|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/custom-models-layers-loss-functions-with-tensorflow
课程评论：没有评论
课程名称：使用TensorFlow构建自定义模型、层和损失函数 课程概述： 在本课程中，您将学习： - 比较功能性API和顺序API，探索使用功能性API可以构建的新模型，并构建一个能够产生多个输出的模型，包括一个西默斯网络。 - 构建自定义损失函数（包括西默斯网络中使用的对比损失函数），以衡量模型的效果并帮助神经网络从训练数据中学习。 - 在现有标准层的基础上创建自定义层，为您的模型自定义网络层，了解它们之间的差异，学习自定义层的组成，以及激活函数的使用。 - 在现有模型的基础上添加自定义功能，学习如何定义自己的自定义类，而不是使用功能性或顺序API，构建可以从TensorFlow模型类继承的模型，并通过定义自定义模型类构建残差网络（ResNet）。 深度学习人工智能的TensorFlow：进阶技术专业化课程介绍了TensorFlow的功能，使学习者可以更好地控制其模型架构，并提供帮助他们创建和训练高级机器学习模型的工具。 本专业化课程适合具备TensorFlow基础知识的初中级软件和机器学习工程师，旨在通过学习高级TensorFlow特性来扩展知识和技能，从而构建强大的模型。 课程大纲： 1. 功能性API - 描述：比较功能性API和顺序API的不同，了解功能性API在设计模型时提供的额外灵活性。实践使用功能性API，构建西默斯网络！ 2. 自定义损失函数 - 描述：损失函数用于衡量模型的表现，并帮助神经网络从训练数据中学习。学习如何构建自定义损失函数，包括西默斯网络中使用的对比损失函数。 3. 自定义层 - 描述：自定义层使您能够实现使用非标准层的模型。实践在现有标准层的基础上构建自定义层。 4. 自定义模型 - 描述：您可以在现有模型的基础上添加自定义功能。本周，扩展TensorFlow模型类以构建ResNet模型！ 5. 附加内容 - 回调 - 描述：自定义回调允许您自定义模型的输出或在训练过程中的行为。本周，实施一个自定义回调，以在检测到过拟合时停止训练。
Part: 1
Title:Functional APIs
Description:Compare how the Functional API differs from the Sequential API, and see how the Functional API gives you additional flexibility in designing models. Practice using the functional API and build a Siamese network!
Part: 2
Title:Custom Loss Functions
Description:Loss functions help measure how well a model is doing, and are used to help a neural network learn from the training data. Learn how to build custom loss functions, including the contrastive loss function that is used in a Siamese network.
Part: 3
Title:Custom Layers
Description:Custom layers give you the flexibility to implement models that use non-standard layers. Practice building off of existing standard layers to create custom layers for your models.
Part: 4
Title:Custom Models
Description:You can build off of existing models to add custom functionality. This week, extend the TensorFlow Model Class to build a ResNet model!
Part: 5
Title:Bonus Content - Callbacks
Description:Custom callbacks allow you to customize what your model outputs or how it behaves during training. This week, implement a custom callback to stop training once the callback detects overfitting.
In this course, you will: • Compare Functional and Sequential APIs, discover new models you can build with the Functional API, and build a model that produces multiple outputs including a Siamese network. • Build custom loss functions (including the contrastive loss function used in a Siamese network) in order to measure how well a model is doing and help your neural network learn from training data. • Build off of existing standard layers to create custom layers for your models, customize a network layer with a lambda layer, understand the differences between them, learn what makes up a custom layer, and explore activation functions. • Build off of existing models to add custom functionality, learn how to define your own custom class instead of using the Functional or Sequential APIs, build models that can be inherited from the TensorFlow Model class, and build a residual network (ResNet) through defining a custom model class. The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture and tools that help them create and train advanced ML models. This Specialization is for early and mid-career software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models.
