# Neural Style Transfer
> Create **artificial artwork** by transferring the appearance of one image (ie a famous painting) to another user-supplied image (e.g. your favorite photo).
**Documentation**: [https://boromir674.github.io/neural-style-transfer/](https://boromir674.github.io/neural-style-transfer/)
<div style="display: flex; align-items: center; margin-bottom: 25px;">
<img src="./tests/data/canoe_water_w300-h225.jpg" alt="Demo Content Image" style="vertical-align: middle;">
<span style="margin: 0 10px; font-size: 24px; vertical-align: middle;">+</span>
<img src="./tests/data/blue-red_w300-h225.jpg" alt="Demo Style Image" style="vertical-align: middle;">
<span style="margin: 0 10px; font-size: 24px; vertical-align: middle;">=</span>
<img src="./tests/data/canoe_water_w300-h225.jpg+blue-red_w300-h225.jpg-100-demo-gui-run-1.png" alt="Demo Gen Image" style="vertical-align: middle;">
</div>
Uses a `Neural Style Transfer` algorithm to transfer the **style** (aka appearance), from one image, into the **contents** of another.
`Neural Style Transfer (NST)` is an algorithm that applies the `style` of an image to the `contents` of another and produces a `generated` image.
The idea is to find out how someone, with the `painting style` shown in one image, would depict the `contents` shown in another image.
NST takes as INPUT a `Content` image (e.g. a picture taken with your camera) and a `Style` image (e.g. a Van Gogh painting) and `Generates` a new image.
# Overview
This project provides an `NST` algorithm through
- the `artificial_artwork` **Python package** (aka module)
- the `nst` **CLI**
- the `boromir674/neural-style-transfer` **Docker image**
<!-- This package exposes a configurable NST algorithm via a convenient CLI program. -->
| Build | Package | Containerization | Code Quality |
|-------|---------|------------------|--------------|
| ![CI Pipeline Status][ci-pipeline-status] | ![PyPI][pypi] ![Wheel][wheel] ![Python Versions][python-versions] ![Commits Since][commits-since] | ![Docker][docker] ![Image Size][image-size] | ![Codacy][codacy] ![Code Climate][code-climate] ![Maintainability][maintainability] ![Scrutinizer][scrutinizer] |
## Features
- VGG-19 Convolutional Neural Network, as `Image model`
- Selection of `style layers` at runtime
- Efficient Iterative Learning Algorithm, with `tensorflow`
- Fast minimization of loss/cost function with parallel/multicore execution
- Selection of Algorithm Termination Condition/Criteria, at runtime
- Periodic persistance of `Generated image`, during Learning loop
## Quick-start
Run a demo NST, on sample `Content` and `Style` Images:
```sh
mkdir art
export NST_HOST_MOUNT="$PWD/art"
docker-compose up
# Process runs, in containerized environment, and exits.
```
Check out your Generated Image! Artificial Artwork: art/canoe_water_w300-h225.jpg+blue-red_w300-h225.jpg-100.png
```shell
xdg-open art/canoe_water_w300-h225.jpg+blue-red_w300-h225.jpg-100.png
```
## Usage
Run the `nst` CLI with the `--help` option to see the available options.
```shell
docker run boromir674/neural-style-transfer:1.0.2 --help
```
## Development
### Installation
Install `nst` CLI and `artificial_artwork` python package from `pypi`:
Note: Installation on Debian-based Distros for Python 3.11 require `distutils` which is
not included in python3.11 standard distribution (but included in python3.10).
```shell
sudo apt-get install python3.11-distutils
```
```shell
pip install artificial_artwork
```
Only python3.8 wheel is included atm.
Sample commands to install the NST CLI from source, using a terminal:
```shell
git clone https://github.com/boromir674/neural-style-transfer.git
pip install ./neural-style-transfer
```
> The Neural Style Transfer - CLI heavely depends on Tensorflow (tf) and therefore it is crucial that tf is installed correctly in your Python environment.
[ci-pipeline-status]: https://img.shields.io/github/actions/workflow/status/boromir674/neural-style-transfer/test.yaml?branch=main&label=build&logo=github-actions&logoColor=233392FF
[pypi]: https://img.shields.io/pypi/v/artificial-artwork?color=blue&label=pypi&logo=pypi&logoColor=%23849ed9
[wheel]: https://img.shields.io/pypi/wheel/artificial-artwork?logo=python&logoColor=%23849ed9
[python-versions]: https://img.shields.io/pypi/pyversions/artificial-artwork?color=blue&logo=python&logoColor=%23849ed9
[commits-since]: https://img.shields.io/github/commits-since/boromir674/neural-style-transfer/v2.0.0/main?color=blue&logo=Github
[docker]: https://img.shields.io/docker/v/boromir674/neural-style-transfer/latest?logo=docker&logoColor=%23849ED9
[image-size]: https://img.shields.io/docker/image-size/boromir674/neural-style-transfer/latest?logo=docker&logoColor=%23849ED9
[codacy]: https://app.codacy.com/project/badge/Grade/07b27ac547a94708aefc5e845d2b6d01
[code-climate]: https://api.codeclimate.com/v1/badges/2ea98633f88b75e87d1a/maintainability
[maintainability]: https://img.shields.io/codeclimate/tech-debt/boromir674/neural-style-transfer?logo=CodeClimate
[scrutinizer]: https://img.shields.io/scrutinizer/quality/g/boromir674/neural-style-transfer/main?logo=scrutinizer-ci
Raw data
{
"_id": null,
"home_page": "https://github.com/boromir674/neural-style-transfer",
"name": "artificial-artwork",
"maintainer": "Konstantinos Lampridis",
"docs_url": null,
"requires_python": "<3.12,>=3.10",
"maintainer_email": "k.lampridis@hotmail.com",
"keywords": "artificial intelligence, neural style transfer, artificial art, deep learning, cli, gui",
"author": "Konstantinos Lampridis",
"author_email": "k.lampridis@hotmail.com",
"download_url": "https://files.pythonhosted.org/packages/cb/3a/3a90b05f6dd31e54e463aad48f8cc35b7f24843a011c60796de674fd81bf/artificial_artwork-2.0.0.tar.gz",
"platform": null,
"description": "# Neural Style Transfer\n\n> Create **artificial artwork** by transferring the appearance of one image (ie a famous painting) to another user-supplied image (e.g. your favorite photo).\n\n**Documentation**: [https://boromir674.github.io/neural-style-transfer/](https://boromir674.github.io/neural-style-transfer/)\n\n<div style=\"display: flex; align-items: center; margin-bottom: 25px;\">\n <img src=\"./tests/data/canoe_water_w300-h225.jpg\" alt=\"Demo Content Image\" style=\"vertical-align: middle;\">\n <span style=\"margin: 0 10px; font-size: 24px; vertical-align: middle;\">+</span>\n <img src=\"./tests/data/blue-red_w300-h225.jpg\" alt=\"Demo Style Image\" style=\"vertical-align: middle;\">\n <span style=\"margin: 0 10px; font-size: 24px; vertical-align: middle;\">=</span>\n <img src=\"./tests/data/canoe_water_w300-h225.jpg+blue-red_w300-h225.jpg-100-demo-gui-run-1.png\" alt=\"Demo Gen Image\" style=\"vertical-align: middle;\">\n</div>\n\nUses a `Neural Style Transfer` algorithm to transfer the **style** (aka appearance), from one image, into the **contents** of another.\n\n\n`Neural Style Transfer (NST)` is an algorithm that applies the `style` of an image to the `contents` of another and produces a `generated` image. \nThe idea is to find out how someone, with the `painting style` shown in one image, would depict the `contents` shown in another image.\n\nNST takes as INPUT a `Content` image (e.g. a picture taken with your camera) and a `Style` image (e.g. a Van Gogh painting) and `Generates` a new image.\n\n\n\n# Overview\nThis project provides an `NST` algorithm through\n- the `artificial_artwork` **Python package** (aka module)\n- the `nst` **CLI**\n- the `boromir674/neural-style-transfer` **Docker image**\n\n<!-- This package exposes a configurable NST algorithm via a convenient CLI program. -->\n\n| Build | Package | Containerization | Code Quality |\n|-------|---------|------------------|--------------|\n| ![CI Pipeline Status][ci-pipeline-status] | ![PyPI][pypi] ![Wheel][wheel] ![Python Versions][python-versions] ![Commits Since][commits-since] | ![Docker][docker] ![Image Size][image-size] | ![Codacy][codacy] ![Code Climate][code-climate] ![Maintainability][maintainability] ![Scrutinizer][scrutinizer] |\n\n\n## Features\n- VGG-19 Convolutional Neural Network, as `Image model`\n- Selection of `style layers` at runtime\n- Efficient Iterative Learning Algorithm, with `tensorflow`\n- Fast minimization of loss/cost function with parallel/multicore execution\n- Selection of Algorithm Termination Condition/Criteria, at runtime\n- Periodic persistance of `Generated image`, during Learning loop\n\n## Quick-start\n\nRun a demo NST, on sample `Content` and `Style` Images:\n\n```sh\nmkdir art\nexport NST_HOST_MOUNT=\"$PWD/art\"\n\ndocker-compose up\n\n# Process runs, in containerized environment, and exits.\n```\n\nCheck out your Generated Image! Artificial Artwork: art/canoe_water_w300-h225.jpg+blue-red_w300-h225.jpg-100.png\n\n```shell\nxdg-open art/canoe_water_w300-h225.jpg+blue-red_w300-h225.jpg-100.png\n```\n\n## Usage\n\nRun the `nst` CLI with the `--help` option to see the available options.\n\n```shell\ndocker run boromir674/neural-style-transfer:1.0.2 --help\n```\n\n## Development\n\n### Installation\n\nInstall `nst` CLI and `artificial_artwork` python package from `pypi`:\n\nNote: Installation on Debian-based Distros for Python 3.11 require `distutils` which is\nnot included in python3.11 standard distribution (but included in python3.10).\n\n```shell\nsudo apt-get install python3.11-distutils\n```\n\n```shell\npip install artificial_artwork\n```\n\nOnly python3.8 wheel is included atm.\n\n\nSample commands to install the NST CLI from source, using a terminal:\n\n```shell\ngit clone https://github.com/boromir674/neural-style-transfer.git\n \npip install ./neural-style-transfer\n```\n\n> The Neural Style Transfer - CLI heavely depends on Tensorflow (tf) and therefore it is crucial that tf is installed correctly in your Python environment.\n\n\n[ci-pipeline-status]: https://img.shields.io/github/actions/workflow/status/boromir674/neural-style-transfer/test.yaml?branch=main&label=build&logo=github-actions&logoColor=233392FF\n[pypi]: https://img.shields.io/pypi/v/artificial-artwork?color=blue&label=pypi&logo=pypi&logoColor=%23849ed9\n[wheel]: https://img.shields.io/pypi/wheel/artificial-artwork?logo=python&logoColor=%23849ed9\n[python-versions]: https://img.shields.io/pypi/pyversions/artificial-artwork?color=blue&logo=python&logoColor=%23849ed9\n[commits-since]: https://img.shields.io/github/commits-since/boromir674/neural-style-transfer/v2.0.0/main?color=blue&logo=Github\n[docker]: https://img.shields.io/docker/v/boromir674/neural-style-transfer/latest?logo=docker&logoColor=%23849ED9\n[image-size]: https://img.shields.io/docker/image-size/boromir674/neural-style-transfer/latest?logo=docker&logoColor=%23849ED9\n[codacy]: https://app.codacy.com/project/badge/Grade/07b27ac547a94708aefc5e845d2b6d01\n[code-climate]: https://api.codeclimate.com/v1/badges/2ea98633f88b75e87d1a/maintainability\n[maintainability]: https://img.shields.io/codeclimate/tech-debt/boromir674/neural-style-transfer?logo=CodeClimate\n[scrutinizer]: https://img.shields.io/scrutinizer/quality/g/boromir674/neural-style-transfer/main?logo=scrutinizer-ci\n\n\n",
"bugtrack_url": null,
"license": "AGPL-3.0-only",
"summary": "Create artificial artwork by transfering the appearance of one image (eg a famous painting) to another user-supplied image (eg your favourite photograph).",
"version": "2.0.0",
"project_urls": {
"Bug Tracker": "https://github.com/boromir674/neural-style-transfer/issues",
"CI: Github Actions": "https://github.com/boromir674/neural-style-transfer/actions",
"Changelog": "https://github.com/boromir674/neural-style-transfer/blob/master/CHANGELOG.rst",
"Documentation": "https://neural-style-transfer.readthedocs.io/",
"Homepage": "https://github.com/boromir674/neural-style-transfer",
"Repository": "https://github.com/boromir674/neural-style-transfer",
"Source Code": "https://github.com/boromir674/neural-style-transfer"
},
"split_keywords": [
"artificial intelligence",
" neural style transfer",
" artificial art",
" deep learning",
" cli",
" gui"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "220854f8b5b800b3ad567cd5426d39c8b9a8854e2562bf4934b0729562c2b7d3",
"md5": "498b5b8b8b3fd546ecbcce2e2ec036cf",
"sha256": "4c6fba3d134b611b42bfad52a470165bf07955e4164104cdfcbf5345c09a7ef0"
},
"downloads": -1,
"filename": "artificial_artwork-2.0.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "498b5b8b8b3fd546ecbcce2e2ec036cf",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.12,>=3.10",
"size": 76384,
"upload_time": "2024-11-08T15:57:05",
"upload_time_iso_8601": "2024-11-08T15:57:05.259149Z",
"url": "https://files.pythonhosted.org/packages/22/08/54f8b5b800b3ad567cd5426d39c8b9a8854e2562bf4934b0729562c2b7d3/artificial_artwork-2.0.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "cb3a3a90b05f6dd31e54e463aad48f8cc35b7f24843a011c60796de674fd81bf",
"md5": "15622045a49e2837d42fbe88fa734a39",
"sha256": "a941f19ce93cddfb873bd9ce238650ba985135a5ac558f230aaa9610903f5b6b"
},
"downloads": -1,
"filename": "artificial_artwork-2.0.0.tar.gz",
"has_sig": false,
"md5_digest": "15622045a49e2837d42fbe88fa734a39",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.12,>=3.10",
"size": 1371749,
"upload_time": "2024-11-08T15:57:06",
"upload_time_iso_8601": "2024-11-08T15:57:06.628981Z",
"url": "https://files.pythonhosted.org/packages/cb/3a/3a90b05f6dd31e54e463aad48f8cc35b7f24843a011c60796de674fd81bf/artificial_artwork-2.0.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-08 15:57:06",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "boromir674",
"github_project": "neural-style-transfer",
"travis_ci": false,
"coveralls": true,
"github_actions": true,
"circle": true,
"tox": true,
"lcname": "artificial-artwork"
}
JSON
