lightcone

Name	lightcone JSON
Version	0.1.0 JSON
	download
home_page	https://github.com/windisch/lightcone
Summary	A framework to explore the latent space of autoencoders implemented in torch
upload_time	2023-01-03 23:41:27
maintainer
docs_url	None
author	Tobias Windisch
requires_python	>=3.8.0
license	Apache-2.0
keywords	graphical models
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            # lightcone


[![Test Package](https://github.com/windisch/lightcone/actions/workflows/test_package.yml/badge.svg)](https://github.com/windisch/lightcone/actions/workflows/test_package.yml)
[![Documentation Status](https://readthedocs.org/projects/lightcone/badge/?version=latest)](https://lightcone.readthedocs.io/en/latest/?badge=latest)
[![PyPI](https://img.shields.io/pypi/v/lightcone)](https://pypi.org/project/lightcone/)

A framework to explore the latent space of convolutional autoencoders
implemented in `pytorch`.

## Example

Compose your decoder and your encoder into the `lightcone`
autoencoder:

```python
from lightcone.models import AutoEncoder

model = AutoEncoder(encoder=your_encoder, decoder=your_decoder)
```

After `model` has been training, the latent space can be explored in a
Jupyter-Notebook as follows

```python
model.explore(data_loader=your_data_loader)
```


## Jupyter Dash
Make sure to install and activate the Jupyter notebook extenstion

```bash
jupyter nbextension install --py jupyter_dash
jupyter nbextension enable --py jupyter_dash
```


            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/windisch/lightcone",
    "name": "lightcone",
    "maintainer": "",
    "docs_url": null,
    "requires_python": ">=3.8.0",
    "maintainer_email": "",
    "keywords": "graphical models",
    "author": "Tobias Windisch",
    "author_email": "tobias.windisch@hs-kempten.de",
    "download_url": "https://files.pythonhosted.org/packages/85/64/29831ea18946aae80840f0439c04eb73a6e49b6f71241ea13dd8e5809d0e/lightcone-0.1.0.tar.gz",
    "platform": null,
    "description": "# lightcone\n\n\n[![Test Package](https://github.com/windisch/lightcone/actions/workflows/test_package.yml/badge.svg)](https://github.com/windisch/lightcone/actions/workflows/test_package.yml)\n[![Documentation Status](https://readthedocs.org/projects/lightcone/badge/?version=latest)](https://lightcone.readthedocs.io/en/latest/?badge=latest)\n[![PyPI](https://img.shields.io/pypi/v/lightcone)](https://pypi.org/project/lightcone/)\n\nA framework to explore the latent space of convolutional autoencoders\nimplemented in `pytorch`.\n\n## Example\n\nCompose your decoder and your encoder into the `lightcone`\nautoencoder:\n\n```python\nfrom lightcone.models import AutoEncoder\n\nmodel = AutoEncoder(encoder=your_encoder, decoder=your_decoder)\n```\n\nAfter `model` has been training, the latent space can be explored in a\nJupyter-Notebook as follows\n\n```python\nmodel.explore(data_loader=your_data_loader)\n```\n\n\n## Jupyter Dash\nMake sure to install and activate the Jupyter notebook extenstion\n\n```bash\njupyter nbextension install --py jupyter_dash\njupyter nbextension enable --py jupyter_dash\n```\n\n",
    "bugtrack_url": null,
    "license": "Apache-2.0",
    "summary": "A framework to explore the latent space of autoencoders implemented in torch",
    "version": "0.1.0",
    "split_keywords": [
        "graphical",
        "models"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "f9a77de46fef5ac9f66c477bdf89e3e4414c2328cf2e5dbf7420e23ddddf5062",
                "md5": "d7672ecdfba9bff3f3b0bc1ad7006761",
                "sha256": "68887303c5ca3d717c7da121b3ded9e3eaa6932a3517e38942ff77fdbbca8d36"
            },
            "downloads": -1,
            "filename": "lightcone-0.1.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "d7672ecdfba9bff3f3b0bc1ad7006761",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.8.0",
            "size": 7529,
            "upload_time": "2023-01-03T23:41:25",
            "upload_time_iso_8601": "2023-01-03T23:41:25.977134Z",
            "url": "https://files.pythonhosted.org/packages/f9/a7/7de46fef5ac9f66c477bdf89e3e4414c2328cf2e5dbf7420e23ddddf5062/lightcone-0.1.0-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "856429831ea18946aae80840f0439c04eb73a6e49b6f71241ea13dd8e5809d0e",
                "md5": "18fe6a4b2b78744c0d9c55c15fee529c",
                "sha256": "51ecdfe50385a35c35c1502e691e8487ffdd80465c540d82e1ffcdb6e2e93a89"
            },
            "downloads": -1,
            "filename": "lightcone-0.1.0.tar.gz",
            "has_sig": false,
            "md5_digest": "18fe6a4b2b78744c0d9c55c15fee529c",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.8.0",
            "size": 7118,
            "upload_time": "2023-01-03T23:41:27",
            "upload_time_iso_8601": "2023-01-03T23:41:27.177932Z",
            "url": "https://files.pythonhosted.org/packages/85/64/29831ea18946aae80840f0439c04eb73a6e49b6f71241ea13dd8e5809d0e/lightcone-0.1.0.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2023-01-03 23:41:27",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "github_user": "windisch",
    "github_project": "lightcone",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "requirements": [],
    "lcname": "lightcone"
}