 9), and a CPU (layers 20 through 36). This device strategy is for the purpose of
# illustration. Tuning would be required for an actual device setup.
$ pastiche                            \
    --device cuda:0                   \
    --supplemental-device cuda:1 6    \
    --supplemental-device cuda:0 10   \
    --supplemental-device cpu 20      \
    --info-step 10                    \
    --size 2048                       \
    --num-steps 500                   \
    --init pastiche1.png              \
    --content boston.jpg              \
    --styles vangogh_starry_night.jpg \
    --output pastiche2.png

# Split the computation across a GPU (layers 0 through 3) and CPU (layers 4 through 36). This
# device strategy is for the purpose of illustration. Tuning would be required for an actual
# device setup.
$ pastiche                            \
    --device cuda                     \
    --supplemental-device cpu 4       \
    --info-step 1                     \
    --size 4096                       \
    --num-steps 100                   \
    --init pastiche2.png              \
    --content boston.jpg              \
    --styles vangogh_starry_night.jpg \
    --output 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`.

<img src="https://github.com/dstein64/pastiche/blob/master/example/pastiche_preserve_color.jpg?raw=true" width="384"/>

License
-------

The source code has an [MIT License](https://en.wikipedia.org/wiki/MIT_License).

See [LICENSE](https://github.com/dstein64/pastiche/blob/master/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.


