{
    "info": {
        "author": "Matthias K\u00fcmmerer",
        "author_email": "matthias.kuemmerer@bethgelab.org",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Intended Audience :: Developers",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: MIT License",
            "Programming Language :: Python :: 2.7",
            "Programming Language :: Python :: 3",
            "Programming Language :: Python :: 3.5",
            "Programming Language :: Python :: 3.6",
            "Topic :: Scientific/Engineering"
        ],
        "description": "Pysaliency\n==========\n\nPysaliency is a python package for saliency modelling. It aims at providing a unified interface\nto both the traditional saliency maps used in saliency modeling as well as probabilistic saliency\nmodels.\n\nPysaliency can evaluate most commonly used saliency metrics, including AUC, sAUC, NSS, CC\nimage-based KL divergence, fixation based KL divergence and SIM for saliency map models and\nlog likelihoods and information gain for probabilistic models.\n\nPysaliency provides several important datasets:\n\n* MIT1003\n* MIT300\n* CAT2000\n* Toronto\n* Koehler\n* iSUN\n* SALICON (both the 2015 and the 2017 edition and each with both the original mouse traces and the inferred fixations)\n* FIGRIM\n* OSIE\n* NUSEF (the part with public images)\n\nand some influential models:\n* AIM\n* SUN\n* ContextAwareSaliency\n* BMS\n* GBVS\n* GBVSIttiKoch\n* Judd\n* IttiKoch\n* RARE2012\n* CovSal\n\n\nThese models are using the original code which is often matlab.\nTherefore, a matlab licence is required to make use of these models, although quite some of them\nwork with octave, too (see below).\n\n\nInstallation\n------------\n\nYou can install pysaliency from pypi via\n\n    pip install pysaliency\n\n\nQuickstart\n----------\n\n    import pysaliency\n    \n    dataset_location = 'datasets'\n    model_location = 'models'\n\n    mit_stimuli, mit_fixations = pysaliency.external_datasets.get_mit1003(location=dataset_location)\n    aim = pysaliency.AIM(location=model_location)\n    saliency_map = aim.saliency_map(mit_stimuli.stimuli[0])\n\n    plt.imshow(saliency_map)\n\n\n    auc = aim.AUC(mit_stimuli, mit_fixations)\n\nIf you already have saliency maps for some dataset, you can import them into pysaliency easily:\n\n    my_model = pysaliency.SaliencyMapModelFromDirectory(mit_stimuli, '/path/to/my/saliency_maps')\n    auc = my_model.AUC(mit_stimuli, mit_fixations)\n\n\nUsing Octave\n------------\n\npysaliency will fall back to octave if no matlab is installed.\nSome models might work with octave, e.g. AIM and GBVSIttiKoch. In Debian/Ubuntu you need to install\n`octave`, `octave-image`, `octave-statistics`, `liboctave-dev`.\n\nThese models and dataset seem to work with octave:\n\n- models\n  - AIM\n  - GBVSIttiKoch\n- datasets\n  - Toronto\n  - MIT1003\n  - MIT300\n  - SALICON\n\nDependencies\n-----------\n\nThe Judd Model needs some libraries to work. In ubuntu/debian you need to install these packages:\n`libopencv-core-dev, libopencv-flann-dev, libopencv-imgproc-dev, libopencv-photo-dev, libopencv-video-dev, libopencv-features2d-dev, libopencv-objdetect-dev, libopencv-calib3d-dev, libopencv-ml-dev, opencv2/contrib/contrib.hpp`",
        "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/matthiask/pysaliency",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "pysaliency",
        "package_url": "https://pypi.org/project/pysaliency/",
        "platform": "",
        "project_url": "https://pypi.org/project/pysaliency/",
        "project_urls": {
            "Homepage": "https://github.com/matthiask/pysaliency"
        },
        "release_url": "https://pypi.org/project/pysaliency/0.2.3/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "python library to develop, evaluate and benchmark saliency models",
        "version": "0.2.3"
    },
    "last_serial": 4520872,
    "releases": {
        "0.2.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "a6d9919823081b53edf6646a6a38b848",
                    "sha256": "98ec293b83899727e4488febfd088311d1b6db5f6a8f57d6341cdf13ac9ad525"
                },
                "downloads": -1,
                "filename": "pysaliency-0.2.0.tar.gz",
                "has_sig": false,
                "md5_digest": "a6d9919823081b53edf6646a6a38b848",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 138151,
                "upload_time": "2018-10-07T11:09:26",
                "url": "https://files.pythonhosted.org/packages/4f/f8/e4cdd8d8f31a29293ff32dae5b8442aba10f95d813596052d5899fe5c842/pysaliency-0.2.0.tar.gz"
            }
        ],
        "0.2.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "d3dca6eb78b25a2908cf81c17cc9336e",
                    "sha256": "a213e74c93493f8de3993e7cafd7747a026f74f9fd4eac5aca09946a864f5d68"
                },
                "downloads": -1,
                "filename": "pysaliency-0.2.3.tar.gz",
                "has_sig": false,
                "md5_digest": "d3dca6eb78b25a2908cf81c17cc9336e",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 138243,
                "upload_time": "2018-11-23T14:45:27",
                "url": "https://files.pythonhosted.org/packages/b2/02/bfc186ddb31f5ff3df5ba598b4bba5a9c0b14fbcd2789a8f55f7b87ef4ad/pysaliency-0.2.3.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "d3dca6eb78b25a2908cf81c17cc9336e",
                "sha256": "a213e74c93493f8de3993e7cafd7747a026f74f9fd4eac5aca09946a864f5d68"
            },
            "downloads": -1,
            "filename": "pysaliency-0.2.3.tar.gz",
            "has_sig": false,
            "md5_digest": "d3dca6eb78b25a2908cf81c17cc9336e",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 138243,
            "upload_time": "2018-11-23T14:45:27",
            "url": "https://files.pythonhosted.org/packages/b2/02/bfc186ddb31f5ff3df5ba598b4bba5a9c0b14fbcd2789a8f55f7b87ef4ad/pysaliency-0.2.3.tar.gz"
        }
    ]
}