Convolutional neural network implementation for car classification

Click for: original source

Convolutional Neural Networks (CNN) are state-of-the-art Neural Network architectures that are primarily used for computer vision tasks. CNN can be applied to a number of different tasks, such as image recognition, object localization, and change detection. By Dr. Evan Eames and Henning Kropp.

This article captures interesting challenge: Develop a Computer Vision application which could identify the car model in a given image. Considering that different car models can appear quite similar and any car can look very different depending on their surroundings and the angle at which they are photographed, such a task was, until quite recently, simply impossible.

The article is split into:

  • Setting up an Artificial Neural Network to Classify Images
  • Image Augmentation with Koalas
  • Coding a ResNet in Keras
  • Tracking Results with MLflow and Azure Machine Learning
  • Getting Started with CNN Image Classification

This article and notebooks demonstrate the main techniques used in setting up an end-to-end workflow training and deploying a Neural Network in production on Azure. The exercises of the linked notebook will walk you through the required steps of creating this inside your own Azure Databricks environment using tools like Keras, Databricks Koalas, MLflow, and Azure ML. Superb!

[Read More]

Tags big-data data-science azure learning