{"id":13442702,"url":"https://github.com/hpi-xnor/bitorch","last_synced_at":"2025-03-20T15:30:29.249Z","repository":{"id":39751590,"uuid":"425837016","full_name":"hpi-xnor/bitorch","owner":"hpi-xnor","description":"BITorch: Open-Source Implementation of Binary Neural Networks with PyTorch","archived":false,"fork":false,"pushed_at":"2023-05-23T11:31:34.000Z","size":2141,"stargazers_count":32,"open_issues_count":1,"forks_count":4,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-04-26T18:46:06.966Z","etag":null,"topics":["binary-neural-networks","deep-learning","python","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hpi-xnor.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":"AUTHORS","dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-11-08T12:54:50.000Z","updated_at":"2024-06-13T12:27:56.035Z","dependencies_parsed_at":"2024-06-13T12:27:44.829Z","dependency_job_id":"e479710d-af95-4ddb-be2e-61f8f29c5006","html_url":"https://github.com/hpi-xnor/bitorch","commit_stats":{"total_commits":505,"total_committers":9,"mean_commits":"56.111111111111114","dds":0.6435643564356436,"last_synced_commit":"d6c14d59c77bf346c85fbbd11a4375128f729a49"},"previous_names":[],"tags_count":7,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hpi-xnor%2Fbitorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hpi-xnor%2Fbitorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hpi-xnor%2Fbitorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hpi-xnor%2Fbitorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hpi-xnor","download_url":"https://codeload.github.com/hpi-xnor/bitorch/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244639833,"owners_count":20485938,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["binary-neural-networks","deep-learning","python","pytorch"],"created_at":"2024-07-31T03:01:49.396Z","updated_at":"2025-03-20T15:30:28.918Z","avatar_url":"https://github.com/hpi-xnor.png","language":"Python","funding_links":[],"categories":["Python","Software and Repositories"],"sub_categories":[],"readme":"# BITorch\n\nBITorch is a library currently under development to simplify building quantized and binary neural networks\nwith [PyTorch](https://pytorch.org/).\nThis is an early preview version of the library.\nIf you wish to use it and encounter any problems, please create an issue.\nOur current roadmap contains:\n\n- Extending the model zoo with pre-trained models of state-of-the-art approaches\n- Adding examples for advanced training methods with multiple stages, knowledge distillation, etc.\n\nAll changes are tracked in the [changelog](https://github.com/hpi-xnor/bitorch/blob/main/CHANGELOG.md).\n\nPlease refer to [our wiki](https://bitorch.readthedocs.io/en/latest/) for a comprehensive introduction into\nthe library or use the introduction notebook in `examples/notebooks`.\n\n## Installation\n\nSimilar to recent versions of [torchvision](https://github.com/pytorch/vision), you should be using Python 3.8 or newer.\nCurrently, the only supported installation is pip (a conda package is planned in the future).\n\n### Pip\n\nIf you wish to use a _specific version_ of PyTorch for compatibility with certain devices or CUDA versions,\nwe advise on installing the corresponding versions of `pytorch` and `torchvision` first (or afterwards),\nplease consult [pytorch's getting started guide](https://pytorch.org/get-started/locally/).\n\nOtherwise, simply run:\n```bash\npip install bitorch\n```\n\nNote, that you can also request a specific PyTorch version directly, e.g. for CUDA 11.3:\n```bash\npip install bitorch --extra-index-url https://download.pytorch.org/whl/cu113\n```\n\nIf you want to run the examples install the optional dependencies as well:\n```bash\npip install \"bitorch[opt]\"\n```\n\n#### Local and Development Install Options\n\nThe package can also be installed locally for editing and development.\nFirst, clone the [repository](https://github.com/hpi-xnor/bitorch), then run:\n\n```bash\npip install -e .         # without optional dependencies\npip install -e \".[opt]\"  # with optional dependencies\n```\n\n### Dali Preprocessing\n\nIf you want to use the [Nvidia dali preprocessing library](https://github.com/NVIDIA/DALI),\ne.g. with CUDA 11.x, (currently only supported for imagenet)\nyou need to install the `nvidia-dali-cuda110` package by running the following command:\n\n```\npip install --extra-index-url https://developer.download.nvidia.com/compute/redist --upgrade nvidia-dali-cuda110\n```\n\n## Development\n\nInstall the package and _dev_ requirements locally for development:\n\n```bash\npip install -e \".[dev]\"\n```\n\n### Tests\n\nThe tests can be run with [pytest](https://docs.pytest.org/):\n\n```bash\npytest\n```\n\n### Code formatting and typing\n\nFor conveniently checking whether your code suites the required style (more details below), run\n```bash\n./check-codestyle.sh\n```\n\nNew code should be compatible with Python 3.X versions and be compliant with PEP8. To check the codebase, please run\n```bash\nflake8\n```\n\nThe codebase has type annotations, please make sure to add type hints if required. We use `mypy` for type checking:\n```bash\nmypy --config-file mypy.ini\n```\n\nFor code formatting we use `black`:\n```bash\nblack . --check --verbose --diff --color  # check what changes the formatter would do\nblack .  # apply the formatter\n```\n\nIn order to automatically apply the code formatting with every commit, you can also install pre-commit\nand use the pre-commit hook:\n```bash\npre-commit install\n```\n\n### Documentation\n\nWe use [Google's Python Docstring Format](https://sphinxcontrib-napoleon.readthedocs.io/en/latest/example_google.html)\nto document our code.\n\nDocumentation can be generated with\n```bash\nsphinx-build -b html docs/source/ docs/build/ -a\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhpi-xnor%2Fbitorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhpi-xnor%2Fbitorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhpi-xnor%2Fbitorch/lists"}