comparemela.com

Embedding Artificial Intelligence onto low-power devices is a challenging task that has been partly overcome with recent advances in machine learning and hardware design. Presently, deep neural networks can be deployed on embedded targets to perform different tasks such as speech recognition, object detection or Human Activity Recognition. However, there is still room for optimization of deep neural networks onto embedded devices. These optimizations mainly address power consumption, memory and real-time constraints, but also an easier deployment at the edge. Moreover, there is still a need for a better understanding of what can be achieved for different use cases. This work focuses on quantization and deployment of deep neural networks onto low-power 32-bit microcontrollers. The quantization methods, relevant in the context of an embedded execution onto a microcontroller, are first outlined. Then, a new framework for end-to-end deep neural networks training, quantization and deployment is presented. This framework, called MicroAI, is designed as an alternative to existing inference engines (TensorFlow Lite for Microcontrollers and STM32Cube.AI). Our framework can indeed be easily adjusted and/or extended for specific use cases. Execution using single precision 32-bit floating-point as well as fixed-point on 8- and 16 bits integers are supported. The proposed quantization method is evaluated with three different datasets (UCI-HAR, Spoken MNIST and GTSRB). Finally, a comparison study between MicroAI and both existing embedded inference engines is provided in terms of memory and power efficiency. On-device evaluation is done using ARM Cortex-M4F-based microcontrollers (Ambiq Apollo3 and STM32L452RE).

Related Keywords

Ambiq Apollo , ,Asics ,Quantization Of Deep Neural Networks ,Deployment Of Quantized Neural Network ,Neural Network ,Neural Networks ,Intel ,Human Activity Recognition ,Floating Point Unit ,Tensorflow Lite ,Sparkfun Edge ,Embedded Execution ,Quantized Neural ,Statistics Aware Weight Binning ,Learned Step Size Quantization ,Differentiable Quantization ,Deep Neural Networks ,Gaussian Mixture Models ,Instruction Set Architecture ,Rectified Linear Unit ,Deep Neural ,Fixed Point Quantization ,Per Filter Scale ,Quantization Aware Training ,Flow Lite ,அஸிக்ஸ் ,நரம்பியல் வலைப்பின்னல் ,நரம்பியல் நெட்வொர்க்குகள் ,இன்டெல் ,மனிதன் நடவடிக்கை அங்கீகாரம் ,மிதக்கும் பாயஂட் அலகு ,ஆழமான நரம்பியல் நெட்வொர்க்குகள் ,அறிவுறுத்தல் அமை கட்டிடக்கலை ,ஆழமான நரம்பியல் ,ஓட்டம் லைட் ,

© 2024 Vimarsana

comparemela.com © 2020. All Rights Reserved.