{
    "info": {
        "author": "Andrei-Marius Avram",
        "author_email": "avram.andreimarius@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Intended Audience :: Developers",
            "Intended Audience :: Information Technology",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: MIT License",
            "Operating System :: OS Independent",
            "Programming Language :: Python :: 3",
            "Topic :: Scientific/Engineering :: Artificial Intelligence",
            "Topic :: Scientific/Engineering :: Visualization"
        ],
        "description": "# OpenNNG (Work in progress...)\n\nOpenNNG (Open Neural Network Generator) is a general purpose data generator toolkit that uses TensorFlow 2.0. Supported architectures:\n\n- [variational autoencoder](https://arxiv.org/abs/1312.6114)\n- [generative adversarial network](https://arxiv.org/abs/1406.2661)\n\n## Key features\n\nOpenNNG focuses on modularity to support advanced modeling and training capabilities:\n\n - usage of predefined models\n - creation of custom architectures\n - domain adaptation\n\n## Installation\n\n### Clone repository\n\nIf you want to use OpenNNG as a command line interface where the processes of training, evaluating etc. are all automated, run the following commands:\n\n```\ngit clone https://github.com/avramandrei/OpenNNG.git\npip install -r requirements.txt\n```\n\n### pip\n\nIf you want to use OpenNNG as an API and have more flexibility, install it via pip:\n\n```\npip install opennng\n```\n\n## Usage\n\nOpenNNG requires:\n - Python >= 3.6\n - TensorFlow >= 2.0.0rc0\n - Pillow >=6.1\n\n### Data processing\n\nData must be saved in Numpy `.npy` files. In this example we will use the mnist dataset to generate new images. For this purpose, use \nthe `download.py` script with `mnist` as argument. This command will automatically download mnist (raw and processed) dataset in `data/` directory.\n\n```\npython3 download.py mnist\n```\n\n### Configuration\n\nTo train and generate new samples, a `YAML` configuration file must be provided. [Here](https://github.com/avramandrei/OpenNNG/blob/master/examples/yaml_config/config_docs.yml) is an exhaustive list of all the configuration parameters.\n\n### Train\n\nTo train, run `train.py` with a `YAML` configuration file as parameter.\n\n```\npython3 train.py <path_to_yaml_config_file>\n```\n\nThis script will automatically generate 10 samples that shows how the training process evolves at evrey checkpoint. To disable this functionality, set `generate_train_samples` to `False` in `YAML` configuration file. \n\n| Model | Samples |\n| --- | --- |\n| ConvVAESmall | ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_vae/train_sameple_1.gif?raw=true) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_vae/train_sameple_2.gif?raw=true) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_vae/train_sameple_3.gif?raw=true) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_vae/train_sameple_4.gif?raw=true) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_vae/train_sameple_5.gif?raw=true) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_vae/train_sameple_6.gif?raw=true) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_vae/train_sameple_7.gif?raw=true) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_vae/train_sameple_8.gif?raw=true) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_vae/train_sameple_9.gif?raw=true) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_vae/train_sameple_10.gif?raw=true) |\n| ConvGANSmall | ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_gan/train_sameple_1.gif) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_gan/train_sameple_2.gif) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_gan/train_sameple_3.gif) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_gan/train_sameple_4.gif) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_gan/train_sameple_5.gif) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_gan/train_sameple_6.gif) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_gan/train_sameple_7.gif) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_gan/train_sameple_8.gif) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_gan/train_sameple_9.gif) ![alt text](https://github.com/avramandrei/OpenNNG/blob/master/examples/train_samples/conv_gan/train_sameple_10.gif) |\n\n\n### Generate\n\nTo generate a new sample, run `generate.py` with a `YAML` configuration file as parameter.\n\n```\npython3 generate.py <path_to_yaml_config_file>\n```\n\n\n\n",
        "description_content_type": "text/markdown",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/avramandrei/OpenNNG",
        "keywords": "generative-models tensorflow generative-adversarial-network gan variational-autoencoder vae",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "opennng",
        "package_url": "https://pypi.org/project/opennng/",
        "platform": "",
        "project_url": "https://pypi.org/project/opennng/",
        "project_urls": {
            "Homepage": "https://github.com/avramandrei/OpenNNG"
        },
        "release_url": "https://pypi.org/project/opennng/0.1.8/",
        "requires_dist": [
            "tensorflow (>=2.0.0rc0)",
            "Pillow (>=6.1.0)"
        ],
        "requires_python": "",
        "summary": "OpenNNG is a toolkit that offers an easy interface to generative models.",
        "version": "0.1.8"
    },
    "last_serial": 5750005,
    "releases": {
        "0.1.6": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "bb1d610e533b89f273495f19540b3213",
                    "sha256": "6e9d456cb460a79ea62403f0e0e23583be2aa54f345b81f10b92c08a1507ca50"
                },
                "downloads": -1,
                "filename": "opennng-0.1.6-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "bb1d610e533b89f273495f19540b3213",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 11732,
                "upload_time": "2019-08-29T08:12:42",
                "url": "https://files.pythonhosted.org/packages/b9/ad/c7b281974bc45f68452cac1fc79cd46feddd1698f6bfbd7f55a65ec807d2/opennng-0.1.6-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "0ffff690743fc185c29fcd13368ec561",
                    "sha256": "72336e56eedade8b1012ba6d546d1afb4978c01e69ba47c1457665b14b6696f7"
                },
                "downloads": -1,
                "filename": "opennng-0.1.6.tar.gz",
                "has_sig": false,
                "md5_digest": "0ffff690743fc185c29fcd13368ec561",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7444,
                "upload_time": "2019-08-29T08:12:44",
                "url": "https://files.pythonhosted.org/packages/29/16/13ce5cb5078f4fc5cb10728f0a290ed88a400a208a0e00e1d92cdaa9cefc/opennng-0.1.6.tar.gz"
            }
        ],
        "0.1.7": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "c84ecba68a2c2c4280e71bbc8f816719",
                    "sha256": "28285bace10f54643dcf74514474c824ede8bd27583d4e8b968c1c982331e826"
                },
                "downloads": -1,
                "filename": "opennng-0.1.7-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "c84ecba68a2c2c4280e71bbc8f816719",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 11731,
                "upload_time": "2019-08-29T08:17:46",
                "url": "https://files.pythonhosted.org/packages/6a/9c/b564166d58d3037e070ea1ca7a51d93ee36250b7d2feb09e49bdd611422f/opennng-0.1.7-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "837433051ddf85717d2353a20bae19d6",
                    "sha256": "124f2ace23756a731ed35b253e925898b8ac88d59c281d7f1f962754fcfee32d"
                },
                "downloads": -1,
                "filename": "opennng-0.1.7.tar.gz",
                "has_sig": false,
                "md5_digest": "837433051ddf85717d2353a20bae19d6",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7446,
                "upload_time": "2019-08-29T08:17:49",
                "url": "https://files.pythonhosted.org/packages/af/67/475f6e3f6b05b10b5a05c138034a880cd0bf82247c07b84ae321a28de06c/opennng-0.1.7.tar.gz"
            }
        ],
        "0.1.8": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "f33de83de4d2e6580b04b4c9847f462b",
                    "sha256": "6ee0f662fd5079f9e0a9ac94d747ab9375c338b0c84ebf43216e7991777e3ffa"
                },
                "downloads": -1,
                "filename": "opennng-0.1.8-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "f33de83de4d2e6580b04b4c9847f462b",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 11727,
                "upload_time": "2019-08-29T08:23:13",
                "url": "https://files.pythonhosted.org/packages/55/88/799ae27833c87c722eff74deb9bf416426a20c6f0f6823361957f426b9ee/opennng-0.1.8-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "720698597ba18e4ce836b032387b23a9",
                    "sha256": "3385466cc335efabde7371c4682732dd98f3d198c369932ca681ae97c8da7d02"
                },
                "downloads": -1,
                "filename": "opennng-0.1.8.tar.gz",
                "has_sig": false,
                "md5_digest": "720698597ba18e4ce836b032387b23a9",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 7438,
                "upload_time": "2019-08-29T08:23:14",
                "url": "https://files.pythonhosted.org/packages/52/4e/a1154d29df9557f7044348b2a56a532bbe0ec6171a24a1e77e12ac79cf0e/opennng-0.1.8.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "f33de83de4d2e6580b04b4c9847f462b",
                "sha256": "6ee0f662fd5079f9e0a9ac94d747ab9375c338b0c84ebf43216e7991777e3ffa"
            },
            "downloads": -1,
            "filename": "opennng-0.1.8-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "f33de83de4d2e6580b04b4c9847f462b",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": null,
            "size": 11727,
            "upload_time": "2019-08-29T08:23:13",
            "url": "https://files.pythonhosted.org/packages/55/88/799ae27833c87c722eff74deb9bf416426a20c6f0f6823361957f426b9ee/opennng-0.1.8-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "720698597ba18e4ce836b032387b23a9",
                "sha256": "3385466cc335efabde7371c4682732dd98f3d198c369932ca681ae97c8da7d02"
            },
            "downloads": -1,
            "filename": "opennng-0.1.8.tar.gz",
            "has_sig": false,
            "md5_digest": "720698597ba18e4ce836b032387b23a9",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 7438,
            "upload_time": "2019-08-29T08:23:14",
            "url": "https://files.pythonhosted.org/packages/52/4e/a1154d29df9557f7044348b2a56a532bbe0ec6171a24a1e77e12ac79cf0e/opennng-0.1.8.tar.gz"
        }
    ]
}