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>Learn about NHWC format</li>
	<li>Reshape the input data to NHWC</li>
</ul>


<h2>A. NHWC format</h2>

<div id="section1_l2" class="collapse show">
<p>As mentioned in the previous chapter, <code>inputs</code> has shape <code>(batch_size, self.input_dim**2)</code>. However, in order to use the data with our convolutional neural network, we need to get it into NHWC format.</p>
<p>NHWC format has a shape with four dimensions:
	<ol>
		<li>Number of image data samples (batch size)</li>
		<li>Height of each image</li>
		<li>Width of each image</li>
		<li>Channels per image </li>
	</ol>
The height and width of each image from the dataset is <code>self.input_dim</code>, while the number of channels is 1 (since the images are grayscale). The number of samples, i.e. batch size, is unspecified, since we allow for a variable number of input images.</p>
</div>


<h2>Chapter Goals:</h2>
<ul>
	<li>Learn about NHWC format</li>
	<li>Reshape the input data to NHWC</li>
</ul>


<h2>A. NHWC format</h2>

<div id="section1_l2">
<p>As mentioned in the previous chapter, <code>inputs</code> has shape <code>(batch_size, self.input_dim**2)</code>. However, in order to use the data with our convolutional neural network, we need to get it into NHWC format.</p>
<p>NHWC format has a shape with four dimensions:
	<ol>
		<li>Number of image data samples (batch size)</li>
		<li>Height of each image</li>
		<li>Width of each image</li>
		<li>Channels per image </li>
	</ol>
The height and width of each image from the dataset is <code>self.input_dim</code>, while the number of channels is 1 (since the images are grayscale). The number of samples, i.e. batch size, is unspecified, since we allow for a variable number of input images.</p>
</div>


Reshape image data from the basic 2-D matrix format into NHWC format.

What you'll learn from this course

Image Processing

CNN

SqueezeNet

ResNet

Reshaping

Chapter Goals:

A. NHWC format