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 hyperparameters 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.
Overview
Syllabus
- Introduction
- Course Introduction
- Introduction to Computer Vision and Pre-built ML Models for Image Classification
- What Is Computer Vision
- Different Type of Computer Vision Problems
- Computer Vision Use Cases
- Vision API - Pre-built ML Models
- Lab Introduction - Detecting Labels, Faces, and Landmarks in Images with the Cloud Vision API
- Detecting Labels, Faces, and Landmarks in Images with the Cloud Vision API
- Lab Introduction - Lab: Extracting Text from the images using the Google Cloud Vision API
- Extracting Text from the Images using the Google Cloud Vision API
- Readings
- Quiz
- Vertex AI and AutoML Vision on Vertex AI
- What is Vertex AI and why does a unified platform matter?
- Introduction to AutoML Vision on Vertex AI
- How does Vertex AI help with the ML workflow, part 1 ?
- How does Vertex AI help with the ML workflow, part 2 ?
- Which vision product is right for you ?
- Lab Introduction - Identifying Damaged Car Parts with Vertex AI for AutoML Vision users
- Identifying Damaged Car Parts with Vertex AI for AutoML Vision Users
- Readings
- Quiz
- Custom Training with Linear, Neural Network and Deep Neural Network models
- Introduction
- Introduction to Linear Models
- Reading the Data
- Implementing Linear Models for Image Classification
- Lab Introduction - Classifying Images with a Linear Model
- Classifying Images with a Linear Model
- Neural Networks and Deep Neural Networks for Image Classification
- Lab Introduction - Classifying Images with a NN and DNN Model
- Classifying Images with a NN and DNN Model
- Deep Neural Networks with Dropout and Batch Normalization
- Lab Introduction - Classifying Images using Dropout and Batchnorm Layer
- Classifying Images using Dropout and Batchnorm Layer
- Readings
- Quiz
- Convolutional Neural Networks
- Introduction
- Convolutional Neural Networks
- Understanding Convolutions
- CNN Model Parameters
- Working with Pooling Layers
- Implementing CNNs on Vertex AI with pre-built TF container using Vertex Workbench
- Lab Introduction - Classifying Images with pre-built TF Container on Vertex AI
- Classifying Images with pre-built TF Container on Vertex AI
- Readings
- Quiz
- Dealing with Image Data
- Introduction
- Preprocessing the Image Data
- Model Parameters and the Data Scarcity Problem
- Data Augmentation
- Lab Introduction - Classifying Images using Data Augmentation
- Classifying Images using Data Augmentation
- Transfer Learning
- Lab Introduction - Classifying Images with Transfer Learning
- Classifying Images with Transfer Learning
- Readings
- Quiz
- Summary
- Summary
- Readings
- Your Next Steps
- Course Badge
