Exploring Deep Neural Networks on Edge TPU
It addresses the challenge of deploying neural networks on resource-constrained edge devices, offering practical guidance for engineers, but is incremental as it applies existing methods to new hardware.
This paper investigates the performance and energy efficiency of Google's Edge TPU for running deep neural network classifiers on edge devices, comparing it to an ARM Cortex-A53 CPU and providing a decision chart for platform selection based on model parameters.
This paper explores the performance of Google's Edge TPU on feed forward neural networks. We consider Edge TPU as a hardware platform and explore different architectures of deep neural network classifiers, which traditionally has been a challenge to run on resource constrained edge devices. Based on the use of a joint-time-frequency data representation, also known as spectrogram, we explore the trade-off between classification performance and the energy consumed for inference. The energy efficiency of Edge TPU is compared with that of widely-used embedded CPU ARM Cortex-A53. Our results quantify the impact of neural network architectural specifications on the Edge TPU's performance, guiding decisions on the TPU's optimal operating point, where it can provide high classification accuracy with minimal energy consumption. Also, our evaluations highlight the crossover in performance between the Edge TPU and Cortex-A53, depending on the neural network specifications. Based on our analysis, we provide a decision chart to guide decisions on platform selection based on the model parameters and context.