It’s now possible to include Tensorflow AI models in your C-project, and thus to enable Edge AI applications, thanks to the integration of Imagimob AI in IAR Embedded Workbench.
In the latest release of IAR Embedded Software for Arm, Imagimob is listed as a partner with an integrated solution in the Information Center. This means that IAR Embedded Workbench users can click on a link that takes them to the Imagimob website, where they can download the Imagimob AI software that is configured so that it works well with the IAR software.
The steps below will show you how to setup the Imagimob AI software inside IAR Embedded Workbench. The first step is to create an account in Imagimob AI and download the Imagimob AI software from https://account.imagimob.com/
The software download includes Imagimob AI, a command line tool and a pre-configured example project.
Install the Imagimob AI software and then use the Custom Build options inside IAR Embedded Workbench.
To setup the Imagimob AI software for new or existing projects follow this guide.
1. Go to Project → Options → Custom Build
2. Add this under Filename extensions: .h5
3. Add this line under Command Line: imc $FILE_PATH$ -oc $FILE_BNAME$.c -oh $FILE_BNAME$.h
4. Add these lines under Output Files: $FILE_BNAME$.c $FILE_BNAME$.h
5. Add the .h5 file that you want to convert to the project.
6. Make project (make sure that the project contains a file named main.c)
7. The generated .c and .h files can now be found in the Files window under model.h5 → Output.
When this is done, you can simply right-click on an h5-file to generate C-code and include it in your project.
Imagimob AI supports conversion of Tensorflow/Keras .h5 models generated with a Tensorflow backend of version 2.x. Models containing unsupported layers will fail to convert. See supported layers and activation functions here, https://developer.imagimob.com/iar-embedded-workbench?id=supported-tensorflow-layers.
About IAR Embedded Workbench
IAR Embedded Workbench for Arm delivers a complete C/C++ compiler and debugger toolchain, including powerful optimizations and comprehensive debugging capabilities. It also includes integrated static and runtime analysis tools, user-friendly features for helping developers in the daily workflow, as well as a powerful RTOS awareness plugin that enables a high level of control and visibility over an application built on top of a real-time operating system. With the strong technology, IAR Systems offers global technical support and a support and update service enabling customers to easily get access to the latest features and updates.
Imagimob is a fast growing startup driving innovation at the forefront of Edge AI and tinyML—and enabling the intelligent products of the future. Based in Stockholm, Sweden, the company has been serving global customers within the automotive, manufacturing, healthcare, and lifestyle industries since 2013. In 2020, Imagimob launched their SaaS Imagimob AI for the swift and easy end-to-end development of Edge AI applications for devices with constrained resources. Imagimob AI guides and empowers users throughout the entire development journey, resulting in game-changing productivity and faster time-to-market. Tirelessly dedicated to staying on top of the latest research, the experienced team behind Imagimob is always thinking new, and thinking big.
Imagimob has the expertise, software tools and methods to de...