Image for post
Image for post
Photo by Arthur V. on https://unsplash.com/photos/b5zOkA3swe8

Disclaimer

This was written on 27–11–2020. I cannot monitor all of my articles. There is a high probability that when you read this article the tips are outdated and the processes have changed.

If you need more information on certain parts, feel free to point it out in the comments.

How

The original image is this:

Image for post
Image for post
Photo by Arthur V. on https://unsplash.com/photos/b5zOkA3swe8

The picture shows the famous Schönbrunn Palace, in Vienna, Austria.

I wonder what an AI would transform it to when supplied with various style ideas. There are many open source implementations of style transfer. I mixed and improved a bit. The idea is that AI


By visualizing the layers of CNN architectures we dive into the understanding of how machines process images.

Image for post
Image for post
Source https://unsplash.com/photos/hJKkyoG8_ng by Hadi Yazdi Aznaveh — Unsplash Award 2019 selected in “Current events”

Convolutional neural networks (CNNs) allow the computer to classify images. Apart from classifying objects they also are able to give us insights on what makes a picture. What is the essence of a picture? By visualizing the layers of CNN architectures we dive into the understanding of how machines process images. This gives provides also insights into how the human “sees” pictures.

The article shall on one side present what elements build a picture and also provide code for a Python implementation with Keras.

Table of Contents


Image for post
Image for post

Mir scheint, die Zeit läuft mir davon;

Rinnt mir durch die Finger,

fliegt an mir vorüber;

Und lässt mich doch nicht zurück;

Denn wo sie vorbei geht,

fängt sie wieder an.

https://juliaannakarina.wordpress.com/


Image for post
Image for post
by Paolo Bendandi https://unsplash.com/photos/hZUlyk-EeuU

Today I want to talk about Neural Style Transfer and Convolutional Neural Networks (CNNs). There are already quite a few articles and tutorials available. Sometimes content is just copied, some provide a novel implementation. What all have in common is a very fast dive into specifics. Too specific in my opinion. Not only that, but there are often implementation details that make it harder to focus on the main concept as a whole.

This article can be considered as an overview and comprehension of other articles (listed in my “Inspiration” section), to understand the concept on a higher level. My intention is to strip away some implementation details, being high level enough for beginners and sparking curiosity for reading the original research paper and subsequent implementations. …


Image for post
Image for post
Photo https://unsplash.com/photos/aVeKubCF-48

Mac + AMD Radeon RX5700 XT + Keras

Every machine learning engineer these days will come to the point where he wants to use a GPU to speed up his deeplearning calculations. I happen to get an AMD Radeon GPU from a friend. Unfortunately, I saw that there is a big difference between AMD and Nvidia GPUs, whereas only the later is supported greatly in deeplearning libraries like Tensorflow. I came across some articles and made my mac+amd GPU setup work anyways. 🚀

This can be seen as comprehension of other articles (see “additional reading”) and some additional solutions from my side during implementation.

Disclaimer

I am not associated with any of the services I use in this article. …


Getting Started

Image for post
Image for post
Photo by Daniel Korpai https://unsplash.com/photos/HyTwtsk8XqA

COVID-19 prediction end-to-end app

After developing and selling a Python API, I now want to expand the idea with a machine learning solution. So I decided to quickly write a COVID-19 prediction algorithm, deploy it, and make it sellable. If you want to see how I did it, check out the post for a step by step tutorial.

Table of Contents


The article paints a picture for developing a Python API from start to end and provides help in more difficult areas.

Image for post
Image for post
Image: https://unsplash.com/photos/LJ9KY8pIH3E

I recently read a blog post about setting up your own API and selling it.

I was quite inspired and wanted to test if it works. In just 5 days I was able to create an API from start to end. So I thought I share issues I came across, elaborate on concepts that the article was introducing, and provide a quick checklist to build something yourself. All of this by developing another API.

Table of Contents


This is a small overview on how to use the API https://rapidapi.com/Createdd/api/anonymization.

Subscribe to a plan

Navigate to the pricing tab and select a plan for your desired usage.

The first on is free to a certain limit of calls.

Test endpoint

At the endpoint tab there is button to test the endpoint. Currently, there is only one endpoint (POST, for getting the table.)

Image for post
Image for post

There is already an example in the request body:

{
"Food": {
"col 1": "a",
"col 2": "b"
},
"Material": {
"col 1": "c",
"col 2": "d"
},
"Name": {
"col 1": "a",
"col 2": "b"
},
"Random": {
"col 1": "c",
"col 2": "d"
}…


Image for post
Image for post
Photo by Jye B on Unsplash — https://unsplash.com/photos/RuTMP0iI_ek

During my studies at JKU there was a task for preprocessing images for a machine learning project. It is necessary to clean the raw images before using them in a learning algorithm, so thats why we create a pre-processing function. I think it can be quite useful for others as well so I want to share a bit of my approach. The file is structured in a way that it is easy to understand and also should have a tutorial-like effect.

Table of Contents

The pre processing errors

There are a few errors, that are often encountered when processing images for machine learning tasks. …

About

Daniel Deutsch

Data Science and Business Law. https://www.createdd.com/

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