You can apply for this internship untill the 7th of June.
Context
RIWO has a number of ongoing projects that involve the use of neural networks. Such algorithms are typically used to detect and identify objects in an image. In many cases, however, such nets need to run on a relatively limited controller, which places constraints on system resources that can lead to throughput limitations. At the R&D department, we are looking for methods to improve the performance of our neural nets.
Assignment: Net optimization
When a neural net is deployed on an industrial platform, it often has to deal with limited system resources. Most platforms have limited on-board computing available, which can form a bottleneck due to the computational power required by neural net solutions. We are interested in net optimization, which would allow us to deploy more advanced, more expensive, or simply more neural nets in the field with the same type of hardware. One solution of particular interest is the TensorRT SDK offered by NVIDIA, but alternate solutions are also welcome.
Your job will be to investigate TensorRT and apply this to a classification, a detection and a segmentation net that we are currently using. You can then compare the performance (both time and precision) to the original implementation. You can also compare this for multiple hardware platforms.
Our nets are trained in PyTorch and deployed in ONNXRuntime, therefore knowledge of C++ and Python is desirable.
Suggested program(s): (applied) computer science, robotics
How we work
All of our student assignments are all related to ongoing R&D projects, so your input may end up in a real product at one of our customers.
At our department we work in with the Agile/SCRUM workflow. At the start of you assignment you will write a problem description in your own words, to see if you clearly understand the goal of the assignment. Then for each 3-week sprint you write a sprint report where you discuss the process, implementation and results of the finished sprint and determine the functional requirements and planning for the upcoming sprint.
At the end of your assignment you will present your achievements to the company in the form of a presentation and demonstration.
We are happy with curious, enthusiastic and independent students who want to look back on a meaningful internship period. You’ll have a lot of freedom to develop yourself, with personal guidance. Take control of your assignment, tailor it to your needs. Your ideas are welcome!
All internship students receive a internship allowance, the amount depends on the level of education.
About RIWO
RIWO specializes in industrial automation and machine and process control. We work on (customized) projects which are prepared in our office and commissioned onsite. Within RIWO, we appreciate an informal and collegial working atmosphere.
We differentiate ourselves by relieving our customers by supporting them in project management, organization and selection of machine controls, be in lead of automation development, but especially by investing in ourselves. Most importantly, our employees make the difference. By combining the aspects mentioned above, our customer relations will turn into partnerships.