Skip to main content

Image style transfer using Torch

Project description

Logo

License repo size

Description


Timst is a python package based on pyTorch that extracts the features of an image and tranfers them into another; such a technique is known as image style transfer. The following implementation is a re-implementation of this code that is based on the following scientific paper. The architecture is based on Convolutional Neural Network (CNN) which is one of the applications of Deep Learning.

How to install


There are different ways the package can be installed:

  • By clonning this repository and running the following command in the terminal (you might require sudo privilege)
git clone https://github.com/Radonirinaunimi/Style-Transfer
cd Style-Transfer/
python setup.py install --user
  • By installing it through the Python Package Index (PyPI)
pip install timst --upgrade

How to use


To use timst, just run the following:

timst -i [IMAGE_TO_BE_STYLED] -s [STYLE_TO_BE_APPLIED] [-n NUMBER_OF_ITERATIONS]

For bugs and feature request


Open an issue or a pull request.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

timst-0.2.1.tar.gz (5.1 kB view details)

Uploaded Source

Built Distribution

timst-0.2.1-py3-none-any.whl (6.0 kB view details)

Uploaded Python 3

File details

Details for the file timst-0.2.1.tar.gz.

File metadata

  • Download URL: timst-0.2.1.tar.gz
  • Upload date:
  • Size: 5.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/49.2.0 requests-toolbelt/0.9.1 tqdm/4.48.0 CPython/3.8.5

File hashes

Hashes for timst-0.2.1.tar.gz
Algorithm Hash digest
SHA256 4e134efff1d603a8e0938c37271babbd584e12cc50f3181b46ec3ebe8a56e2d6
MD5 315a7480e08bba089c75c174f900c7cd
BLAKE2b-256 116a7fbd1753792b648a0b02713a93a43fa8d235f21c3137a091852c99a12895

See more details on using hashes here.

File details

Details for the file timst-0.2.1-py3-none-any.whl.

File metadata

  • Download URL: timst-0.2.1-py3-none-any.whl
  • Upload date:
  • Size: 6.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/49.2.0 requests-toolbelt/0.9.1 tqdm/4.48.0 CPython/3.8.5

File hashes

Hashes for timst-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 188e8d2bc1d11ab1b1f864d7d588920df556c46e508e06a30af8f5a591bdf587
MD5 737dcbdd2b76c4f09a51fcd23f88e897
BLAKE2b-256 dfc22af4d2891fa26efc20ab1d52831e0a3a10018e65814e2f0d29641e66be6e

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page