匿名用户2021年11月11日
45阅读
开发技术Python
所属分类人工智能、机器学习/深度学习
授权协议Apache-2.0 License

作品详情

TensorFlow.js

TensorFlow.jsisanopen-sourcehardware-acceleratedJavaScriptlibraryfortraininganddeployingmachinelearningmodels.

DevelopMLintheBrowserUseflexibleandintuitiveAPIstobuildmodelsfromscratchusingthelow-levelJavaScriptlinearalgebralibraryorthehigh-levellayersAPI.

DevelopMLinNode.jsExecutenativeTensorFlowwiththesameTensorFlow.jsAPIundertheNode.jsruntime.

RunExistingmodelsUseTensorFlow.jsmodelconverterstorunpre-existingTensorFlowmodelsrightinthebrowser.

RetrainExistingmodelsRetrainpre-existingMLmodelsusingsensordataconnectedtothebrowserorotherclient-sidedata.

Aboutthisrepo

Thisrepositorycontainsthelogicandscriptsthatcombineseveralpackages.

APIs:

TensorFlow.jsCore,aflexiblelow-levelAPIforneuralnetworksandnumericalcomputation.TensorFlow.jsLayers,ahigh-levelAPIwhichimplementsfunctionalitysimilartoKeras.TensorFlow.jsData,asimpleAPItoloadandpreparedataanalogoustotf.data.TensorFlow.jsConverter,toolstoimportaTensorFlowSavedModeltoTensorFlow.jsTensorFlow.jsVis,in-browservisualizationforTensorFlow.jsmodelsTensorFlow.jsAutoML,SetofAPIstoloadandrunmodelsproducedbyAutoMLEdge.

Backends/Platforms:

TensorFlow.jsCPUBackend,pure-JSbackendforNode.jsandthebrowser.TensorFlow.jsWebGLBackend,WebGLbackendforthebrowser.TensorFlow.jsWASMBackend,WebAssemblybackendforthebrowser.TensorFlow.jsWebGPU,WebGPUbackendforthebrowser.TensorFlow.jsNode,Node.jsplatformviaTensorFlowC++adapter.TensorFlow.jsReactNative,ReactNativeplatformviaexpo-gladapter.

Ifyoucareaboutbundlesize,youcanimportthosepackagesindividually.

IfyouarelookingforNode.jssupport,checkouttheTensorFlow.jsNodedirectory.

Examples

Checkoutourexamplesrepositoryandourtutorials.

Gallery

BesuretocheckoutthegalleryofallprojectsrelatedtoTensorFlow.js.

Pre-trainedmodels

Besuretoalsocheckoutourmodelsrepositorywherewehostpre-trainedmodelsonNPM.

BenchmarksLocalbenchmarktool.Usethiswebpagetooltocollecttheperformancerelatedmetrics(speed,memory,etc)ofTensorFlow.jsmodelsandkernelsonyourlocaldevicewithCPU,WebGLorWASMbackends.Youcanbenchmarkcustommodelsbyfollowingthisguide.Multi-devicebenchmarktool.Usethistooltocollectthesameperformancerelatedmetricsonacollectionofremotedevices.Gettingstarted

TherearetwomainwaystogetTensorFlow.jsinyourJavaScriptproject:viascripttagsorbyinstallingitfromNPMandusingabuildtoollikeParcel,WebPack,orRollup.

viaScriptTag

AddthefollowingcodetoanHTMLfile:

声明:本文仅代表作者观点,不代表本站立场。如果侵犯到您的合法权益,请联系我们删除侵权资源!如果遇到资源链接失效,请您通过评论或工单的方式通知管理员。未经允许,不得转载,本站所有资源文章禁止商业使用运营!
下载安装【程序员客栈】APP
实时对接需求、及时收发消息、丰富的开放项目需求、随时随地查看项目状态

评论