Implementation of the Neural Network Execution Framework in a More Advanced Space-Like Hardware and Software Configuration

Implementation of the Neural Network Execution Framework in a More Advanced Space-Like Hardware and Software Configuration

Salt Palace Convention Center, Salt Lake City, UT

This work presents our Neural Network Execution Framework (NNEF), which aims to provide a cross-platform and reusable framework to deploy and execute trained neural networks (NN) for deep learning (DL) aerospace applications. This framework will execute any neural network inference process, regardless of the original deep learning framework in which it was created, in several flight software frameworks, operating systems, and hardware configurations. Users and organizations can use this framework to create reusable deployment and execution solutions for deep learning, instead of implementing one-off solutions each time they need to develop a specific aerospace application. This approach allows developers to focus on their deep learning model architectures, rather than the implementation and deployment process on the flight platform. This work demonstrates the design, implementation, and testing of our framework, for deploying and executing neural networks developed in Pytorch and TensorFlow, including our advanced NASA’s SDO neural-based compression algorithm. To emulate the space-like hardware-software configuration, we used NASA’s cFS and F Prime as a flight software, on top of two different small, low-cost, and single-board development hardware architectures.