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 the basics of the `PIL` module
- Use `PIL` to load an image and return its resized pixel data



# A. PIL module

While we can do large scale image processing in TensorFlow, the `PIL` module (from [Pillow](https://python-pillow.org/)) allows us to do more fine-grained image processing. In this Lab we will demonstrate basic resizing and filtering as an introduction to `PIL`. However, the library also has many more utility functions for advanced image processing and analysis. Documentation and extended examples using the `PIL` module can be found [here](http://pillow.readthedocs.io/en/stable/reference/index.html).

The `PIL` module has a submodule called `Image`, which is the main module used for image processing. With it, we can create an `Image` object from an image file and obtain the image's pixel data. The nice thing about PIL is that the methods are more user-friendly than the TensorFlow methods; for example, the file reading and decoding are done together and resizing can work with unknown image formats.

The `image_mode` variable refers to the interpretation of the pixels, e.g. Grayscale vs. RGB vs. RGBA. PIL provides us with many types of [modes](https://pillow.readthedocs.io/en/stable/handbook/concepts.html#modes).

We'll use `image_mode` to convert our image into RGBA format so that we can resize it without worrying about what format it's in.

Use the PIL library to extract and modify data from an image.

What you'll learn from this course

Image Processing

CNN

SqueezeNet

ResNet

PIL Library

Chapter Goals:

A. PIL module