{
    "info": {
        "author": "Meet Pragnesh Shah",
        "author_email": "meetshah1995@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 4 - Beta",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: MIT License",
            "Programming Language :: Python :: 2.7",
            "Topic :: Scientific/Engineering :: Artificial Intelligence"
        ],
        "description": "pytorch-semseg\n==============\n\n|license|\n\nSemantic Segmentation Algorithms Implemented in PyTorch\n-------------------------------------------------------\n\nThis repository aims at mirroring popular semantic segmentation\narchitectures in PyTorch.\n\n.. raw:: html\n\n   <p align=\"center\">\n\n.. raw:: html\n\n   </p>\n\nNetworks implemented\n~~~~~~~~~~~~~~~~~~~~\n\n-  `PSPNet <https://arxiv.org/abs/1612.01105>`__ - With support for\n   loading pretrained models w/o caffe dependency\n-  `FRRN <https://arxiv.org/abs/1611.08323>`__ - Model A and B\n-  `FCN <https://arxiv.org/abs/1411.4038>`__ - All 1 (FCN32s), 2\n   (FCN16s) and 3 (FCN8s) stream variants\n-  `U-Net <https://arxiv.org/abs/1505.04597>`__ - With optional\n   deconvolution and batchnorm\n-  `Link-Net <https://codeac29.github.io/projects/linknet/>`__ - With\n   multiple resnet backends\n-  `Segnet <https://arxiv.org/abs/1511.00561>`__ - With Unpooling using\n   Maxpool indices\n\nUpcoming\n^^^^^^^^\n\n-  `E-Net <https://arxiv.org/abs/1606.02147>`__\n-  `RefineNet <https://arxiv.org/abs/1611.06612>`__\n\nDataLoaders implemented\n~~~~~~~~~~~~~~~~~~~~~~~\n\n-  `CamVid <http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/>`__\n-  `Pascal\n   VOC <http://host.robots.ox.ac.uk/pascal/VOC/voc2012/segexamples/index.html>`__\n-  `ADE20K <http://groups.csail.mit.edu/vision/datasets/ADE20K/>`__\n-  `MIT Scene Parsing\n   Benchmark <http://data.csail.mit.edu/places/ADEchallenge/ADEChallengeData2016.zip>`__\n-  `Cityscapes <https://www.cityscapes-dataset.com/>`__\n\nUpcoming\n^^^^^^^^\n\n-  `NYUDv2 <http://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html>`__\n-  `Sun-RGBD <http://rgbd.cs.princeton.edu/>`__\n-  `MS COCO <http://mscoco.org/>`__\n\nRequirements\n~~~~~~~~~~~~\n\n-  pytorch >=0.3.0\n-  torchvision ==0.2.0\n-  visdom >=1.0.1 (for loss and results visualization)\n-  scipy\n-  tqdm\n\nOne-line installation\n^^^^^^^^^^^^^^^^^^^^^\n\n``pip install -r requirements.txt``\n\nData\n~~~~\n\n-  Download data for desired dataset(s) from list of URLs\n   `here <https://meetshah1995.github.io/semantic-segmentation/deep-learning/pytorch/visdom/2017/06/01/semantic-segmentation-over-the-years.html#sec_datasets>`__.\n-  Extract the zip / tar and modify the path appropriately in\n   ``config.json``\n\nUsage\n~~~~~\n\nLaunch `visdom <https://github.com/facebookresearch/visdom#launch>`__ by\nrunning (in a separate terminal window)\n\n::\n\n    python -m visdom.server\n\n**To train the model :**\n\n::\n\n    python train.py [-h] [--arch [ARCH]] [--dataset [DATASET]]\n                    [--img_rows [IMG_ROWS]] [--img_cols [IMG_COLS]]\n                    [--n_epoch [N_EPOCH]] [--batch_size [BATCH_SIZE]]\n                    [--l_rate [L_RATE]] [--feature_scale [FEATURE_SCALE]]\n                    [--visdom [VISDOM]]\n\n      --arch           Architecture to use ['fcn8s, unet, segnet etc']\n      --dataset        Dataset to use ['pascal, camvid, ade20k etc']\n      --img_rows       Height of the input image\n      --img_cols       Width of the input image\n      --n_epoch        # of the epochs\n      --batch_size     Batch Size\n      --l_rate         Learning Rate\n      --feature_scale  Divider for # of features to use\n      --visdom         Show visualization(s) on visdom | False by default\n\n**To validate the model :**\n\n::\n\n    python validate.py [-h] [--model_path [MODEL_PATH]] [--dataset [DATASET]]\n                       [--img_rows [IMG_ROWS]] [--img_cols [IMG_COLS]]\n                       [--batch_size [BATCH_SIZE]] [--split [SPLIT]]\n\n      --model_path   Path to the saved model\n      --dataset      Dataset to use ['pascal, camvid, ade20k etc']\n      --img_rows     Height of the input image\n      --img_cols     Width of the input image\n      --batch_size   Batch Size\n      --split        Split of dataset to validate on\n\n**To test the model w.r.t. a dataset on custom images(s):**\n\n::\n\n    python test.py [-h] [--model_path [MODEL_PATH]] [--dataset [DATASET]]\n                   [--dcrf [DCRF]] [--img_path [IMG_PATH]] [--out_path [OUT_PATH]]\n     \n      --model_path          Path to the saved model\n      --dataset             Dataset to use ['pascal, camvid, ade20k etc']\n      --dcrf                Enable DenseCRF based post-processing\n      --img_path            Path of the input image\n      --out_path            Path of the output segmap\n\n.. |license| image:: https://img.shields.io/github/license/mashape/apistatus.svg\n   :target: https://github.com/meetshah1995/pytorch-semseg/blob/master/LICENSE",
        "description_content_type": null,
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/meetshah1995/pytorch-semseg",
        "keywords": "semantic-segmentation,fully-convolutional-networks,deep-learning,pytorch",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "pytorch-semseg",
        "package_url": "https://pypi.org/project/pytorch-semseg/",
        "platform": "",
        "project_url": "https://pypi.org/project/pytorch-semseg/",
        "project_urls": {
            "Homepage": "https://github.com/meetshah1995/pytorch-semseg"
        },
        "release_url": "https://pypi.org/project/pytorch-semseg/0.1.2/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "Semantic Segmentation Architectures implemented in PyTorch",
        "version": "0.1.2"
    },
    "last_serial": 3565725,
    "releases": {
        "0.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "3b935b6e61c7b10de3db93db596175bc",
                    "sha256": "ba41ef16d1a5fefd311518f7176bf9ee58b2f1eb2f51aee2f89b7d643444fe7c"
                },
                "downloads": -1,
                "filename": "pytorch-semseg-0.1.tar.gz",
                "has_sig": false,
                "md5_digest": "3b935b6e61c7b10de3db93db596175bc",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 30042,
                "upload_time": "2018-02-09T00:19:25",
                "url": "https://files.pythonhosted.org/packages/a3/2e/1876447e32fc8e4e9bc3c4af0c6cdb96660ea713043dc7b41d13f6d4fcf0/pytorch-semseg-0.1.tar.gz"
            }
        ],
        "0.1.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "7dfd9a676fa8cab713a6dc74f44febb4",
                    "sha256": "c90991be4bb13501077df2f58274b80fced5dfb89a13accc912f7db1a00dc5b0"
                },
                "downloads": -1,
                "filename": "pytorch-semseg-0.1.1.tar.gz",
                "has_sig": false,
                "md5_digest": "7dfd9a676fa8cab713a6dc74f44febb4",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 32197,
                "upload_time": "2018-02-09T00:26:43",
                "url": "https://files.pythonhosted.org/packages/dd/2b/ad48be17d47d35e7f960ab0b03e1387d7f7c6d246c52b4931f36c1ad5729/pytorch-semseg-0.1.1.tar.gz"
            }
        ],
        "0.1.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "4d1e4e9bab756e85b39a2443b11506e7",
                    "sha256": "2df65b7a17ff4a100c8d1e0d0e90af26897d4fdedcb123fe2bc402e5ea89a41c"
                },
                "downloads": -1,
                "filename": "pytorch-semseg-0.1.2.tar.gz",
                "has_sig": false,
                "md5_digest": "4d1e4e9bab756e85b39a2443b11506e7",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 32425,
                "upload_time": "2018-02-09T00:28:18",
                "url": "https://files.pythonhosted.org/packages/f3/6a/c70e875a14b3cc9839a3d27431f471e62a111c47e9e14ce88e273954f383/pytorch-semseg-0.1.2.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "4d1e4e9bab756e85b39a2443b11506e7",
                "sha256": "2df65b7a17ff4a100c8d1e0d0e90af26897d4fdedcb123fe2bc402e5ea89a41c"
            },
            "downloads": -1,
            "filename": "pytorch-semseg-0.1.2.tar.gz",
            "has_sig": false,
            "md5_digest": "4d1e4e9bab756e85b39a2443b11506e7",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 32425,
            "upload_time": "2018-02-09T00:28:18",
            "url": "https://files.pythonhosted.org/packages/f3/6a/c70e875a14b3cc9839a3d27431f471e62a111c47e9e14ce88e273954f383/pytorch-semseg-0.1.2.tar.gz"
        }
    ]
}