Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems

by   Julian Moosmann, et al.

This paper deploys and explores variants of TinyissimoYOLO, a highly flexible and fully quantized ultra-lightweight object detection network designed for edge systems with a power envelope of a few milliwatts. With experimental measurements, we present a comprehensive characterization of the network's detection performance, exploring the impact of various parameters, including input resolution, number of object classes, and hidden layer adjustments. We deploy variants of TinyissimoYOLO on state-of-the-art ultra-low-power extreme edge platforms, presenting an in-depth a comparison on latency, energy efficiency, and their ability to efficiently parallelize the workload. In particular, the paper presents a comparison between a novel parallel RISC-V processor (GAP9 from Greenwaves) with and without use of its on-chip hardware accelerator, an ARM Cortex-M7 core (STM32H7 from ST Microelectronics), two ARM Cortex-M4 cores (STM32L4 from STM and Apollo4b from Ambiq), and a multi-core platform with a CNN hardware accelerator (Analog Devices MAX78000). Experimental results show that the GAP9's hardware accelerator achieves the lowest inference latency and energy at 2.12ms and 150uJ respectively, which is around 2x faster and 20 MAX78000. The hardware accelerator of GAP9 can even run an increased resolution version of TinyissimoYOLO with 112x112 pixels and 10 detection classes within 3.2ms, consuming 245uJ. To showcase the competitiveness of a versatile general-purpose system we also deployed and profiled a multi-core implementation on GAP9 at different operating points, achieving 11.3ms with the lowest-latency and 490uJ with the most energy-efficient configuration. With this paper, we demonstrate the suitability and flexibility of TinyissimoYOLO on state-of-the-art detection datasets for real-time ultra-low-power edge inference.


page 7

page 9

page 10

page 11


TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers

This paper introduces a highly flexible, quantized, memory-efficient, an...

TinyVers: A Tiny Versatile System-on-chip with State-Retentive eMRAM for ML Inference at the Extreme Edge

Extreme edge devices or Internet-of-thing nodes require both ultra-low p...

TinyTracker: Ultra-Fast and Ultra-Low-Power Edge Vision In-Sensor for Gaze Estimation

Intelligent edge vision tasks encounter the critical challenge of ensuri...

Towards real-time and energy efficient Siamese tracking – a hardware-software approach

Siamese trackers have been among the state-of-the-art solutions in each ...

TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference

Temporal Convolutional Networks (TCNs) are emerging lightweight Deep Lea...

Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices

In this paper, we propose a data-model-hardware tri-design framework for...

PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V Processors

We present PULP-NN, an optimized computing library for a parallel ultra-...

Please sign up or login with your details

Forgot password? Click here to reset