{"id":13430887,"url":"https://github.com/SciSharp/SiaNet","last_synced_at":"2025-03-16T06:31:34.809Z","repository":{"id":77102960,"uuid":"108052184","full_name":"SciSharp/SiaNet","owner":"SciSharp","description":"An easy to use C# deep learning library with CUDA/OpenCL support","archived":true,"fork":false,"pushed_at":"2019-05-30T10:53:17.000Z","size":76617,"stargazers_count":380,"open_issues_count":6,"forks_count":83,"subscribers_count":51,"default_branch":"master","last_synced_at":"2024-10-29T23:35:55.464Z","etag":null,"topics":["artificial-intelligence","cognitive-services","deep-learning","deep-neural-network","image-classification","image-processing","machine-learning","neural-network","object-detection"],"latest_commit_sha":null,"homepage":"https://scisharp.github.io/SiaNet","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/SciSharp.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2017-10-23T23:30:53.000Z","updated_at":"2024-07-31T21:00:01.000Z","dependencies_parsed_at":"2023-07-08T16:45:44.110Z","dependency_job_id":null,"html_url":"https://github.com/SciSharp/SiaNet","commit_stats":null,"previous_names":["deepakkumar1984/sianet"],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SciSharp%2FSiaNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SciSharp%2FSiaNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SciSharp%2FSiaNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SciSharp%2FSiaNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SciSharp","download_url":"https://codeload.github.com/SciSharp/SiaNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242487815,"owners_count":20136653,"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-intelligence","cognitive-services","deep-learning","deep-neural-network","image-classification","image-processing","machine-learning","neural-network","object-detection"],"created_at":"2024-07-31T02:00:58.717Z","updated_at":"2025-03-16T06:31:30.027Z","avatar_url":"https://github.com/SciSharp.png","language":"C#","funding_links":[],"categories":["Frameworks, Libraries and Tools","框架, 库和工具","neural-network","C\\#","deep-learning"],"sub_categories":["Machine Learning and Data Science","机器学习和科学研究"],"readme":"[![Join the chat at https://gitter.im/publiclab/publiclab](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/sci-sharp/community)\n[![Build status](https://dev.azure.com/deepakkumarb/SIA/_apis/build/status/SiaNet%20Beta%200.4.1)](https://dev.azure.com/deepakkumarb/SIA/_build/latest?definitionId=4)\n![Build Status](https://travis-ci.org/SciSharp/SiaNet.svg?branch=master)\n[![Backers on Open Collective](https://opencollective.com/sianet/backers/badge.svg)](#backers) [![Sponsors on Open Collective](https://opencollective.com/sianet/sponsors/badge.svg)](#sponsors) \n\n[\u003cimg src=\"https://img.shields.io/badge/slack-@siadroid/sianet-green.svg?logo=slack\"\u003e](https://siadroid.slack.com/messages/CGL4QULPM)\n\nTrello is used to track SiaNet devlopment activities. You are welcome to watch any task and track progress. Suggestion will be put on the wishlist and then will be planned out for development\n\nhttps://trello.com/b/bLbgQLgy/sianet-development\n\n\n\n# A C# deep learning library\n\nDeveloping a C# wrapper to help developer easily create and train deep neural network models.\n\n* Easy to use library, just focus on research\n* Multiple backend - CNTK, TensorFlow, MxNet, PyTorch, ArrayFire\n* CUDA/ OpenCL support for some of the backends\n* Light weight libray, built with .NET standard 2.0\n* Code well structured, easy to extend if you would like to extend with new layer, loss, metrics, optimizers, constraints, regularizer\n\n# A Basic example\nThe below is a classification example with Titanic dataset. Able to reach 75% accuracy within 10 epoch. \n```c#\n//Setup Engine. If using TensorSharp then pass SiaNet.Backend.TensorSharp.SiaNetBackend.Instance. \n//Once other backend is ready you will be able to use CNTK, TensorFlow and MxNet as well.\nGlobal.UseEngine(SiaNet.Backend.ArrayFire.SiaNetBackend.Instance, DeviceType.CPU);\n\nvar dataset = LoadTrain(); //Load train data\nvar test = LoadTest(); //Load test data\n\nvar (train, val) = dataset.Split(0.25);\n\n//Build model\nvar model = new Sequential();\nmodel.EpochEnd += Model_EpochEnd;\nmodel.Add(new Dense(128, ActivationType.ReLU));\nmodel.Add(new Dense(64, ActivationType.ReLU));\nmodel.Add(new Dense(1, ActivationType.Sigmoid));\n\n//Compile with Optimizer, Loss and Metric\nmodel.Compile(OptimizerType.Adam, LossType.BinaryCrossEntropy, MetricType.BinaryAccurary);\n\n// Train for 100 epoch with batch size of 32\nmodel.Train(train, 100, 32, val);\n\nvar predictions = model.Predict(test);\npredictions.Print();\n```\n### Training Result\n\n![Figure 1-1](https://i.ibb.co/KG87pv4/Titanic-1.png \"Figure 1-1\")\n\nComplete Code: https://github.com/SciSharp/SiaNet/blob/master/Examples/BasicClassificationWithTitanicDataset/Program.cs\n\nMore examples: https://github.com/SciSharp/SiaNet/blob/master/Examples\n\n# API Docs\nhttps://scisharp.github.io/SiaNet/\n\n# Contribution\nAny help is welcome!!!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FSciSharp%2FSiaNet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FSciSharp%2FSiaNet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FSciSharp%2FSiaNet/lists"}