Home 2018-05-04T15:44:46+00:00

Using TensorFlow Models with Core ML on iOS

Von | 18. Juli 2018|

In iOS 11 Apple introduced Core ML, its own framework for Machine Learning on iPhone and iPad. In this article we show how to convert a trained TensorFlow Model and integrate it with an iOS app.

Machine learning and more precisely convolutional neural networks are an interesting approach for image classification on mobile devices. In the recent past it wasn&#

Let’s encrypt the web! All of it.

Von | 13. Juli 2018|

Are you serving your website via HTTPS yet? You really should and Let's Encrypt is here to help you get up to speed on that.

Does your website still run on plain HTTP? Would you like it to run on HTTPS? You should, because soon you might not have a choice anymore. The HTTPS saturation of th

Use Your TensorFlow Mobile Model in an Android App

Von | 19. Juni 2018|

In this post we'll show how to integrate machine learning, more accurately a neural network, to recognize houseplants in an Android app—using TensorFlow Mobile directly on the device!

Nowadays, modern mobile devices are extremely powerful and enable new approaches. Even if it sounds like a platitude, it is clear that some of these approaches are ve

Terraform in an AWS Multi Account Environment

Von | 19. Juni 2018|

Terraform is a great tool to spin up environments on AWS—or in other clouds. But when it comes to a multi account environment there might be a gap. This article offers different solutions to bypass this with some kind of Makefile magic.

Terraform is a great tool to spin up environments on AWS—or in other clouds. But when it comes to a multi account environment there might be a gap. This article offer

Generative Adversarial Networks explained

Von | 14. Juni 2018|

Recent improvements on the architecture and the training of Generative Adversarial Networks have rendered them applicable on a greater variety of problems, e.g sequential or discrete data. In this blog article we take a closer look on the general theoretical GAN architecture and its variations.

Neural networks are one of the technologies that have the potential to change our lives forever. Besides lots of applications and machines in the industry they have d

Als Student bei ITO@inovex

Von | 04. Juni 2018|

In diesem Artikel beschreibe ich, wie ich als Dualer Student der Abteilung IT Engineering & Operations in einem Kundenprojekt die Infrastruktur für einen Hadoop-Cluster bereitgestellt habe.

„ITO“ steht für IT Engineering & Operations und ist die drittgrößte Abteilung bei inovex. Bei ITO stehen Themen wie Infrastruktur-Provisionierung, Hosting und äh

Komponentenbibliotheken für die Web-Entwicklung

Von | 28. Mai 2018|

Im Folgenden möchten wir den Begriff der Komponentenbibliothek erläutern und aus unseren Erfahrungen der parallelen Web-Entwicklung berichten.

Für größere Projekte, in denen mehrere Teams parallel an Web-Applikationen entwickeln, können wir bedenkenlos die Entwicklung und den Einsatz einer Komponentenbibliot

Text Spotting using semi-supervised Generative Adversarial Networks

Von | 24. Mai 2018|

We built a text spotting (OCR) pipeline that out-performed Google Cloud Vision using semi-supervised Generative Adversarial Networks.

Despite all advances in machine learning due to the advent of deep learning, the latter has one major shortcoming: It requires a lot of data during the learning proce

Agile Sales: Wie unser Vertrieb mit Scrum seine Strategie optimiert

Von | 17. Mai 2018|

2017 haben wir angefangen, die Arbeit unseres Sales Teams agil zu organisieren. Wie es dazu kam und was das genau bedeutet, stelle ich hier vor.

inovex ist ein IT-Projekthaus, d. h. wir entwickeln IT-Projekte gemeinsam mit unseren Kunden. Dass wir die Durchführung dieser IT-Projekte agil organisieren, versteht

TensorFlow Mobile: Training and Deploying a Neural Network

Von | 08. Mai 2018|

In this blog series we explain how you can train and deploy a convolutional neural network for image classification to a mobile app using TensorFlow Mobile.

Smart Assistants, fancy image filters in Snapchat and apps like Prisma all have one thing in common—they are powered by Machine Learning. The use of Machine Learning

WebAssembly in Production

Von | 30. April 2018|

This article describes how WebAssembly can help you accelerating hot code portions of ordinary JavaScript apps with tools available today.

WebAssembly (or wasm for short) is a relatively new way to efficiently execute code in a browser. Since late 2017, it is supported in all modern major browsers (Chrom

Load More Posts