{
    "info": {
        "author": "Tristan Deleu",
        "author_email": "tristan.deleu@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 5 - Production/Stable",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: MIT License",
            "Programming Language :: Python :: 3",
            "Programming Language :: Python :: 3.5",
            "Programming Language :: Python :: 3.6",
            "Programming Language :: Python :: 3.7",
            "Topic :: Scientific/Engineering :: Artificial Intelligence"
        ],
        "description": "# Torchmeta\n[![PyPI](https://img.shields.io/pypi/v/torchmeta)](https://pypi.org/project/torchmeta/) [![Build Status](https://travis-ci.com/tristandeleu/pytorch-meta.svg?branch=master)](https://travis-ci.com/tristandeleu/pytorch-meta) [![Documentation](https://img.shields.io/badge/docs-torchmeta-blue)](https://tristandeleu.github.io/pytorch-meta/)\n\nA collection of extensions and data-loaders for few-shot learning & meta-learning in [PyTorch](https://pytorch.org/). Torchmeta contains popular meta-learning benchmarks, fully compatible with both [`torchvision`](https://pytorch.org/docs/stable/torchvision/index.html) and PyTorch's [`DataLoader`](https://pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader).\n\n#### Features\n  - A unified interface for both few-shot classification and regression problems, to allow easy benchmarking on multiple problems and reproducibility.\n  - Helper functions for some popular problems, with default arguments from the literature.\n  - An thin extension of PyTorch's [`Module`](https://pytorch.org/docs/stable/nn.html#torch.nn.Module), called `MetaModule`, that simplifies the creation of certain meta-learning models (e.g. gradient based meta-learning methods). See the [MAML example](examples/maml) for an example using `MetaModule`.\n\n#### Datasets available\n  - **Few-shot regression** (toy problems):\n    - Sine waves ([Finn et al., 2017](https://arxiv.org/abs/1703.03400))\n    - Harmonic functions ([Lacoste et al., 2018](https://arxiv.org/abs/1806.07528))\n    - Sinusoid & lines ([Finn et al., 2018](https://arxiv.org/abs/1806.02817))\n  - **Few-shot classification** (image classification):\n    - Omniglot ([Lake et al., 2015](http://www.sciencemag.org/content/350/6266/1332.short)[, 2019](https://arxiv.org/abs/1902.03477))\n    - Mini-ImageNet ([Vinyals et al., 2016](https://arxiv.org/abs/1606.04080), [Ravi et al., 2017](https://openreview.net/forum?id=rJY0-Kcll))\n    - Tiered-ImageNet ([Ren et al., 2018](https://arxiv.org/abs/1803.00676))\n    - CIFAR-FS ([Bertinetto et al., 2018](https://arxiv.org/abs/1805.08136))\n    - Fewshot-CIFAR100 ([Oreshkin et al., 2018](https://arxiv.org/abs/1805.10123))\n\n## Installation\nYou can install Torchmeta either using Python's package manager pip, or from source. To avoid any conflict with your existing Python setup, it is suggested to work in a virtual environment with [`virtualenv`](https://docs.python-guide.org/dev/virtualenvs/). To install `virtualenv`:\n```bash\npip install --upgrade virtualenv\nvirtualenv venv\nsource venv/bin/activate\n```\n\n#### Requirements\n - Python 3.5 or above\n - PyTorch 1.2\n - Torchvision 0.4\n\n#### Using pip\nThis is the recommended way to install Torchmeta:\n```bash\npip install torchmeta\n```\n\n#### From source\nYou can also install Torchmeta from source. This is recommended if you want to contribute to Torchmeta.\n```bash\ngit clone https://github.com/tristandeleu/pytorch-meta.git\ncd pytorch-meta\npython setup.py install\n```\n\n## Example\n\n#### Minimal example\nThis minimal example below shows how to create a dataloader for the 5-shot 5-way Omniglot dataset with Torchmeta. The dataloader loads a batch of randomly generated tasks, and all the samples are concatenated into a single tensor. For more examples, check the [examples](examples/) folder.\n```python\nfrom torchmeta.datasets.helpers import omniglot\nfrom torchmeta.utils.data import BatchMetaDataLoader\n\ndataset = omniglot(\"data\", ways=5, shots=5, test_shots=15, meta_train=True, download=True)\ndataloader = BatchMetaDataLoader(dataset, batch_size=16, num_workers=4)\n\nfor batch in dataloader:\n    train_inputs, train_targets = batch[\"train\"]\n    print('Train inputs shape: {0}'.format(train_inputs.shape))    # (16, 25, 1, 28, 28)\n    print('Train targets shape: {0}'.format(train_targets.shape))  # (16, 25)\n\n    test_inputs, test_targets = batch[\"test\"]\n    print('Test inputs shape: {0}'.format(test_inputs.shape))      # (16, 75, 1, 28, 28)\n    print('Test targets shape: {0}'.format(test_targets.shape))    # (16, 75)\n```\n\n#### Advanced example\nHelper functions are only avaiable for some of the datasets available. However, all of them are available through the unified interface provided by Torchmeta. The variable `dataset` defined above is equivalent to the following\n```python\nfrom torchmeta.datasets import Omniglot\nfrom torchmeta.transforms import Categorical, ClassSplitter, Rotation\nfrom torchvision.transforms import Compose, Resize, ToTensor\nfrom torchmeta.utils.data import BatchMetaDataLoader\n\ndataset = Omniglot(\"data\",\n                   # Number of ways\n                   num_classes_per_task=5,\n                   # Resize the images to 28x28 and converts them to PyTorch tensors (from Torchvision)\n                   transform=Compose([Resize(28), ToTensor()]),\n                   # Transform the labels to integers (e.g. (\"Glagolitic/character01\", \"Sanskrit/character14\", ...) to (0, 1, ...))\n                   target_transform=Categorical(num_classes=5),\n                   # Creates new virtual classes with rotated versions of the images (from Santoro et al., 2016)\n                   class_augmentations=[Rotation([90, 180, 270])],\n                   meta_train=True,\n                   download=True)\ndataset = ClassSplitter(dataset, shuffle=True, num_train_per_class=5, num_test_per_class=15)\ndataloader = BatchMetaDataLoader(dataset, batch_size=16, num_workers=4)\n```\nNote that the dataloader, receiving the dataset, remains the same.\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/tristandeleu/pytorch-meta",
        "keywords": "meta-learning,pytorch,few-shot,few-shot learning",
        "license": "",
        "maintainer": "",
        "maintainer_email": "",
        "name": "torchmeta",
        "package_url": "https://pypi.org/project/torchmeta/",
        "platform": "",
        "project_url": "https://pypi.org/project/torchmeta/",
        "project_urls": {
            "Homepage": "https://github.com/tristandeleu/pytorch-meta"
        },
        "release_url": "https://pypi.org/project/torchmeta/1.1.1/",
        "requires_dist": [
            "torch (<1.3.0,>=1.2.0)",
            "torchvision (<0.5.0,>=0.4.0)",
            "numpy (>=1.14.0)",
            "Pillow (>=5.0.0)",
            "h5py (~=2.9.0)",
            "tqdm (>=4.0.0)",
            "requests",
            "pandas (~=0.24.0) ; extra == 'tcga'",
            "academictorrents (~=2.1.0) ; extra == 'tcga'",
            "six (~=1.11.0) ; extra == 'tcga'"
        ],
        "requires_python": "",
        "summary": "Dataloaders for meta-learning in Pytorch",
        "version": "1.1.1"
    },
    "last_serial": 5838032,
    "releases": {
        "1.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "95c0dbe6c3a0446b20184e3ccc8ef469",
                    "sha256": "e3870c06b07b866356ad2a8f298639271ada6bf17830e1ea401f5136ac6495e7"
                },
                "downloads": -1,
                "filename": "torchmeta-1.1.0-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "95c0dbe6c3a0446b20184e3ccc8ef469",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 133039,
                "upload_time": "2019-09-16T12:59:29",
                "url": "https://files.pythonhosted.org/packages/42/6f/f80815de042a9e7d46b98f0c0921c4ddd5ad64137ab5bccd49e9833a743e/torchmeta-1.1.0-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "2e64ef67b20f646fad57a0c5e9c05aae",
                    "sha256": "8440e42f800409e589e3bc5f72da11156b4eda8a9c454bc55f611821e68f666f"
                },
                "downloads": -1,
                "filename": "torchmeta-1.1.0.tar.gz",
                "has_sig": false,
                "md5_digest": "2e64ef67b20f646fad57a0c5e9c05aae",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 108065,
                "upload_time": "2019-09-16T12:59:31",
                "url": "https://files.pythonhosted.org/packages/2c/ab/14c6aa941bfb943cdcfd8c336e5947eef6e8c65de7523d13eab446d91be0/torchmeta-1.1.0.tar.gz"
            }
        ],
        "1.1.0rc1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "162e3d6772093cc43743e226155ebdc0",
                    "sha256": "711b8cf23d00c262ab7abb7f69669c903203d1031a738c3510e01344d576e6ad"
                },
                "downloads": -1,
                "filename": "torchmeta-1.1.0rc1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "162e3d6772093cc43743e226155ebdc0",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 43348,
                "upload_time": "2019-08-16T10:40:49",
                "url": "https://files.pythonhosted.org/packages/d3/f4/6394a464a48d8f657533f34dfa2f8217edd6a92f55fc274981dfdb3f2dde/torchmeta-1.1.0rc1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "90fb65cebe22f5df32e8e59b10f9bb6e",
                    "sha256": "6b602684c300fcaec6a92a0c4a8f89a07310e4506dd93524967d2e46c35a25af"
                },
                "downloads": -1,
                "filename": "torchmeta-1.1.0rc1.tar.gz",
                "has_sig": false,
                "md5_digest": "90fb65cebe22f5df32e8e59b10f9bb6e",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 104261,
                "upload_time": "2019-08-16T10:24:34",
                "url": "https://files.pythonhosted.org/packages/e1/49/5a937be6081a0776c4b0e1978d1ae42aecb1744cf30aaeb60d6d27a0b9df/torchmeta-1.1.0rc1.tar.gz"
            }
        ],
        "1.1.0rc2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "32d8dd96ab883ac944cf6ad774158ef3",
                    "sha256": "ae54eb36c144c39e39253254d3a1a82662e063cc89d3ed02c0e1161fefaf9f21"
                },
                "downloads": -1,
                "filename": "torchmeta-1.1.0rc2-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "32d8dd96ab883ac944cf6ad774158ef3",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 129708,
                "upload_time": "2019-09-16T08:44:44",
                "url": "https://files.pythonhosted.org/packages/0b/d9/c07c041950869b933372beaf67a701c6f7b2d68091c649e65c365518c6ba/torchmeta-1.1.0rc2-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "80736953eacb08f8ca6919456488eeb3",
                    "sha256": "f53dba3b453e1d238be21539208585540b5046d0c38964f6907a9cb622df18b8"
                },
                "downloads": -1,
                "filename": "torchmeta-1.1.0rc2.tar.gz",
                "has_sig": false,
                "md5_digest": "80736953eacb08f8ca6919456488eeb3",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 105820,
                "upload_time": "2019-09-16T08:44:46",
                "url": "https://files.pythonhosted.org/packages/51/73/d250a3c5a5d90aed9bee806e5afbe0f4334d89e8ee91c3af6bd8e75a947c/torchmeta-1.1.0rc2.tar.gz"
            }
        ],
        "1.1.0rc8": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "8a0f9ab2cac29425d8394cb5cb4b9aa2",
                    "sha256": "56f09aa11281d8eb94a9dfc91b7f3ff41412f71ecb9ad2a0785ea96e685b9538"
                },
                "downloads": -1,
                "filename": "torchmeta-1.1.0rc8-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "8a0f9ab2cac29425d8394cb5cb4b9aa2",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 132671,
                "upload_time": "2019-09-16T12:02:43",
                "url": "https://files.pythonhosted.org/packages/d7/cd/bb7f6472f08c27968249c87f0423e56409940112261aca9f048c8d270199/torchmeta-1.1.0rc8-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "6f7f20cd5d56b1dc27e73c4e701e2508",
                    "sha256": "8f90cdbd4c064ae1b4f350165f800429a88df1c1464ab99037fd8a137a9e9328"
                },
                "downloads": -1,
                "filename": "torchmeta-1.1.0rc8.tar.gz",
                "has_sig": false,
                "md5_digest": "6f7f20cd5d56b1dc27e73c4e701e2508",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 107733,
                "upload_time": "2019-09-16T12:02:45",
                "url": "https://files.pythonhosted.org/packages/9b/3e/f4473d9b5bbcff50027ab4b79e89c373e44ece73ef0c3cd335539b466fe8/torchmeta-1.1.0rc8.tar.gz"
            }
        ],
        "1.1.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "80c0dd6856d79f18204e38dfc402e228",
                    "sha256": "76a605f34eceef68404c784d21e01cb462879f8b5244e270a49e0826e477b204"
                },
                "downloads": -1,
                "filename": "torchmeta-1.1.1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "80c0dd6856d79f18204e38dfc402e228",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 133052,
                "upload_time": "2019-09-16T20:09:48",
                "url": "https://files.pythonhosted.org/packages/a9/15/007c1f2527f50fa25844afec7ca05f66be30bbc9a85a36d9c3e722a32705/torchmeta-1.1.1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "e1fb15af43cd4083a334d81e1a0651b2",
                    "sha256": "3ecb2a55c507dc091cb33d5318c31663125f1c5f459f1ea213b37d26bd00a4c8"
                },
                "downloads": -1,
                "filename": "torchmeta-1.1.1.tar.gz",
                "has_sig": false,
                "md5_digest": "e1fb15af43cd4083a334d81e1a0651b2",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 108089,
                "upload_time": "2019-09-16T20:09:50",
                "url": "https://files.pythonhosted.org/packages/b3/96/857cec3acf16f6e205420c9cd971844db827f65afa3ab503ec3ec0a5d5b7/torchmeta-1.1.1.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "80c0dd6856d79f18204e38dfc402e228",
                "sha256": "76a605f34eceef68404c784d21e01cb462879f8b5244e270a49e0826e477b204"
            },
            "downloads": -1,
            "filename": "torchmeta-1.1.1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "80c0dd6856d79f18204e38dfc402e228",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": null,
            "size": 133052,
            "upload_time": "2019-09-16T20:09:48",
            "url": "https://files.pythonhosted.org/packages/a9/15/007c1f2527f50fa25844afec7ca05f66be30bbc9a85a36d9c3e722a32705/torchmeta-1.1.1-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "e1fb15af43cd4083a334d81e1a0651b2",
                "sha256": "3ecb2a55c507dc091cb33d5318c31663125f1c5f459f1ea213b37d26bd00a4c8"
            },
            "downloads": -1,
            "filename": "torchmeta-1.1.1.tar.gz",
            "has_sig": false,
            "md5_digest": "e1fb15af43cd4083a334d81e1a0651b2",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 108089,
            "upload_time": "2019-09-16T20:09:50",
            "url": "https://files.pythonhosted.org/packages/b3/96/857cec3acf16f6e205420c9cd971844db827f65afa3ab503ec3ec0a5d5b7/torchmeta-1.1.1.tar.gz"
        }
    ]
}