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

<p>In this section of the course you will be building <a href="https://arxiv.org/pdf/1512.03385.pdf" target="_blank">ResNet</a>, the winner of the 2015 <a href="https://en.wikipedia.org/wiki/ImageNet#ImageNet_Challenge" target="_blank">ImageNet Challenge</a> and one of the major innovations in deep learning. Specifically, you'll recreate <a href="https://arxiv.org/pdf/1603.05027.pdf" target="_blank">Version 2</a> of ResNet, which switches the ordering of certain layers from Version 1 for better performance.</p>



# A. Deep learning obstacles

<div id="section1_l0" class="collapse show">
<p>While deep learning can be a great tool for solving modern day problems, there are still obstacles to overcome when building our models. Since deep models (models with many layers) tend to have numerous weight parameters, they take a long time to train. Furthermore, because deep models extract more hidden features than shallow models, they have a higher risk of overfitting the training data.</p>
<p>Nevertheless, the above two issues can be dealt with relatively seamlessly. Using modern day <a href="https://en.wikipedia.org/wiki/Graphics_processing_unit#Computational_functions" target="_blank">GPUs</a> and distributed training (i.e. training a model in parallel across multiple processing units), models can be trained in significantly less time. We have also already gone over a few tricks to reduce overfitting, such as max pooling layers, dropout, and global average pooling.</p>
<p>Although issues in deep learning continue to pop up, researchers are usually able to solve them. This problem solving process oftentimes leads to groundbreaking progress and revolutionary discoveries. In fact, the ResNet model that we will be building was created specifically to solve a problem in deep learning known as <i>degradation</i>.</p>
</div>


# A. Deep learning obstacles

<div id="section1_l0">
<p>While deep learning can be a great tool for solving modern day problems, there are still obstacles to overcome when building our models. Since deep models (models with many layers) tend to have numerous weight parameters, they take a long time to train. Furthermore, because deep models extract more hidden features than shallow models, they have a higher risk of overfitting the training data.</p>
<p>Nevertheless, the above two issues can be dealt with relatively seamlessly. Using modern day <a href="https://en.wikipedia.org/wiki/Graphics_processing_unit#Computational_functions" target="_blank">GPUs</a> and distributed training (i.e. training a model in parallel across multiple processing units), models can be trained in significantly less time. We have also already gone over a few tricks to reduce overfitting, such as max pooling layers, dropout, and global average pooling.</p>
<p>Although issues in deep learning continue to pop up, researchers are usually able to solve them. This problem solving process oftentimes leads to groundbreaking progress and revolutionary discoveries. In fact, the ResNet model that we will be building was created specifically to solve a problem in deep learning known as <i>degradation</i>.</p>
</div>


What you'll learn from this course

Image Processing

CNN

SqueezeNet

ResNet

Introduction