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>Add a multi-fire module block to the model</li>
	<li>Learn about delayed downsampling</li>
</ul>


<h2>A. Delayed downsampling</h2>

<div id="section1_l6" class="collapse show">
<p>While reducing the data dimensions via max pooling can help our model training, strategic placement of max pooling layers can improve the SqueezeNet model's accuracy. Rather than applying max pooling within the first fire module (e.g. after the squeeze layer), we instead apply it after the first two fire modules.</p>
<p>Placing the max pooling layers later in the model structure is referred to as <i>delayed downsampling</i>. We wait until later in the model structure to <i>downsample</i> the data (i.e. reduce height/width dimensions through pooling), so the earlier convolution layers can have a larger dimension input. The creators of SqueezeNet showed that having larger dimension inputs for more layers in the model can help improve its accuracy.</p>
</div>


<h2>Chapter Goals:</h2>
<ul>
	<li>Add a multi-fire module block to the model</li>
	<li>Learn about delayed downsampling</li>
</ul>


<h2>A. Delayed downsampling</h2>

<div id="section1_l6">
<p>While reducing the data dimensions via max pooling can help our model training, strategic placement of max pooling layers can improve the SqueezeNet model's accuracy. Rather than applying max pooling within the first fire module (e.g. after the squeeze layer), we instead apply it after the first two fire modules.</p>
<p>Placing the max pooling layers later in the model structure is referred to as <i>delayed downsampling</i>. We wait until later in the model structure to <i>downsample</i> the data (i.e. reduce height/width dimensions through pooling), so the earlier convolution layers can have a larger dimension input. The creators of SqueezeNet showed that having larger dimension inputs for more layers in the model can help improve its accuracy.</p>
</div>


Add fire modules to the model and learn about delayed downsampling.

What you'll learn from this course

Image Processing

CNN

SqueezeNet

ResNet

Adding Fire

Chapter Goals:

A. Delayed downsampling