Gain insights into image data processing and CNNs for image classification using TensorFlow. Delve into CNN architectures and their applications, requiring Python and TensorFlow knowledge.

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

This saves a large amount of space compared to the regular data matrix format

Since CNNs have more layers than MLPs, the data needs to be in a different format

NHWC format is significantly faster to process than regular data matrix format

It puts the data in the proper format to be used with convolution layers

Why do we reshape the input data into NHWC format for a CNN?

Why do we reshape the input data into NHWC format for a CNN?

Taking absolute values via the ReLU function

Which mathematical operation is the main component of a convolution layer?

Which mathematical operation is the main component of a convolution layer?

It helps the CNN avoid overfitting by reducing the number of parameters in the model

Pooling is required for a convolution layer to work properly

Pooling is an extension of the convolution layers, so the weights are reinforced

What is the purpose of a pooling layer?

It helps each neuron depend on one another, reinforcing the best results

It increases the learning rate for a certain number of training steps

It randomly chooses a fraction of the neurons to drop, reducing neuron co-adaptation

It randomly drops certain training iterations from contributing to the overall loss

How does dropout help a neural network avoid overfitting?

How does dropout help a neural network avoid overfitting?

What you'll learn from this course

Image Processing

CNN

SqueezeNet

ResNet

Quiz