Benchmarking Deep Learning Models on NVIDIA Jetson Nano for Real-Time Systems: An Empirical Investigation
This work addresses the problem of real-time AI deployment on low-power edge devices for developers and engineers, though it is incremental as it applies existing optimization techniques to new hardware.
This paper tackles the challenge of deploying complex deep learning models on resource-constrained embedded devices like the NVIDIA Jetson Nano by empirically investigating model optimization. The results show that optimized models achieve an average 16.11% speed improvement in inference for image classification and video action detection tasks.
The proliferation of complex deep learning (DL) models has revolutionized various applications, including computer vision-based solutions, prompting their integration into real-time systems. However, the resource-intensive nature of these models poses challenges for deployment on low-computational power and low-memory devices, like embedded and edge devices. This work empirically investigates the optimization of such complex DL models to analyze their functionality on an embedded device, particularly on the NVIDIA Jetson Nano. It evaluates the effectiveness of the optimized models in terms of their inference speed for image classification and video action detection. The experimental results reveal that, on average, optimized models exhibit a 16.11% speed improvement over their non-optimized counterparts. This not only emphasizes the critical need to consider hardware constraints and environmental sustainability in model development and deployment but also underscores the pivotal role of model optimization in enabling the widespread deployment of AI-assisted technologies on resource-constrained computational systems. It also serves as proof that prioritizing hardware-specific model optimization leads to efficient and scalable solutions that substantially decrease energy consumption and carbon footprint.