We may earn an affiliate commission when you visit our partners.
Hadelin de Ponteves, SuperDataScience Team, and Luka Anicin

欢迎来到TensorFlow 2.0!

刚刚发布的TensorFlow 2.0引入了诸多功能来简化模型的开发和维护过程。在教学方面,通过将许多复杂概念进行简化来增进人们的理解。从工业界的角度,模型变得更容易理解、维护和开发。

深度学习是人工智能发展最快的领域之一。在过去几年中,我们已经证实深度学习模型,即使是最简单的模型,也能够解决非常困难和复杂的问题。如今,随着深度学习的流行语时代成为过去时,人们正在不断释放其威力和潜能,用来改进他们的产品。

本课程的结构设计涵盖包括从神经网络建模,训练,到将模型投入生产环境的全部主题。

在课程的第1部分,您会了解到贯穿我们整个课程的技术栈(第1节),以及TensorFlow 2.0库的基础和语法(第2节)。

在课程的第2部分,我们将进入激动人心的深度学习领域。在这部分的课程中,您将亲手实现若干类型的神经网络(全连接神经网络(第3节),卷积神经网络(第4节),递归神经网络(第5节))。在这部分的尾声,第6节,您将学习并创建这些神经网络的迁移学习应用,这些应用在“猫狗分类”数据集上取得了目前最为领先(SOTA)的结果。

在完成课程第2部分,并最终掌握如何实现神经网络之后,您将在课程的第3部分学习如何利用强化学习,尤其是深度-Q学习,来构造自己的股票市场交易机器人模型。

Read more

欢迎来到TensorFlow 2.0!

刚刚发布的TensorFlow 2.0引入了诸多功能来简化模型的开发和维护过程。在教学方面,通过将许多复杂概念进行简化来增进人们的理解。从工业界的角度,模型变得更容易理解、维护和开发。

深度学习是人工智能发展最快的领域之一。在过去几年中,我们已经证实深度学习模型,即使是最简单的模型,也能够解决非常困难和复杂的问题。如今,随着深度学习的流行语时代成为过去时,人们正在不断释放其威力和潜能,用来改进他们的产品。

本课程的结构设计涵盖包括从神经网络建模,训练,到将模型投入生产环境的全部主题。

在课程的第1部分,您会了解到贯穿我们整个课程的技术栈(第1节),以及TensorFlow 2.0库的基础和语法(第2节)。

在课程的第2部分,我们将进入激动人心的深度学习领域。在这部分的课程中,您将亲手实现若干类型的神经网络(全连接神经网络(第3节),卷积神经网络(第4节),递归神经网络(第5节))。在这部分的尾声,第6节,您将学习并创建这些神经网络的迁移学习应用,这些应用在“猫狗分类”数据集上取得了目前最为领先(SOTA)的结果。

在完成课程第2部分,并最终掌握如何实现神经网络之后,您将在课程的第3部分学习如何利用强化学习,尤其是深度-Q学习,来构造自己的股票市场交易机器人模型。

课程第4部分全部是关于TensorFlow Extended (TFX)的内容。在这部分课程中,您会学习如何处理数据,并创建用于生产的数据流水线。在第8节,我们将通过TensorFlow Data Validation库查看数据集是否存在异常,在这之后的第9节,我们会通过TensorFlow Transform库来构造数据预处理流水线。

在课程第10节,您会通过Flask Python库和训练好的模型,来学习和创建自己的Fashion API。在这一节中,您将更好的了解如何通过互联网向一个模型发送请求。但是在这个阶段,以模型为中心的体系并不能扩展到能够接受数百万的请求。那么当我们进入第11节,在这部分课程中,您将学习如何通过TensorFlow Serving库来改进我们前一节的解决方案。您将轻松学习并创建能够支持每日数百万请求的图像分类API!

当前,在Android和iOS应用中使用深度学习模型正在变得逐渐流行,但神经网络需要大量的耗电以及资源!这时,TensorFlow Lite库就要发挥作用了。在课程第12节,您将学习对神经网络进行优化和转换,以适应移动设备的要求。

在本课程的尾声,即课程第5部分,在第13节中您将学习如何通过TensorFlow 2.0库,将任意神经网络的训练分布到多个GPU,甚至是服务器上。

Enroll now

What's inside

Learning objectives

  • 如何在数据科学中使用tensorflow 2.0
  • Tensorflow 1.x和tensorflow 2.0之间的重要差异
  • 如何在tensorflow 2.0中实现人工神经网络
  • 如何在tensorflow 2.0中实现卷积神经网络
  • 如何在tensorflow 2.0中实现递归神经网络
  • 如何在tensorflow 2.0中构建你自己的迁移学习应用
  • 如何通过强化学习(深度-q网络)来构建股票市场交易机器人
  • 如何在tensorflow 2.0中构造机器学习流水线
  • 如何通过tensorflow data validation和tensorflow transform进行数据验证和数据集预处理
  • 将tensorflow 2.0模型放入生产
  • 如何利用flask和tensorflow 2.0创造一个fashion api
  • 如何通过restful api为tensorflow模型提供服务
  • Show more
  • Show less

Syllabus

课程体系 & Colab工具箱
TensorFlow 2.0 基础
引言
欢迎来到TensorFlow 2.0 课程! 了解课程结构和TF工具箱
Read more
从TensorFlow 1.x 到 TensorFlow 2.0
常量, 变量, 张量
张量运算
字符串
人工神经网络
项目设置
数据预处理
评估迁移学习结果
构建人工神经网络
评估人工神经网络
人工神经网络测验
家庭作业: 人工神经网络
家庭作业解答: 人工神经网络
卷积神经网络
项目设置 & 数据预处理
训练和评估递归神经网络
构建卷积神经网络
训练和评估卷积神经网络
卷积神经网络测验
家庭作业: 卷积神经网络
家庭作业解答: 卷积神经网络
递归神经网络
构建递归神经网络
递归神经网络测验
迁移学习和微调
什么是迁移学习?
加载 MobileNet V2 模型
冻结预训练模型
为预训练模型添加自定义头
定义迁移学习模型
编译迁移学习模型
图像数据生成器
迁移学习
微调模型定义
编译微调模型
微调
评估微调结果
迁移学习测验
深度强化学习理论
什么是强化学习?
贝尔曼方程
马尔可夫决策过程 (MDP)
Q-学习直觉力
时间差分
深度Q-学习直觉力 - 步骤 1
深度Q-学习直觉力 - 步骤 2
经验回放
动作选择策略
用于股票市场交易的深度强化学习
AI 交易员 - 步骤 1
AI 交易员 - 步骤 2
AI 交易员 - 步骤 3
AI 交易员 - 步骤 4
AI 交易员 - 步骤 5
数据集加载模块函数
状态创建模块函数
加载数据集
定义模型
训练循环 - 步骤 1
训练循环 - 步骤 2
使用TensorFlow Data Validation (TFDV)进行数据验证
加载污染数据集
创建数据集 Schema
计算测试集统计信息
使用TensorFlow Data Validation进行异常检测
为生产准备 Schema
保存 Schema
下一步做什么? TEXT
使用TensorFlow Transform (TFT)进行数据集预处理
初始数据集预处理
数据集元数据
预处理函数
数据集预处理流水线
通过Flask和TensorFlow 2.0创建Fashion API
导入项目依赖
加载预训练模型
定义Flask应用
创建分类函数
开始Flask应用
通过网络给模型发送API请求
通过TensorFlow Serving创建图像分类API
什么是TensorFlow Serving?
TensorFlow Serving结构
数据集预处理
定义,训练和评估模型
为生产保存模型

Save this course

Save TensorFlow 2.0: 关于全新TensorFlow的完整指南 to your list so you can find it easily later:
Save

Activities

Coming soon We're preparing activities for TensorFlow 2.0: 关于全新TensorFlow的完整指南. These are activities you can do either before, during, or after a course.

Career center

Learners who complete TensorFlow 2.0: 关于全新TensorFlow的完整指南 will develop knowledge and skills that may be useful to these careers:

Reading list

We haven't picked any books for this reading list yet.
Provides practical recipes to help you get started with reinforcement learning using TensorFlow 2.0. It covers topics like Markov decision processes, Q-learning, and deep reinforcement learning.
Covers the fundamentals of deep learning and how to use TensorFlow 2.0 and Keras to build and train deep learning models. It's a great resource for beginners who want to get started with deep learning.
Provides a hands-on introduction to deep learning using the Python programming language. It is written by the creator of the Keras deep learning library and is known for its practical examples and clear explanations.
Provides a comprehensive overview of deep learning for climate science, covering the fundamental concepts, algorithms, and applications. It is written by a leading researcher in the field and is known for its clear explanations and hands-on approach.
Provides a comprehensive overview of deep learning for natural language processing, covering the fundamental concepts, algorithms, and applications. It is written by a leading researcher in the field and is considered one of the most authoritative resources on deep learning for NLP.
Provides a comprehensive overview of deep learning for robotics, covering the fundamental concepts, algorithms, and applications. It is written by a leading researcher in the field and is known for its clear explanations and hands-on approach.
Provides a comprehensive overview of deep learning for finance, covering the fundamental concepts, algorithms, and applications. It is written by a leading researcher in the field and is known for its clear explanations and hands-on approach.
Provides a comprehensive overview of deep learning for materials science, covering the fundamental concepts, algorithms, and applications. It is written by a leading researcher in the field and is known for its clear explanations and hands-on approach.
Provides a comprehensive overview of deep learning, covering the fundamental concepts, algorithms, and applications. It is written by three leading researchers in the field and is considered one of the most authoritative resources on deep learning.
Provides a comprehensive overview of deep learning for transportation, covering the fundamental concepts, algorithms, and applications. It is written by a leading researcher in the field and is known for its clear explanations and hands-on approach.
Provides a comprehensive overview of deep learning for genomics, covering the fundamental concepts, algorithms, and applications. It is written by a leading researcher in the field and is known for its clear explanations and hands-on approach.
作为一本中文著作,深入浅出地讲解了深度学习的原理、算法和应用,适合作为入门或进阶的学习教材。
Provides a practical guide to deep learning for computer vision, focusing on the design and implementation of deep learning models for image and video processing. It is written by a leading researcher in the field and is known for its clear explanations and hands-on approach.
This practical guide provides a comprehensive overview of deep learning, using Python and the Keras library. It covers a wide range of topics, including convolutional neural networks, recurrent neural networks, and generative adversarial networks. It is suitable for beginners and experienced practitioners alike.
This advanced textbook provides a comprehensive and rigorous treatment of neural networks, covering topics such as supervised learning, unsupervised learning, and deep learning. It is suitable for graduate students and researchers with a strong background in mathematics and statistics.
This practical guide provides a hands-on introduction to machine learning, including neural networks. It covers a wide range of topics, including data preprocessing, feature engineering, model selection, and evaluation. It is suitable for beginners and experienced practitioners alike.
Authored by three leading researchers in the field, this advanced textbook provides a comprehensive and rigorous treatment of deep learning, covering topics such as convolutional neural networks, recurrent neural networks, and generative adversarial networks. It is suitable for graduate students and researchers with a strong background in machine learning.

Share

Help others find this course page by sharing it with your friends and followers:

Similar courses

Similar courses are unavailable at this time. Please try again later.
Our mission

OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.

Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.

Find this site helpful? Tell a friend about us.

Affiliate disclosure

We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.

Your purchases help us maintain our catalog and keep our servers humming without ads.

Thank you for supporting OpenCourser.

© 2016 - 2025 OpenCourser