|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/deep-learning-in-practice-ii/
课程评论：没有评论
**课程名称：** 深度学习实践 II：迁移学习项目 **课程概述：** 本课程专为希望快速入门深度学习项目开发，但又希望回避繁琐的数学理论和编程任务的学习者设计。课程旨在提供一个自动化、无痛的深度学习解决方案开发流程。 **课程内容：** 该课程是“深度学习实践”系列课程的第二部分，专注于迁移学习和模型评估。学习者将掌握以下内容： * **管理复杂的深度学习项目：** 学习如何有效地组织和开展深度学习项目。 * **利用迁移学习开发模型：** 深入理解迁移学习的概念，并学习如何使用多种先进的卷积神经网络（CNN）算法进行模型开发。 * **开发可复用的项目：** 学习构建能够适应不同项目的深度学习解决方案。 * **自动化模型评估：** 掌握如何以自动化方式比较不同深度学习模型的性能并解读结果。 * **实际项目应用：** 通过真实世界的项目实例，学习如何在实践中应用迁移学习进行深度学习分类模型的训练。 * **简化的模型评估：** 使用预先配置好的库，轻松获得并解释模型的性能评估结果。 **课程亮点：** * 提供即用型 Google Colab Notebooks，包含所有课程代码。 * 课程代码可轻松改编和复用于任何分类项目，实现自动化开发。 * 适用于想要跳过基础理论，直接进行实践操作的学习者。 **系列课程介绍：** * **深度学习实践 I：基础与数据集设计：** 学习深度神经网络分类项目基础，以及如何为工业级深度学习项目设计数据集。 * **深度学习实践 II：迁移学习与模型评估：** 本课程。 * **深度学习实践 III：深度学习模型部署：** 学习如何在生产环境中部署深度学习模型，包括 Flask、Docker、Tensorflow Serving、Tensorflow JavaScript 和 Tensorflow Lite 等工业级部署技术。
You want to start developing deep learning solutions, but you do not want to lose time in mathematics and theory?You want to conduct deep learning projects, but do not like the hassle of tedious programming tasks?Do you want an automated process for developing deep learning solutions?This course is then designed for you! Welcome to Deep Learning in Practice, with NO PAIN!This course is the second course on a series of Deep Learning in Practice Courses of Anis Koubaa, namelyDeep Learning in Practice I: Basics and Dataset Design: the student will learn the basics of conducting a classification project using deep neural networks, then he learns about how to design a dataset for industrial-level professional deep learning projects. Deep Learning in Practice II: Transfer Learning and Models Evaluation: the student will learn how to manage complex deep learning projects and develop models using transfer learning using several state-of-the-art CNN algorithms. He will learn how to develop reusable projects and how to compare the results of different deep learning models in an automated manner. Deep Learning in Practice III: Deployment of Deep Learning Models: the student will learn how to deploy deep learning models in a production environment. We will present the deployment techniques used in industry such as Flask, Docker, Tensorflow Serving, Tensorflow JavaScript, and Tensorflow Lite, for deployment in a different environment. Despite important, this topic has little coverage in tutorials and documentations. Deep Learning in Practice II: Transfer Learning ProjectsThis course introduces you to transfer learning and demonstrate to you how to use transfer learning in real-world projects. In this course, I demonstrate how to conduct training of a deep learning classification model using transfer learning.Besides, you will learn how to evaluate the performance of a model with some pre-configured libraries that makes it easy to obtain the results and interpret them. I also provide ready-to-use Google Colab Notebooks with all codes used in this course.The same code can be easily adapted and reused for any classification project in an automated way.
