irml.tar.gz

image-rec

If you want to dive into the technology behind computer vision and self driving cars, this is where to start.

In this course you'll learn how to process data from image files and create convolutional neural networks (CNNs) to classify different types of images. After completing this course, you will have a solid understanding of why CNNs work and which CNN architectures to use for different tasks.

The code for this course is built around the TensorFlow framework, one of the premier frameworks for industry machine learning, and the Python pandas library for data analysis. Knowledge of Python and TensorFlow are prerequisites. 

This course was created by AdaptiLab, a company specializing in evaluating, sourcing, and upskilling enterprise machine learning talent. It is built in collaboration with industry machine learning experts from Google, Microsoft, Amazon, and Apple.

Image Recognition with Machine Learning

Grayscale image data will have one channel, while RGB image data will have three

RGB image data will take on a larger range of pixel values than grayscale images

Grayscale image data uses negative pixel values while RGB data uses positive values

Grayscale and RGB data is the same, it is just interpreted differently by the code

How would we distinguish between grayscale and RGB image data?

How would we distinguish between grayscale and RGB image data?

The mapping function duplicated the data so we can iterate through the dataset multiple times

The mapping function converted raw contents from the image files into usable pixel data

A mapping function must always we used whenever we work with Tensorflow datasets

The mapping function splits the dataset into different batches

In the Dataset chapter, why did we apply a mapping function to the image dataset?

In the Dataset chapter, why did we apply a mapping function to the image dataset?

The iteration is halted and the dataset is deleted

The iteration goes back to beginning of the dataset

What happens when we try to iterate past the end of a dataset?

What happens when we try to iterate past the end of a dataset?

What you'll learn from this course

Image Processing

CNN

SqueezeNet

ResNet

Quiz