Skip to main content

PIL × DAT - Pillow extension for AI-based image upscaling.

Project description

iLoveData

PIL × DAT - Pillow extension for AI-based image upscaling.

Build Status License


Installation

For PyPI:

pip install pillow-dat

For Conda:

conda install -c conda-forge pillow-dat

Get started

    1. Download DAT_light_x2.pth model weight from Google Drive. We highly recommend utilizing DAT_light_x*.pth models due to their lightweight design and exceptional speed.
    1. 🎉 Then you are all set to upscale your images:
from PIL.Image import open
from PIL_DAT.Image import upscale

image = open("./lumine.png")
image = upscale(lumine_image, "./DAT_light_x2.pth", 2)
image.show()

Contribution

Please install Miniconda.

Please install VSCode extensions:

  • Black Formatter
  • isort
  • Python
  • Pylance

To install dependencies on a given pillow-dat Python environnement:

conda env create --file environment.yml

To update this environment:

conda env update --file environment.yml --prune

To run unit tests:

python -m pytest

Acknowledgement

This library is founded upon the pioneering research paper, "Dual Aggregation Transformer for Image Super-Resolution".

@inproceedings{chen2023dual,
    title={Dual Aggregation Transformer for Image Super-Resolution},
    author={Chen, Zheng and Zhang, Yulun and Gu, Jinjin and Kong, Linghe and Yang, Xiaokang and Yu, Fisher},
    booktitle={ICCV},
    year={2023}
}

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

pillow_dat-0.1.0.tar.gz (35.7 kB view details)

Uploaded Source

Built Distribution

pillow_dat-0.1.0-py3-none-any.whl (14.2 kB view details)

Uploaded Python 3

File details

Details for the file pillow_dat-0.1.0.tar.gz.

File metadata

  • Download URL: pillow_dat-0.1.0.tar.gz
  • Upload date:
  • Size: 35.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.2 CPython/3.12.2 Windows/11

File hashes

Hashes for pillow_dat-0.1.0.tar.gz
Algorithm Hash digest
SHA256 8f43d1cce01878ef27d809218443f85e7e2462eb573aefcd52cfa1631766d88b
MD5 5b9eed7adf3d4d5e3d7a99be8ff34807
BLAKE2b-256 2b86f96bf1afd16010c635c150c12dbab003bfb13286064f92c53e9f6ba6f7b0

See more details on using hashes here.

File details

Details for the file pillow_dat-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: pillow_dat-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 14.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.2 CPython/3.12.2 Windows/11

File hashes

Hashes for pillow_dat-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6c50e2d7ee214cefa85703320e96dd96d8788171efe42eccec418766a87791c6
MD5 921a1336baffd530dcdb467fee3e08f2
BLAKE2b-256 564736c0f04dad090599993a4f5a5e49b8e80ecfa78c68a6c1e4ba015b353acc

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