New to machine learning? Watch a video course to get practical working knowledge of ML using web technologies
View series
TensorFlow.js 指南
透過集合功能整理內容
你可以依據偏好儲存及分類內容。
除非另有註明,否則本頁面中的內容是採用創用 CC 姓名標示 4.0 授權,程式碼範例則為阿帕契 2.0 授權。詳情請參閱《Google Developers 網站政策》。Java 是 Oracle 和/或其關聯企業的註冊商標。
上次更新時間:2020-10-09 (世界標準時間)。
[null,null,["上次更新時間:2020-10-09 (世界標準時間)。"],[],[],null,["# TensorFlow.js guide\n\n\u003cbr /\u003e\n\nThis guide provides in-depth documentation of important TensorFlow.js topics. If\nyou're just getting started with TensorFlow.js, you might want to explore\n[the tutorials](/js/tutorials) and then return to this guide to learn more.\n\nTensorFlow.js is an open-source web ML library that can run anywhere JavaScript\ncan. It's based on the original TensorFlow library written in Python and aims\nto recreate this developer experience and set of APIs for the JavaScript\necosystem.\n\nThe topics in this guide will help you understand TensorFlow.js and how\nTensorFlow APIs work in JavaScript.\n\nLearn about key Tensorflow concepts:\n\n- [Tensors and operations](/js/guide/tensors_operations) -- An intro to tensors, data, shapes, and data types: the building blocks of TensorFlow.js.\n- [Platform and environment](/js/guide/platform_environment) -- Overview of the different platforms and environments in TensorFlow.js and the tradeoffs between them.\n- [Custom ops, kernels, and gradients](/js/guide/custom_ops_kernels_gradients) -- Outlines the mechanisms for defining custom operations (ops), kernels, and gradients in TensorFlow.js.\n\nLearn about pre-made models:\n\n- [Use a pre-made model](/js/guide/premade_models) -- Guidance on how to find and select pre-made models for your use case.\n\nLearn more about models and how to use them:\n\n- [Models and layers](/js/guide/models_and_layers) -- How to build a model in TensorFlow.js using Layers and the Core API.\n- [Train models](/js/guide/train_models) -- Introduction to training: models, optimizers, losses, metrics, variables.\n- [Save and load models](/js/guide/save_load) -- Learn how to save and load TensorFlow.js models.\n- [Model conversion](/js/guide/conversion) -- See the landscape of model types available in the TensorFlow.js ecosystem and the details behind conversion of models.\n- [Differences from Python tf.keras](/js/guide/layers_for_keras_users) -- Know the major differences and capabilities between TensorFlow.js and Python [`tf.keras`](/api_docs/python/tf/keras) and the API conventions used in JavaScript.\n\nLearn about TensorFlow.js in Node.js:\n\n- [Using TensorFlow.js in Node.js](/js/guide/nodejs) -- Understand the tradeoffs between the three available Node.js bindings and the system requirements they have.\n- [Deploy a TensorFlow.js Node project on cloud](/js/guide/node_in_cloud) -- How to deploy a Node.js process with the `tfjs-node` package on cloud platforms."]]