{
    "info": {
        "author": "sshuair",
        "author_email": "sshuair@gmail.com",
        "bugtrack_url": null,
        "classifiers": [],
        "description": "# torchvision-enhance\n\ntorchvision-enhance is used to enhance the offical PyTorch vision library torchvision. Here is the enhanced parts:\n- support multi-channel(> 4 channels, e.g. 8 channels) images\n- support 16-bit TIF file \n- more easier to semantic segmentation transform\n\n\n\n## Support transforms\n- RandomFlip\n- RandomVFlip\n- RandomHFlip\n- RandomRotate\n- RandomShift\n- RandomCrop\n- CenterCrop\n- Resize\n- Pad\n- GaussianBlur\n- PieceTransform\n- Lambda\n- ToTensor\n- Normalize\n\n## Install\n```\npip install torchvision-enhance\n```  \n\nor  install from the source\n\n```\ngit clone \npip install -r requirements.txt\npython setup.py install\n```\n## Dependencies\n- numpy\n- scipy\n- Pillow\n- PyTorch\n- opencv\n- scikit-image\n\n## Usage\nFor more useage, check out the [example-classification.py](./test/example-classification.py) and [example-segmentation.py](./test/example-segmentation.py)\n\n``` python\nfrom torchvision_x.datasets import image_loader\nfrom torchvision_x.transforms import transforms_seg,functional\n\ntransform = transforms_seg.SegCompose([\n#     transforms_seg.SegFlip(),\n    transforms_seg.SegVFlip(), \n    # transforms_seg.SegHFlip(),\n    # transforms_seg.SegRandomFlip(),\n    # transforms_seg.SegRandomRotate(90),\n    # transforms_seg.SegRandomShift(40),\n    # transforms_seg.SegRandomCrop((256,256)),\n    # transforms_seg.SegCenterCrop(224),\n    # transforms_seg.SegResize(224),\n    # transforms_seg.SegPad(20),\n    # transforms_seg.SegNoise(dtype='uint16', var=0.001),  #TODO\n    # transforms_seg.SegGaussianBlur(sigma=2, dtype='uint8', multichannel=False),\n    # transforms_seg.SegPieceTransform(),\n#     transforms_seg.SegLambda(lambda x: functional.to_tensor(x))\n    transforms_seg.SegToTensor(),\n    transforms_seg.SegNormalize((0.5,0.5,0.5),(0.5,0.5,0.5)),\n    ])\n\ntrainset = image_loader.SemanticSegmentationLoader(\n    rootdir='sample-data/', lstpath='sample-data/segmentation_jpg.lst',\n    filetype='jpg', transform=transform,\n    )\ntrainloader = DataLoader(dataset=trainset,batch_size=batch_size,shuffle=False)\n\nfor step, (inputs, targets) in enumerate(trainloader):\n    print('batch: {} ........'.format(step))\n    print(type(inputs), inputs.shape)\n    print(type(targets), targets.shape)\n```\n\n## TODO\n- Noise\n",
        "description_content_type": "",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/sshuair/torchvision-enhance",
        "keywords": "pytorch",
        "license": "",
        "maintainer": "",
        "maintainer_email": "",
        "name": "torchvision-enhance",
        "package_url": "https://pypi.org/project/torchvision-enhance/",
        "platform": "",
        "project_url": "https://pypi.org/project/torchvision-enhance/",
        "project_urls": {
            "Homepage": "https://github.com/sshuair/torchvision-enhance"
        },
        "release_url": "https://pypi.org/project/torchvision-enhance/0.1.3/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "Enhance torchvision for multi-channel images, 16-bit image, segmentation...",
        "version": "0.1.3"
    },
    "last_serial": 3783182,
    "releases": {
        "0.1.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "d93799cc42829aec7938ec961b28332d",
                    "sha256": "e8c6c32f9992fce81d013f62f06475099b024d9d5b264f254a0bf08a778b3064"
                },
                "downloads": -1,
                "filename": "torchvision-enhance-0.1.1.tar.gz",
                "has_sig": false,
                "md5_digest": "d93799cc42829aec7938ec961b28332d",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 13270,
                "upload_time": "2018-02-16T13:27:12",
                "url": "https://files.pythonhosted.org/packages/6f/55/a094975ef8cd176fc1fcee1b7d689f19e4a6f00c4ba72f4acd69850c92b1/torchvision-enhance-0.1.1.tar.gz"
            }
        ],
        "0.1.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "04cce8906b42f2093637c2142aea9b67",
                    "sha256": "677ec999d53f20ba04f822d22c3ea04cd733bb7ca757a8b9d9cf106f4344400f"
                },
                "downloads": -1,
                "filename": "torchvision-enhance-0.1.2.tar.gz",
                "has_sig": false,
                "md5_digest": "04cce8906b42f2093637c2142aea9b67",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 13285,
                "upload_time": "2018-02-23T06:42:25",
                "url": "https://files.pythonhosted.org/packages/40/09/c8877848c39186b151c9c46acb9ad3d3fb4292ec27c895a5de0786e46178/torchvision-enhance-0.1.2.tar.gz"
            }
        ],
        "0.1.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "a0e6ad8f987525d69a027e9e6529d50e",
                    "sha256": "3f03d638216b33d299d4238fb8f9a5c9968373c33c651e9f8620fd1bf0980eee"
                },
                "downloads": -1,
                "filename": "torchvision-enhance-0.1.3.tar.gz",
                "has_sig": false,
                "md5_digest": "a0e6ad8f987525d69a027e9e6529d50e",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 13449,
                "upload_time": "2018-04-20T07:08:30",
                "url": "https://files.pythonhosted.org/packages/a4/ae/7e1ac9784927b4ae5174c6f6533acacfa964982c30f77cd379ebfbaa7fd6/torchvision-enhance-0.1.3.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "a0e6ad8f987525d69a027e9e6529d50e",
                "sha256": "3f03d638216b33d299d4238fb8f9a5c9968373c33c651e9f8620fd1bf0980eee"
            },
            "downloads": -1,
            "filename": "torchvision-enhance-0.1.3.tar.gz",
            "has_sig": false,
            "md5_digest": "a0e6ad8f987525d69a027e9e6529d50e",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 13449,
            "upload_time": "2018-04-20T07:08:30",
            "url": "https://files.pythonhosted.org/packages/a4/ae/7e1ac9784927b4ae5174c6f6533acacfa964982c30f77cd379ebfbaa7fd6/torchvision-enhance-0.1.3.tar.gz"
        }
    ]
}