|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/image-understanding-tensorflow-gcp
课程评论：没有评论
课程名称：使用TensorFlow在GCP上进行图像理解 概述：本课程是GCP高级机器学习专业化的第三门课程。我们将探讨使用卷积神经网络构建图像分类器的不同策略。通过数据增强、特征提取和超参数微调，提升模型的准确性，并尽量避免过拟合。此外，我们还将讨论在数据不足时遇到的实际问题，以及如何将最新的研究成果融入我们的模型中。 您将通过实验室实践，动手构建和优化自己的图像分类模型，并使用多种公共数据集进行学习。 课程先决条件：基础SQL，了解Python和TensorFlow 课程大纲： 1. 介绍 - 课程介绍 2. 计算机视觉概述及预构建的机器学习模型用于图像分类 - 计算机视觉和预构建的图像分类模型简介 3. Vertex AI及其自动机器学习视觉 - 学习Vertex AI及其上的自动机器学习视觉 4. 用线性、神经网络和深度神经网络模型进行自定义训练 - 学习以线性、神经网络和深度神经网络模型进行自定义训练 5. 卷积神经网络 - 学习卷积神经网络的相关知识 6. 处理图像数据 - 学习如何处理图像数据 7. 总结 - 课程总结
Name:Introduction
Description:Course Introduction
Name:Introduction to Computer Vision and Pre-built ML Models for Image Classification
Description:Introduction to Computer Vision and Pre-built ML Models for Image Classification
Name:Vertex AI and AutoML Vision on Vertex AI
Description:Learn about Vertex AI and AutoML Vision on Vertex AI
Name:Custom Training with Linear, Neural Network and Deep Neural Network models
Description:Learn about Custom Training with Linear, Neural Network and Deep Neural Network models
Name:Convolutional Neural Networks
Description:Learn about Convolutional Neural Networks
Name:Dealing with Image Data
Description:Learn about dealing with Image Data
Name:Summary
Description:Course Summary
This is the third course of the Advanced Machine Learning on GCP specialization. In this course, We will take a look at different strategies for building an image classifier using convolutional neural networks. We'll improve the model's accuracy with augmentation, feature extraction, and fine-tuning hyperparameters while trying to avoid overfitting our data. We will also look at practical issues that arise, for example, when you don’t have enough data and how to incorporate the latest research findings into our models. You will get hands-on practice building and optimizing your own image classification models on a variety of public datasets in the labs we’ll work on together. Prerequisites: Basic SQL, familiarity with Python and TensorFlow
