Image Understanding with TensorFlow on GCP
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.
What you'll learn
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.
Table of contents
- Introduction 7m
- Linear Models 7m
- Lab Intro:Linear Models for Image Classification 1m
- Lab: Image Classification with a Linear Model 0m
- Lab Solution:Linear Models for Image Classification 12m
- DNN Models Review 4m
- Lab Intro:DNN Models for Image Classification 1m
- Lab: Image Classification with a Deep Neural Network Model 0m
- Lab Solution:DNN Models for Image Classification 20m
- Review:What is Dropout? 3m
- Lab Intro:DNNs with Dropout Layer for Image Classification 0m
- Lab: Image Classification with a DNN Model with Dropout 0m
- Lab Solution:DNNs with Dropout Layer for Image Classification 12m
- Introduction 6m
- Understanding Convolutions 8m
- CNN Model Parameters 5m
- Working with Pooling Layers 3m
- Implementing CNNs with TensorFlow 4m
- Lab Intro:Creating an Image Classifier with a Convolutional Neural Network 2m
- Lab: Image Classification with a CNN Model 0m
- Lab Solution:Creating an Image Classifier with a Convolutional Neural Network 10m
- The Data Scarcity Problem 6m
- Data Augmentation 9m
- Lab Intro:Implementing image augmentation 1m
- Lab: Image Augmentation in TensorFlow 0m
- Lab Solution:Implementing image augmentation 3m
- Transfer Learning 5m
- Lab Intro:Implementing Transfer Learning 1m
- Image Classification Transfer Learning with Inception v3 0m
- Lab Solution:Implementing Transfer Learning 8m
- No Data, No Problem 2m
- Introduction 1m
- Pre-built ML Models 6m
- Cloud Vision API 2m
- Demo:Vision API 1m
- AutoML Vision 1m
- Demo:AutoML 5m
- AutoML Architecture 2m
- Lab Intro:Training with Pre-built ML Models using Cloud Vision API and AutoML 1m
- Lab: Training with Pre-built ML Models using Cloud Vision API and AutoML 0m
- Lab Solution:Training with Pre-built ML Models using Cloud Vision API and AutoML 14m
