In this article we will use PySpark to perform data analysis on a large Airbnb dataset.

Apache Spark

Spark is a cluster based computing framework which is designed for distributed data processing on computer clusters. The leverage which Spark provides is noticed when datasets get too large for a single computer to handle quickly. A standard pc uses parallel computing when performing operations, whereas spark uses so called distributed computing via a server or cloud system.

In this article the masked R-CNN will be implemented for the task of segmentation. First an introduction of the R-CNN framework will be presented followed by an example implementation using PyTorch and lastly a presentation of the results.

Mask R-CNN

Frameworks such as the mask R-CNN have been developed for multi use object instance segmentation and detection tasks. The mask R-CNN was originally introduced in 2017 and is an extension of the Faster R-CNN deep learning framework. The mask R-CNN has two fundamental stages; the first stage generates proposals about the regions where there might be an object based on…

U-Net architecture as presented in the original paper by Olaf Ronneberger et. al.

In this article I will present how the original U-Net framework can be implemented using PyTorch for segmentation of medical images. I will first start by giving an overview of the U-Net architecture and how it does its magic; there after the PyTorch implementation will be presented.

U-Net, an overview

The U-Net was first introduced in 2015 by a research group at the University of Freiburg. If you have not already read the paper I would strongly recommend doing so Link. From the image of the U-Net architecture which can seen at the top, it becomes clear where the name “U”-Net comes from…

General idea of the cycleGAN. (Source: Hardik Bansal)

In this article I am going to share an interesting project which I was part of, the project’s goal was to build a cycle GAN which could take in images of class A and transform them to class B, in this case horses and zebras. I will go in order covering the following topics:

  • Cycle GAN description, main features.
  • Where and how to find image data.
  • Implementation of the cycle GAN in PyTorch.
  • Presentation of the results.

Cycle GAN description

The cycle GAN (to the best of my knowledge) was first introduced in the paper Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. (I…

Bjørn Hansen

I believe in all types of learning. Github:

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store