What is Tensorflow?
Tensorflow is a free open-source software developed by the Google Brain team. With Tensorflow you are able to construct neural networks, which allows you to train machine learning models with data fast and easily. Tensorflow is usually used as a Python package, but can also be built from source in C++ code.
With deep learning software like Tensorflow, it’s easier than ever to use machine learning and computer vision and apply it to real-world use cases. Without Tensorflow thousands of companies and projects wouldn’t have the ability to make progress in these areas as well as they do.
Challenge of Implementing Tensorflow on Windows UWP X86
So how should we manage to run our software on 32 bit Windows systems through Tensorflow when the build system is just designed for 64 bit? Usually, most of the time it makes sense to go with 64 bit and not just 32 bit, especially when it comes to large computations such as neural networks.
Usually, the powerful Tensorflow framework, which is a C++ library, is called via python wrappers. So what our developers did was to consume Tensorflow directly in our C++ library without python. Our library is compiled for x86, so we are able to support desktop devices such as the Microsoft Surface as well as the Microsoft HoloLens, which only runs on 32 bit.
Implementation of Tensorflow on Windows UWP X86 with Anyline
By using Tensorflow for our mobile scanning SDK, a higher performance is guaranteed: Our development department trains neural networks with high data volumes and is able to use this trained network for the further enhancement of our mobile scanning software solutions.
With Tensorflow, we’ve got the perfect tool, which provides high performance on the one hand and an accurate way of doing optical character recognition (OCR) in real-time and even while being offline. Tensorflow’s architecture can be trained and optimized consistently and with each update, the Anyline SDK gets more powerful.