TensorFlow
选择 TensorFlow 的原因
使用集合让一切井井有条
根据您的偏好保存内容并对其进行分类。
选择 TensorFlow 的原因
TensorFlow 是一个端到端平台，无论您是专家还是初学者，它都可以让您轻松地构建和部署机器学习模型。
观看视频
案例研究
close
一个完整的生态系统，可以帮助您使用机器学习解决棘手的现实问题
轻松地构建模型
TensorFlow 提供多个抽象级别，因此您可以根据自己的需求选择合适的级别。您可以使用高阶 Keras API 构建和训练模型，该 API 让您能够轻松地开始使用 TensorFlow 和机器学习。
如果您需要更高的灵活性，则可以借助即刻执行环境进行快速迭代和直观的调试。对于大型机器学习训练任务，您可以使用 Distribution Strategy API 在不同的硬件配置上进行分布式训练，而无需更改模型定义。
查看资源
观看视频
close
随时随地进行可靠的机器学习生产
TensorFlow 始终提供直接的生产途径。不管是在服务器、边缘设备还是网络上，TensorFlow 都可以助您轻松地训练和部署模型，无论您使用何种语言或平台。
如果您需要完整的生产环境机器学习流水线，请使用 TFX。如需在移动设备和边缘设备上进行推断，请使用 TensorFlow Lite。如需在 JavaScript 环境中训练和部署模型，请使用 TensorFlow.js。
查看资源
观看视频
close
强大的研究实验
构建和训练先进的模型，并且不会降低速度或性能。借助 Keras Functional API 和 Model Subclassing API 等功能，TensorFlow 可以助您灵活地创建复杂拓扑并实现相关控制。为了轻松地设计原型并快速进行调试，请使用即刻执行环境。
TensorFlow 还支持强大的附加库和模型生态系统以供您开展实验，包括 Ragged Tensors、TensorFlow Probability、Tensor2Tensor 和 BERT。
查看资源
观看视频
close
了解企业如何使用 TensorFlow
Airbnb
Coca Cola
Deepmind
Lenovo
Sinovation
Fluent
WPS
China Mobile
查看案例研究
了解机器学习的工作原理
您是否曾想了解神经网络的工作原理？或者解决机器学习问题有哪些步骤？不用担心，我们会为您讲解。下面将简要介绍机器学习的基础知识。或者，如果您要寻找更深入的信息，请访问我们的教育页面，获取入门级和高级内容。
学习机器学习知识
机器学习简介
解决机器学习问题的步骤
神经网络剖析
训练神经网络
机器学习简介
机器学习是指帮助软件在没有明确的程序或规则的情况下执行任务。对于传统计算机编程，程序员会指定计算机应该使用的规则。但是，机器学习需要另一种思维方式。现实中的机器学习对数据分析的注重程度远高于编码。程序员提供一组样本，然后计算机从数据中学习各种模式。您可以将机器学习视为“使用数据进行编程”。
解决机器学习问题的步骤
使用机器学习从数据中获取答案的过程包含多个步骤。如需了解分步概述，请查看此指南，其中显示了文本分类的完整工作流程，并描述了相关的重要步骤，例如收集数据集，以及使用 TensorFlow 训练和评估模型。
神经网络剖析
神经网络是一种可以通过训练来识别各种模式的模型。神经网络由多个层组成，包括输入层和输出层，以及至少一个隐藏层。各层中的神经元会学习越来越抽象的数据表示法。例如，在此可视化图表中，我们看到了检测线条、形状和纹理的神经元。这些表示法（或学习的特征）可以用来对数据进行分类。
训练神经网络
神经网络是通过梯度下降法进行训练的。每层的权重都以随机值开始，并且这些权重会随着时间的推移以迭代的方式不断改进，使网络更准确。我们使用损失函数量化网络的不准确程度，并使用一种名为“反向传播算法”的流程确定每个权重应该增加还是降低以减小损失。
我们的社区
TensorFlow 社区是一个由开发者、研究人员、创想家、生手和问题解决者组成的活跃群组。您可以随时通过此社区贡献代码、进行合作以及分享您的想法。
了解详情
使用 TensorFlow 轻松地构建、部署和实验模型
开始使用
[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["没有我需要的信息","missingTheInformationINeed","thumb-down"],["太复杂/步骤太多","tooComplicatedTooManySteps","thumb-down"],["内容需要更新","outOfDate","thumb-down"],["翻译问题","translationIssue","thumb-down"],["示例/代码问题","samplesCodeIssue","thumb-down"],["其他","otherDown","thumb-down"]],[],[],[],null,["# Why TensorFlow\n==============\n\nWhether you're an expert or a beginner, TensorFlow is an end-to-end platform that makes it easy for you to build and deploy ML models. \n\nWatch the video\n\n[Case studies](/about/case-studies) \n*close* \n\nAn entire ecosystem to help you solve challenging, real-world problems with machine learning\n--------------------------------------------------------------------------------------------\n\n### Easy model building\n\nTensorFlow offers multiple levels of abstraction so you can choose the right one for your needs. Build and train models by using the high-level Keras API, which makes getting started with TensorFlow and machine learning easy.\n\nIf you need more flexibility, eager execution allows for immediate iteration and intuitive debugging. For large ML training tasks, use the Distribution Strategy API for distributed training on different hardware configurations without changing the model definition. \n[See resources](/guide/effective_tf2) \n*close* \n\n### Robust ML production anywhere\n\nTensorFlow has always provided a direct path to production. Whether it's on servers, edge devices, or the web, TensorFlow lets you train and deploy your model easily, no matter what language or platform you use.\n\nUse TFX if you need a full production ML pipeline. For running inference on mobile and edge devices, use TensorFlow Lite. Train and deploy models in JavaScript environments using TensorFlow.js. \n[See resources](/learn) \n*close* \n\n### Powerful experimentation for research\n\nBuild and train state-of-the-art models without sacrificing speed or performance. TensorFlow gives you the flexibility and control with features like the Keras Functional API and Model Subclassing API for creation of complex topologies. For easy prototyping and fast debugging, use eager execution.\n\nTensorFlow also supports an ecosystem of powerful add-on libraries and models to experiment with, including Ragged Tensors, TensorFlow Probability, Tensor2Tensor and BERT. \n[See resources](/guide/effective_tf2) \n*close* \n\nSee how companies are using TensorFlow\n--------------------------------------\n\nAirbnb \nCoca Cola \nDeepmind \nGE Healthcare \nGoogle \nIntel \nNERSC \nTwitter \n[See case studies](/about/case-studies) \n\nLearn how machine learning works\n--------------------------------\n\nDid you ever want to know how a neural network works? Or what the steps are to solving an ML problem? Don't worry, we've got you covered. Below is a quick overview of the fundamentals of machine learning. Or, if you're looking for a more in-depth information, head to our education page for beginner and advanced content. \n[Learn ML](/resources/learn-ml) \nIntro to ML Steps to solving an ML problem Anatomy of a neural network Training a neural network \n\n### Intro to ML\n\nMachine learning is the practice of helping software perform a task without explicit programming or rules. With traditional computer programming, a programmer specifies rules that the computer should use. ML requires a different mindset, though. Real-world ML focuses far more on data analysis than coding. Programmers provide a set of examples and the computer learns patterns from the data. You can think of machine learning as \"programming with data\". \n\n### Steps to solving an ML problem\n\nThere are multiple steps in the process of getting answers from data using ML. For a step-by-step overview, check out this [guide](https://developers.google.com/machine-learning/guides/text-classification/) that shows the complete workflow for text classification, and describes important steps like collecting a dataset, and training and evaluating a model with TensorFlow. \n\n### Anatomy of a neural network\n\nA neural network is a type of model that can be trained to recognize patterns. It is composed of layers, including input and output layers, and at least one [hidden layer](https://developers.google.com/machine-learning/glossary/#hidden_layer). Neurons in each layer learn increasingly abstract representations of the data. For example, in this visual diagram we see neurons detecting lines, shapes, and textures. These representations (or learned features) make it possible to classify the data. \n\n### Training a neural network\n\nNeural networks are trained by gradient descent. The weights in each layer begin with random values, and these are iteratively improved over time to make the network more accurate. A loss function is used to quantify how inaccurate the network is, and a procedure called backpropagation is used to determine whether each weight should be increased, or decreased, to reduce the loss. \n\nOur community\n-------------\n\nThe TensorFlow community is an active group of developers, researchers, visionaries, tinkerers and problem solvers. The door is always open to contribute, collaborate and share your ideas. \n[Learn more](/community) \n\nBuild, deploy, and experiment easily with TensorFlow\n----------------------------------------------------\n\n[Get started](/tutorials)"]]