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。
TensorFlow 简介
借助 TensorFlow，初学者和专家可以轻松创建适用于桌面、移动、Web 和云环境的机器学习模型。请参阅以下几部分，了解如何开始使用。
TensorFlow
通过面向初学者和专家的教程学习 TensorFlow 基础知识，并运用这些知识创建下一个机器学习项目。
针对 Web
通过 TensorFlow.js 使用 JavaScript 创建新的机器学习模型和部署现有模型。
针对移动设备和边缘设备
Run inference with LiteRT on mobile and embedded devices like Android, iOS, Edge TPU, and Raspberry Pi.
针对生产
使用 TFX 部署可用于生产环境的机器学习流水线，以用于训练和推断。
准备和加载数据以获得成功的机器学习结果
数据可能是决定机器学习工作能否成功的最重要因素。
TensorFlow 提供了多种数据工具，可以帮助您大规模整合、清理和预处理数据：
利用 TensorFlow 生态系统构建和微调模型
探索基于 Core 框架构建的整个生态系统，Core 框架能够简化模型的构建、训练和导出过程。借助 Keras 等 API，TensorFlow 可支持分布式训练、快速模型迭代和轻松调试。模型分析和 TensorBoard 等工具可以帮助您在模型的整个生命周期中跟踪开发和改进情况。
如需快速入门，不妨前往 TensorFlow Hub 寻找 Google 和社区提供的一系列预训练模型，或者前往 Model Garden 获取先进研究模型的实现。您可以从这些高层级组件库中获得强大的模型，并使用新数据对这些模型进行微调；您也可以对它们进行自定义，以执行新的任务。
在设备上、浏览器中、本地或云端部署模型
TensorFlow provides robust capabilities to deploy your models on any environment - servers, edge devices, browsers, mobile, microcontrollers, CPUs, GPUs, FPGAs. TensorFlow Serving can run ML models at production scale on the most advanced processors in the world, including Google's custom Tensor Processing Units (TPUs).
If you need to analyze data close to its source to reduce latency and improve data privacy, the LiteRT framework lets you run models on mobile devices, edge computing devices, and even microcontrollers, and the TensorFlow.js framework lets you run machine learning with just a web browser.
实现适用于生产型机器学习的 MLOps
TensorFlow 平台可帮助您落实数据自动化、模型跟踪、性能监控和模型再训练的最佳实践。
在产品、服务或业务流程的生命周期中使用生产级工具自动化和跟踪模型训练对取得成功来说至关重要。TFX 可为完整 MLOps 部署提供软件框架和工具，并在数据和模型随时间推移不断演变的过程中检测问题。
[null,null,[],[],[],null,["# Introduction to TensorFlow\n==========================\n\nTensorFlow makes it easy for beginners and experts to create machine learning models for desktop, mobile, web, and cloud. See the sections below to get started. \n\n#### TensorFlow\n\nLearn the foundations of TensorFlow with tutorials for beginners and experts to help you create your next machine learning project. \n[Learn more](/tutorials) \n\n#### For Web\n\nUse TensorFlow.js to create new machine learning models and deploy existing models with JavaScript. \n[Learn more](/js) \n\n#### For Mobile \\& Edge\n\nRun inference with LiteRT on mobile and embedded devices like Android, iOS, Edge TPU, and Raspberry Pi. \n[Learn more](https://ai.google.dev/edge/litert) \n\n#### For Production\n\nDeploy a production-ready ML pipeline for training and inference using TFX. \n[Learn more](/tfx) \n\nAn end-to-end platform for machine learning\n-------------------------------------------\n\n### Prepare and load data for successful ML outcomes\n\nData can be the most important factor in the success of your ML endeavors.\nTensorFlow offers multiple data tools to help you consolidate, clean and preprocess data at scale:\n\n- [Standard datasets](https://www.tensorflow.org/datasets) for initial training and validation\n- Highly scalable [data pipelines](https://www.tensorflow.org/guide/data) for loading data\n- [Preprocessing layers](https://www.tensorflow.org/guide/keras/preprocessing_layers) for common input transformations\n- Tools to [validate](https://www.tensorflow.org/tfx/guide/tfdv) and [transform](https://www.tensorflow.org/tfx/guide/tft) large datasets\n\nAdditionally, [responsible AI](https://www.tensorflow.org/responsible_ai) tools help you uncover and eliminate bias in your data to produce fair, ethical outcomes from your models. \n\n#### Try it in Colab\n\n[Load and preprocess an image dataset](https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/load_data/images.ipynb) [Investigate and visualize datasets](https://colab.research.google.com/github/tensorflow/tfx/blob/master/docs/tutorials/data_validation/tfdv_basic.ipynb) \n\n### Build and fine-tune models with the TensorFlow ecosystem\n\nExplore an entire ecosystem built on the [Core framework](https://www.tensorflow.org/guide/basics) that streamlines model construction, training, and export. TensorFlow supports distributed training, immediate model iteration and easy debugging with [Keras](https://keras.io/), and much more. Tools like [Model Analysis](https://www.tensorflow.org/tfx/guide/tfma) and [TensorBoard](https://www.tensorflow.org/tensorboard) help you track development and improvement through your model's lifecycle. \n\nTo help you get started, find collections of pre-trained models at [TensorFlow Hub](https://www.tensorflow.org/hub) from Google and the community, or implementations of state-of-the art research models in the [Model Garden](https://www.tensorflow.org/guide/model_garden). These libraries of high level components allow you to take powerful models, and fine-tune them on new data or customize them to perform new tasks. \n\n#### Try it in Colab\n\n[Train a neural network to classify images](https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/keras/classification.ipynb) [Retrain an image classifier with transfer learning](https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/tf2_image_retraining.ipynb) \n\n### Deploy models on-device, in the browser, on-prem, or in the cloud\n\nTensorFlow provides robust capabilities to deploy your models on any environment - servers, edge devices, browsers, mobile, microcontrollers, CPUs, GPUs, FPGAs. [TensorFlow Serving](https://www.tensorflow.org/tfx/guide/serving) can run ML models at production scale on the most advanced processors in the world, including Google's custom Tensor Processing Units (TPUs). \n\nIf you need to analyze data close to its source to reduce latency and improve data privacy, the [LiteRT](https://ai.google.dev/edge/litert/guide#1_choose_a_model) framework lets you run models on mobile devices, edge computing devices, and even microcontrollers, and the [TensorFlow.js](https://www.tensorflow.org/js) framework lets you run machine learning with just a web browser. \n\n#### Try it in Colab\n\n[Serve a model with TensorFlow Serving](https://colab.research.google.com/github/tensorflow/tfx/blob/master/docs/tutorials/serving/rest_simple.ipynb) \n\n### Implement MLOps for production ML\n\nThe TensorFlow platform helps you implement best practices for data automation, model tracking, performance monitoring, and model retraining. \n\nUsing production-level tools to automate and track model training over the lifetime of a product, service, or business process is critical to success. [TFX](https://www.tensorflow.org/tfx) provides software frameworks and tooling for full MLOps deployments, detecting issues as your data and models evolve over time. \n\n#### Try it in Colab\n\n[Create and run a simple TFX pipeline](https://colab.research.google.com/github/tensorflow/tfx/blob/master/docs/tutorials/tfx/penguin_simple.ipynb) [Track lineage with ML Metadata](https://colab.research.google.com/github/tensorflow/tfx/blob/master/docs/tutorials/mlmd/mlmd_tutorial.ipynb) \n\nLooking to expand your ML knowledge?\n------------------------------------\n\nTensorFlow is easier to use with a basic understanding of machine learning principles and core concepts. Learn and apply fundamental machine learning practices to develop your skills. \n[Learn ML](/resources/learn-ml) \nBegin with curated curriculums to improve your skills in foundational ML areas. \n[Learn more](/resources/learn-ml) \n\nGet started with TensorFlow\n---------------------------\n\n[Explore tutorials](/tutorials)"]]
