{"id":19650289,"url":"https://github.com/flukeskywalker/highway-networks","last_synced_at":"2026-03-05T07:36:26.931Z","repository":{"id":36197826,"uuid":"40502049","full_name":"flukeskywalker/highway-networks","owner":"flukeskywalker","description":"An implementation of Highway Networks in Caffe","archived":false,"fork":false,"pushed_at":"2015-09-20T14:58:09.000Z","size":7132,"stargazers_count":95,"open_issues_count":2,"forks_count":26,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-04-05T09:34:20.364Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/flukeskywalker.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2015-08-10T19:36:57.000Z","updated_at":"2025-01-26T04:13:09.000Z","dependencies_parsed_at":"2022-08-18T18:21:28.518Z","dependency_job_id":null,"html_url":"https://github.com/flukeskywalker/highway-networks","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flukeskywalker%2Fhighway-networks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flukeskywalker%2Fhighway-networks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flukeskywalker%2Fhighway-networks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flukeskywalker%2Fhighway-networks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/flukeskywalker","download_url":"https://codeload.github.com/flukeskywalker/highway-networks/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251345813,"owners_count":21574783,"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":"2024-11-11T14:57:55.724Z","updated_at":"2026-03-05T07:36:26.887Z","avatar_url":"https://github.com/flukeskywalker.png","language":"C++","funding_links":[],"categories":["\u003ca name=\"Vision\"\u003e\u003c/a\u003e2. Vision","Highway Networks"],"sub_categories":["Implementations"],"readme":"# Highway Networks\n\nThis is sample code for convolutional **Highway Networks**, implemented in Caffe checked out at [this](https://github.com/BVLC/caffe/tree/e20498ebf985322bab2f4f28f0f6365ecde80c29) state. It runs only on the NVIDIA GPUs and requires NVIDIA's cuDNN v2. The original Caffe README is reproduced below the line.\n\nHighway Networks utilize the idea of *information highways*, in turn inspired by LSTM networks [[1](http://www.bioinf.at/publications/older/2604.pdf), [2](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.55.5709\u0026rep=rep1\u0026type=pdf), [3](http://arxiv.org/abs/1503.04069)].\nOur experiments on highway networks show that when designed correctly, neural networks with tens, even hundreds of layers can be trained directly with stochastic gradient descent, thereby providing a promising solution to the vanishing gradient problem. More information is available on the [Project Website](http://people.idsia.ch/~rupesh/very_deep_learning/).\n\nHighway Networks were introduced in the following paper:\n\nSrivastava, R. K., Greff, K., \u0026 Schmidhuber, J. (2015). Highway Networks. arXiv preprint [arXiv:1505.00387](http://arxiv.org/abs/1505.00387).\n\nFollowed by a more detailed report:\n\nSrivastava, R. K., Greff, K., \u0026 Schmidhuber, J. (2015). Training Very Deep Networks. arXiv preprint [arXiv:1507.06228](http://arxiv.org/abs/1507.06228).\n\n## Data\n\nYou can get preprocessed datasets (CIFAR-10/100 were global contrast normalized and padded with 8 pixels each side) at the links below.\nCaffe's data generation scripts do not generate validation sets. The provided data below includes splits into training and validation sets.\n\n[CIFAR-10](https://www.dropbox.com/s/r9zuhhhii4uzi24/cifar10-gcn-leveldb-splits.tar.bz2?dl=0) ~ 2.27 GB\n\n[CIFAR-100](https://www.dropbox.com/s/w2qywjihzr7avfa/cifar100-gcn-leveldb-splits.tar.bz2?dl=0) ~ 2.27 GB\n\n[MNIST](https://www.dropbox.com/s/3q04bu5cz9mha52/mnist-splits.tar.bz2?dl=0) ~ 20 MB\n\n\n## Examples\n\nSee examples and sample log outputs in examples/highways. You probably need to adjust the paths to the datasets in the network definition files in order to train networks.\n\n## Citation\n\nPlease cite us if you use this code:\n\n    @article{srivastava2015highway,\n        title={Training Very Deep Networks},\n        author={Srivastava, Rupesh Kumar and Greff, Klaus and Schmidhuber, J{\\\"u}rgen},\n        journal={arXiv preprint arXiv:1507.06228},\n        year={2015}\n    }\n\n----\n\n\n# Caffe\n\nCaffe is a deep learning framework made with expression, speed, and modularity in mind.\nIt is developed by the Berkeley Vision and Learning Center ([BVLC](http://bvlc.eecs.berkeley.edu)) and community contributors.\n\nCheck out the [project site](http://caffe.berkeleyvision.org) for all the details like\n\n- [DIY Deep Learning for Vision with Caffe](https://docs.google.com/presentation/d/1UeKXVgRvvxg9OUdh_UiC5G71UMscNPlvArsWER41PsU/edit#slide=id.p)\n- [Tutorial Documentation](http://caffe.berkeleyvision.org/tutorial/)\n- [BVLC reference models](http://caffe.berkeleyvision.org/model_zoo.html) and the [community model zoo](https://github.com/BVLC/caffe/wiki/Model-Zoo)\n- [Installation instructions](http://caffe.berkeleyvision.org/installation.html)\n\nand step-by-step examples.\n\n[![Join the chat at https://gitter.im/BVLC/caffe](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/BVLC/caffe?utm_source=badge\u0026utm_medium=badge\u0026utm_campaign=pr-badge\u0026utm_content=badge)\n\nPlease join the [caffe-users group](https://groups.google.com/forum/#!forum/caffe-users) or [gitter chat](https://gitter.im/BVLC/caffe) to ask questions and talk about methods and models.\nFramework development discussions and thorough bug reports are collected on [Issues](https://github.com/BVLC/caffe/issues).\n\nHappy brewing!\n\n## License and Citation\n\nCaffe is released under the [BSD 2-Clause license](https://github.com/BVLC/caffe/blob/master/LICENSE).\nThe BVLC reference models are released for unrestricted use.\n\nPlease cite Caffe in your publications if it helps your research:\n\n    @article{jia2014caffe,\n      Author = {Jia, Yangqing and Shelhamer, Evan and Donahue, Jeff and Karayev, Sergey and Long, Jonathan and Girshick, Ross and Guadarrama, Sergio and Darrell, Trevor},\n      Journal = {arXiv preprint arXiv:1408.5093},\n      Title = {Caffe: Convolutional Architecture for Fast Feature Embedding},\n      Year = {2014}\n    }\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflukeskywalker%2Fhighway-networks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fflukeskywalker%2Fhighway-networks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflukeskywalker%2Fhighway-networks/lists"}