Overview
-
Learn how to design, build, and deploy a deep neural network to serve as an image recognition system.
Syllabus
-
Introduction
- Build cutting-edge image recognition systems
- What you should know
- Exercise files
- Installing Python 3, Keras, and TensorFlow on macOS
- Installing Python 3, Keras, and TensorFlow on Windows
- What is a neural network?
- Coding a neural network with Keras
- Feeding images into a neural network
- Recognizing image contents with a neural network
- Adding convolution for translational invariance
- Designing a neural network architecture for image recognition
- Exploring the CIFAR-10 data set
- Loading an image data set
- Dense layers
- Convolution layers
- Max pooling
- Dropout
- A complete neural network for image recognition
- Setting up a neural network for training
- Training a neural network and saving weights
- Making predictions with the trained neural network
- Pre-trained neural networks included with Keras
- Using a pre-trained network for object recognition
- Transfer learning as an alternative to training a new neural network
- Extracting features with a pre-trained neural network
- Training a new neural network with extracted features
- Making predictions with transfer learning
- When to use an API instead of building your own solution
- Introduction to the Google Cloud Vision API
- Setting up Google Cloud Vision account credentials
- Recognizing objects in photographs with Google Cloud Vision
- Extracting text from images with Google Cloud Vision
- Next steps
