From the course: Deep Learning: Image Recognition
Join today to access over 22,700 courses taught by industry experts or purchase this course individually.
Recognizing image contents with a neural network - Python Tutorial
From the course: Deep Learning: Image Recognition
Recognizing image contents with a neural network
- [Instructor] Let's look at how to train the neural network to recognize images. Before we can use the neural network to make classifications we need to train it. Let's pretend that we're training a simple neural network that can recognize the handwritten number eight. To do this we need to collect the dataset of training images. We need lots of images that belong to the class that we wanna recognize. In this case we'll collect 1000 images of the letter eight written by lots of different people. We also need lots of images that represent the other possible kinds of images that we'll see. That way the neural network can learn to tell the two different types or classes of images apart. So we'll also collect 1000 images of other numbers as part of our training dataset. Now that we have training data we can train the neural network by showing it images and telling it what the correct answer will be for each one. So we'll start by showing it some eights and telling it the answer should be…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.