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>Decode raw byte data into usable pixel data</li>
	<li>Understand the relationship between channels and pixels</li>
</ul>


<h2>A. Decoding</h2>

<div id="section1_l2" class="collapse show">
<p>We'll now decode the raw byte data into usable pixel data. The decoding function that we use depends on the format of the image. If the input is a PNG image then we use <code><a href="https://www.tensorflow.org/api_docs/python/tf/image/decode_png" target="_blank">tf.io.decode_png</a></code>, and if the input is a JPEG image we use <code><a href="https://www.tensorflow.org/api_docs/python/tf/image/decode_jpeg" target="_blank">tf.io.decode_jpeg</a></code>. For generic decoding (i.e. decoding any image format), we use <code><a href="https://www.tensorflow.org/api_docs/python/tf/image/decode_image" target="_blank">tf.io.decode_image</a></code>.</p>
<p>Since <code>tf.io.decode_image</code> can decode any type of image, you might be wondering why we even bother with the other two decoding functions. One reason is that you may want to only use specific image formats, in which case it's more efficient and better for code clarity to just use the format-specific decoding function.</p>
<p>Another reason is that <code>tf.io.decode_image</code>  supports GIF decoding, which results in an output shape of <code>(num_frames, height, width, channels)</code>. Since the function can return data with different shapes, we can't use <code>tf.io.decode_image</code> when we also need to resize the image with <code>tf.image.resize</code> (see next chapter).</p>
</div>


<h2>Chapter Goals:</h2>
<ul>
	<li>Decode raw byte data into usable pixel data</li>
	<li>Understand the relationship between channels and pixels</li>
</ul>


<h2>A. Decoding</h2>

<div id="section1_l2">
<p>We'll now decode the raw byte data into usable pixel data. The decoding function that we use depends on the format of the image. If the input is a PNG image then we use <code><a href="https://www.tensorflow.org/api_docs/python/tf/image/decode_png" target="_blank">tf.io.decode_png</a></code>, and if the input is a JPEG image we use <code><a href="https://www.tensorflow.org/api_docs/python/tf/image/decode_jpeg" target="_blank">tf.io.decode_jpeg</a></code>. For generic decoding (i.e. decoding any image format), we use <code><a href="https://www.tensorflow.org/api_docs/python/tf/image/decode_image" target="_blank">tf.io.decode_image</a></code>.</p>
<p>Since <code>tf.io.decode_image</code> can decode any type of image, you might be wondering why we even bother with the other two decoding functions. One reason is that you may want to only use specific image formats, in which case it's more efficient and better for code clarity to just use the format-specific decoding function.</p>
<p>Another reason is that <code>tf.io.decode_image</code>  supports GIF decoding, which results in an output shape of <code>(num_frames, height, width, channels)</code>. Since the function can return data with different shapes, we can't use <code>tf.io.decode_image</code> when we also need to resize the image with <code>tf.image.resize</code> (see next chapter).</p>
</div>


Learn how to decode raw image data into pixel data using TensorFlow.

What you'll learn from this course

Image Processing

CNN

SqueezeNet

ResNet

Image Types

Chapter Goals:

A. Decoding