Computer Vision Fundamentals with Google Cloud
This course describes different types of computer vision use cases and then highlights different machine learning strategies for solving these use cases.
What you'll learn
This course describes different types of computer vision use cases and then highlights different machine learning strategies for solving these use cases. The strategies vary from experimenting with pre-built ML models through pre-built ML APIs and AutoML Vision to building custom image classifiers using linear models, deep neural network (DNN) models or convolutional neural network (CNN) models. The course shows how to improve a model's accuracy with augmentation, feature extraction, and fine-tuning hyper-parameters while trying to avoid overfitting the data.
The course also looks at practical issues that arise, for example, when one doesn't have enough data and how to incorporate the latest research findings into different models. Learners will get hands-on practice building and optimizing their own image classification models on a variety of public datasets in the labs they will work on.
Table of contents
- What Is Computer Vision 4m
- Different Type of Computer Vision Problems 6m
- Computer Vision Use Cases 4m
- Vision API - Pre-built ML Models 12m
- Lab Introduction - Detecting Labels, Faces, and Landmarks in Images with the Cloud Vision API 0m
- Pluralsight: Getting Started with GCP and Qwiklabs 4m
- Lab: Detecting Labels, Faces, and Landmarks in Images with the Cloud Vision API 0m
- Lab Introduction - Lab: Extracting Text from the images using the Google Cloud Vision API 1m
- Lab: Extracting Text from the Images using the Google Cloud Vision API 0m
- Readings 0m
- What is Vertex AI and why does a unified platform matter? 5m
- Introduction to AutoML Vision on Vertex AI 3m
- How does Vertex AI help with the ML workflow, part 1 ? 5m
- How does Vertex AI help with the ML workflow, part 2 ? 7m
- Which vision product is right for you ? 5m
- Lab Introduction - Identifying Damaged Car Parts with Vertex AI for AutoML Vision users 0m
- Lab: Identifying Damaged Car Parts with Vertex AI for AutoML Vision Users 0m
- Readings 0m
- Introduction 5m
- Introduction to Linear Models 3m
- Reading the Data 9m
- Implementing Linear Models for Image Classification 15m
- Lab Introduction - Classifying Images with a Linear Model 0m
- Lab: Classifying Images with a Linear Model 0m
- Neural Networks and Deep Neural Networks for Image Classification 8m
- Lab Introduction - Classifying Images with a NN and DNN Model 0m
- Lab: Classifying Images with a NN and DNN Model 0m
- Deep Neural Networks with Dropout and Batch Normalization 8m
- Lab Introduction - Classifying Images using Dropout and Batchnorm Layer 0m
- Lab: Classifying Images using Dropout and Batchnorm Layer 0m
- Readings 0m
- Introduction 2m
- Convolutional Neural Networks 7m
- Understanding Convolutions 12m
- CNN Model Parameters 12m
- Working with Pooling Layers 5m
- Implementing CNNs on Vertex AI with pre-built TF container using Vertex Workbench 5m
- Lab: Classifying Images with pre-built TF Container on Vertex AI 0m
- Readings 0m
- Introduction 1m
- Preprocessing the Image Data 6m
- Model Parameters and the Data Scarcity Problem 5m
- Data Augmentation 8m
- Lab Introduction - Classifying Images using Data Augmentation 0m
- Lab: Classifying Images using Data Augmentation 0m
- Transfer Learning 7m
- Lab Introduction - Classifying Images with Transfer Learning 0m
- Lab: Classifying Images with Transfer Learning 0m
- Readings 0m
