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

<h2 class="section-title">Chapter Goals:</h2>
<ul>
	<li>Convert the NHWC format data into a batch of flattened vectors</li>
	<li>Apply a fully-connected layer to the flattened data</li>
</ul>


<h2>A. Fully-connected layer</h2>

<div id="section1_l6" class="collapse show">
<p>We apply a fully-connected layer of size 1024 (i.e. the number of neurons in the layer) to the output data of the second pooling layer. The number of units is somewhat arbitrary. Enough to be powerful, but not so much as to be too resource intensive. The purpose of the fully-connected layer is to aggregate the data features before we convert them to logits. This allows the model to make better predictions than if we had just converted the pooling output directly to logits. We'll use those logits in a later chapter</p>
</div>



<h2>Chapter Goals:</h2>
<ul>
	<li>Convert the NHWC format data into a batch of flattened vectors</li>
	<li>Apply a fully-connected layer to the flattened data</li>
</ul>


<h2>A. Fully-connected layer</h2>

<div id="section1_l6">
<p>We apply a fully-connected layer of size 1024 (i.e. the number of neurons in the layer) to the output data of the second pooling layer. The number of units is somewhat arbitrary. Enough to be powerful, but not so much as to be too resource intensive. The purpose of the fully-connected layer is to aggregate the data features before we convert them to logits. This allows the model to make better predictions than if we had just converted the pooling output directly to logits. We'll use those logits in a later chapter</p>
</div>



Understand how fully-connected layers can be used to aggregate and flatten data.

What you'll learn from this course

Image Processing

CNN

SqueezeNet

ResNet

Fully-Connected

Chapter Goals:

A. Fully-connected layer