{"id":13418765,"url":"https://github.com/wichtounet/dll","last_synced_at":"2025-04-12T23:39:46.181Z","repository":{"id":13028127,"uuid":"15707742","full_name":"wichtounet/dll","owner":"wichtounet","description":"Fast Deep Learning Library (DLL) for C++ (ANNs, CNNs, RBMs, DBNs...)","archived":false,"fork":false,"pushed_at":"2024-02-09T11:54:20.000Z","size":17830,"stargazers_count":675,"open_issues_count":1,"forks_count":161,"subscribers_count":58,"default_branch":"master","last_synced_at":"2025-04-12T23:39:42.650Z","etag":null,"topics":["artificial-neural-networks","c-plus-plus","convolutional-neural-networks","cpp","cpp11","cpp14","cpu","deep-learning","gpu","machine-learning","performance","rbm"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/wichtounet.png","metadata":{"files":{"readme":"README.rst","changelog":"ChangeLog.rst","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}},"created_at":"2014-01-07T15:10:30.000Z","updated_at":"2025-03-02T11:37:35.000Z","dependencies_parsed_at":"2024-04-16T19:58:10.404Z","dependency_job_id":"a1a88c34-62b7-43c4-85fd-f629ad28028a","html_url":"https://github.com/wichtounet/dll","commit_stats":{"total_commits":3616,"total_committers":5,"mean_commits":723.2,"dds":"0.0019358407079645978","last_synced_commit":"df1fcae4bdf14fbc73290214cc6dbf4578ac1efe"},"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wichtounet%2Fdll","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wichtounet%2Fdll/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wichtounet%2Fdll/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wichtounet%2Fdll/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wichtounet","download_url":"https://codeload.github.com/wichtounet/dll/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248647255,"owners_count":21139081,"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":["artificial-neural-networks","c-plus-plus","convolutional-neural-networks","cpp","cpp11","cpp14","cpu","deep-learning","gpu","machine-learning","performance","rbm"],"created_at":"2024-07-30T22:01:06.776Z","updated_at":"2025-04-12T23:39:46.162Z","avatar_url":"https://github.com/wichtounet.png","language":"C++","funding_links":[],"categories":["TODO scan for Android support in followings","[Libraries](#awesome-robotics-libraries)","C++"],"sub_categories":["[Machine Learning](#awesome-robotics-libraries)"],"readme":"Deep Learning Library (DLL) 1.1\n===============================\n\n|logo|    |coverage| |jenkins| |license|\n\n.. |logo| image:: logo_small.png\n.. |coverage| image:: https://img.shields.io/sonar/https/sonar.baptiste-wicht.ch/dll/coverage.svg\n.. |jenkins| image:: https://img.shields.io/jenkins/s/https/jenkins.baptiste-wicht.ch/dll.svg\n.. |license| image:: https://img.shields.io/github/license/mashape/apistatus.svg\n\nDLL is a library that aims to provide a C++ implementation of Restricted\nBoltzmann Machine (RBM) and Deep Belief Network (DBN) and their convolution\nversions as well. It also has support for some more standard neural networks.\n\nFeatures\n--------\n\n* **Restricted Boltzmann Machine**\n\n  * Various units: Stochastic binary, Gaussian, Softmax and nRLU units\n  * Contrastive Divergence and Persistence Contrastive Divergence\n\n    * CD-1 learning by default\n\n  * Momentum\n  * Weight decay\n  * Sparsity target\n  * Train as Denoising autoencoder\n\n* **Convolutional Restricted Boltzmann Machine**\n\n  * Standard version\n  * Version with Probabilistic Max Pooling (Honglak Lee)\n  * Binary and Gaussian visible units\n  * Binary and ReLU hidden units for the standard version\n  * Binary hidden units for the Probabilistic Max Pooling version\n  * Training with CD-k or PCD-k (only for standard version)\n  * Momentum, Weight Decay, Sparsity Target\n  * Train as Denoising autoencoder\n\n* **Deep Belief Network**\n\n  * Pretraining with RBMs\n  * Fine tuning with Conjugate Gradient\n  * Fine tuning with Stochastic Gradient Descent\n  * Classification with SVM (libsvm)\n\n* **Convolutional Deep Belief Network**\n\n  * Pretraining with CRBMs\n  * Classification with SVM (libsvm)\n\n* Input data\n\n  * Input data can be either in containers or in iterators\n\n    * Even if iterators are supported for SVM classifier, libsvm will move all\n      the data in memory structure.\n\nBuilding\n--------\n\nNote: When you clone the library, you need to clone the sub modules as well,\nusing the --recursive option.\n\nThe folder **include** must be included with the **-I** option, as well as the\n**etl/include** folder.\n\nThis library is completely header-only, there is no need to build it.\n\nHowever, this library makes extensive use of C++20 and C++23, therefore,\na recent compiler is necessary to use it. Currently, this library is only tested\nwith g++ 13.\n\nIf for some reasons, it should not work on one of the supported compilers,\ncontact me and I'll fix it. It should work fine on recent versions of clang.\n\nThis has never been tested on Windows. While it should compile on Mingw, I don't\nexpect Visual Studio to be able to compile it for now, although recent versions of VS sound\npromising. If you have problems compiling this library, I'd be glad to help, but\ncannot guarantee that this will work on other compilers.\n\nIf you want to use GPU, you should use CUDA 12 or superior and CUDNN 8 or\nsuperior. If you got issues with different\nversions of CUDA and CUDNN, please open an issue on Github.\n\nLicense\n-------\n\nThis library is distributed under the terms of the MIT license, see `LICENSE`\nfile for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwichtounet%2Fdll","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwichtounet%2Fdll","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwichtounet%2Fdll/lists"}