qudida

Name	qudida JSON
Version	0.0.4 JSON
	download
home_page	https://github.com/arsenyinfo/qudida
Summary	QUick and DIrty Domain Adaptation
upload_time	2021-08-09 16:47:55
maintainer
docs_url	None
author
requires_python	>=3.5.0
license
keywords	machine learning computer vision
VCS
bugtrack_url
requirements	opencv-python numpy scikit-learn typing-extensions
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            
# QuDiDA (QUick and DIrty Domain Adaptation)

QuDiDA is a micro library for very naive though quick pixel level image domain adaptation via `scikit-learn` transformers.
Is assumed to be used as image augmentation technique, while was not tested in public benchmarks. 

## Installation
```
pip install qudida
```
or
```
pip install git+https://github.com/arsenyinfo/qudida
```

## Usage 
```
import cv2

from sklearn.decomposition import PCA
from qudida import DomainAdapter

adapter = DomainAdapter(transformer=PCA(n_components=1), ref_img=cv2.imread('target.png'))
source = cv2.imread('source.png')
result = adapter(source)
cv2.imwrite('../result.png', result)
```

## Example 
Source image: 
![source](source.png)
Target image (style donor):
![target](target.png)
Result with various adaptations:
![result](result.gif)



            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/arsenyinfo/qudida",
    "name": "qudida",
    "maintainer": "",
    "docs_url": null,
    "requires_python": ">=3.5.0",
    "maintainer_email": "",
    "keywords": "Machine Learning,Computer Vision",
    "author": "",
    "author_email": "",
    "download_url": "https://files.pythonhosted.org/packages/3e/2d/bab8babd9dc9a9e4df6eb115540cee4322c1a74078fb6f3b3ebc452a22b3/qudida-0.0.4.tar.gz",
    "platform": "",
    "description": "\n# QuDiDA (QUick and DIrty Domain Adaptation)\n\nQuDiDA is a micro library for very naive though quick pixel level image domain adaptation via `scikit-learn` transformers.\nIs assumed to be used as image augmentation technique, while was not tested in public benchmarks. \n\n## Installation\n```\npip install qudida\n```\nor\n```\npip install git+https://github.com/arsenyinfo/qudida\n```\n\n## Usage \n```\nimport cv2\n\nfrom sklearn.decomposition import PCA\nfrom qudida import DomainAdapter\n\nadapter = DomainAdapter(transformer=PCA(n_components=1), ref_img=cv2.imread('target.png'))\nsource = cv2.imread('source.png')\nresult = adapter(source)\ncv2.imwrite('../result.png', result)\n```\n\n## Example \nSource image: \n![source](source.png)\nTarget image (style donor):\n![target](target.png)\nResult with various adaptations:\n![result](result.gif)\n\n\n",
    "bugtrack_url": null,
    "license": "",
    "summary": "QUick and DIrty Domain Adaptation",
    "version": "0.0.4",
    "split_keywords": [
        "machine learning",
        "computer vision"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "a610fdb6ffb429edecde1ab8bfddd921",
                "sha256": "4519714c40cd0f2e6c51e1735edae8f8b19f4efe1f33be13e9d644ca5f736dd6"
            },
            "downloads": -1,
            "filename": "qudida-0.0.4-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "a610fdb6ffb429edecde1ab8bfddd921",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.5.0",
            "size": 3478,
            "upload_time": "2021-08-09T16:47:54",
            "upload_time_iso_8601": "2021-08-09T16:47:54.637858Z",
            "url": "https://files.pythonhosted.org/packages/f0/a1/a5f4bebaa31d109003909809d88aeb0d4b201463a9ea29308d9e4f9e7655/qudida-0.0.4-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "d0a9ba65f9a1537b92400a22685a23a0",
                "sha256": "db198e2887ab0c9aa0023e565afbff41dfb76b361f85fd5e13f780d75ba18cc8"
            },
            "downloads": -1,
            "filename": "qudida-0.0.4.tar.gz",
            "has_sig": false,
            "md5_digest": "d0a9ba65f9a1537b92400a22685a23a0",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.5.0",
            "size": 3100,
            "upload_time": "2021-08-09T16:47:55",
            "upload_time_iso_8601": "2021-08-09T16:47:55.807682Z",
            "url": "https://files.pythonhosted.org/packages/3e/2d/bab8babd9dc9a9e4df6eb115540cee4322c1a74078fb6f3b3ebc452a22b3/qudida-0.0.4.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2021-08-09 16:47:55",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "github_user": "arsenyinfo",
    "github_project": "qudida",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "requirements": [
        {
            "name": "opencv-python",
            "specs": [
                [
                    ">=",
                    "4.0.1"
                ]
            ]
        },
        {
            "name": "numpy",
            "specs": [
                [
                    ">=",
                    "0.18.0"
                ]
            ]
        },
        {
            "name": "scikit-learn",
            "specs": [
                [
                    ">=",
                    "0.19.1"
                ]
            ]
        },
        {
            "name": "typing-extensions",
            "specs": []
        }
    ],
    "lcname": "qudida"
}