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

# Chapter Goals:
- Learn about the ResNet model structure
- Understand the difference between channels-first and channels-last


# A. Model overview


The ResNet model follows a repetitive structure built around its main building block. The overall model contains four layers of blocks, where the number of blocks per layer depends on how large we want our ResNet model to be. In our code, the `block_layer_sizes` dictionary gives the number of blocks for each of the four block layers, based on the total number of weight layers in the ResNet model.


There are six options for how many weight layers (convolution + one fully-connected layer) are in the ResNet model: 18, 34, 50, 101, 152, 200. When the number of layers is less than 50, the model uses a regular building block. However, when the number of layers is 50 or more, the model uses a *bottleneck* block. We'll discuss what a bottleneck block is in a later chapter.

Discover how the ResNet model is structured for each of its configurations.

What you'll learn from this course

Image Processing

CNN

SqueezeNet

ResNet

Initialization

Chapter Goals:

A. Model overview