{"id":13398647,"url":"https://github.com/hannes-brt/hebel","last_synced_at":"2025-04-08T06:36:54.558Z","repository":{"id":11975794,"uuid":"14549208","full_name":"hannes-brt/hebel","owner":"hannes-brt","description":"GPU-Accelerated Deep Learning Library in Python","archived":false,"fork":false,"pushed_at":"2020-12-29T05:32:20.000Z","size":1347,"stargazers_count":1166,"open_issues_count":6,"forks_count":120,"subscribers_count":81,"default_branch":"master","last_synced_at":"2025-04-01T05:33:30.359Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":"yuantiku/YTKKeyValueStore","license":"gpl-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hannes-brt.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGES.md","contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2013-11-20T07:01:18.000Z","updated_at":"2025-03-26T17:35:35.000Z","dependencies_parsed_at":"2022-09-01T14:41:59.103Z","dependency_job_id":null,"html_url":"https://github.com/hannes-brt/hebel","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hannes-brt%2Fhebel","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hannes-brt%2Fhebel/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hannes-brt%2Fhebel/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hannes-brt%2Fhebel/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hannes-brt","download_url":"https://codeload.github.com/hannes-brt/hebel/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247792892,"owners_count":20996891,"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":[],"created_at":"2024-07-30T19:00:29.927Z","updated_at":"2025-04-08T06:36:54.526Z","avatar_url":"https://github.com/hannes-brt.png","language":"Python","funding_links":[],"categories":["Researchers","Python","资源列表","Table of Contents","Machine Learning","Frameworks"],"sub_categories":["Frameworks","深度学习","General-Purpose Machine Learning","机器学习","List of lists"],"readme":"# Hebel\n\nGPU-Accelerated Deep Learning Library in Python\n\nHebel is a library for deep learning with neural networks in Python using GPU acceleration with CUDA through PyCUDA. It implements the most important types of neural network models and offers a variety of different activation functions and training methods such as momentum, Nesterov momentum, dropout, and early stopping.\n\nI no longer actively develop Hebel. If you are looking for a deep learning framework in Python, I now recommend [Chainer](https://github.com/pfnet/chainer).\n\n## Models\n\nRight now, Hebel implements feed-forward neural networks for classification and regression on one or multiple tasks. Other models such as Autoencoder, Convolutional neural nets, and Restricted Boltzman machines are planned for the future.\n\nHebel implements dropout as well as L1 and L2 weight decay for regularization.\n\n## Optimization\n\nHebel implements stochastic gradient descent (SGD) with regular and Nesterov momentum.\n\n## Compatibility\n\nCurrently, Hebel will run on Linux and Windows, and probably Mac OS X (not tested). \n\n## Dependencies\n- PyCUDA\n- numpy\n- PyYAML\n- skdata (only for MNIST example)\n\n## Installation\n\nHebel is on PyPi, so you can install it with\n\n    pip install hebel\n\n## Getting started\nStudy the yaml configuration files in `examples/` and run\n    \n    python train_model.py examples/mnist_neural_net_shallow.yml\n    \nThe script will create a directory in `examples/mnist` where the models and logs are saved.\n\nRead the Getting started guide at [hebel.readthedocs.org/en/latest/getting_started.html](http://hebel.readthedocs.org/en/latest/getting_started.html) for more information.\n\n## Documentation\n[hebel.readthedocs.org](http://hebel.readthedocs.org)\n\n## Contact\nMaintained by [Hannes Bretschneider](http://github.com/hannes-brt) (hannes@psi.utoronto.ca).\nIf your are using Hebel, please let me know whether you find it useful and file a Github issue if you find any bugs or have feature requests.\n\n## Citing\n[![http://dx.doi.org/10.5281/zenodo.10050](https://zenodo.org/badge/doi/10.5281/zenodo.10050.png)](http://dx.doi.org/10.5281/zenodo.10050)\n\nIf you make use of Hebel in your research, please cite it. The BibTeX reference is\n    \n    @article{Bretschneider:10050,\n      author        = \"Hannes Bretschneider\",\n      title         = \"{Hebel - GPU-Accelerated Deep Learning Library in Python}\",\n      month         = \"May\",\n      year          = \"2014\",\n      doi           = \"10.5281/zenodo.10050\",\n      url           = \"https://zenodo.org/record/10050\",\n    }\n\n## What's with the name?\n_Hebel_ is the German word for _lever_, one of the oldest tools that humans use. As Archimedes said it: _\"Give me a lever long enough and a fulcrum on which to place it, and I shall move the world.\"_\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhannes-brt%2Fhebel","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhannes-brt%2Fhebel","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhannes-brt%2Fhebel/lists"}