How to reduction of ROM / RAM usage:the new function of e-AI Translator V2.1.0 “8-bit quantization by supporting TensorFlow Lite“
What is e-AI Translator?
A tool that converts learned AI algorithms created using an open source AI framework into C source code dedicated to inference.
The latest version of e-AI Translator, V2.1.0, was released on September 30, 2021.In this article, Renesas will introduce the new function of V2.1.0 "8-bit quantization function by supporting TensorFlow Lite".
Bottleneck when processing AI on the MCU: memory resources
The needs are increasing that not only acquiring data but also making judgments by using AI algorithms on the system using MCUs and sensors.
If real-time performance is required for judgments, the MCU is the best platform for AI operating environment.
On the other hand, the problem of low memory resources is an obstacle to using AI algorithms on the MCU.
The AI algorithm is represented by a polynomial with many variables.
Therefore, compared to the conventional algorithm, it was difficult to allocate many AI parameters to a small amount of memory resources of MCU.
In recent years, the quantization of AI algorithms by TensorFlow Lite has become widespread to solve this memory resource problem.
ROM/RAM usage reduction effect of TensorFlow Lite 8bit quantization
First, please check how much the ROM / RAM usage reduction effect of the MCU by TensorFlow Lite 8bit quantization is.
As shown in the table below, the reduction effect varies depending on the structure of the model, but the maximum ROM / RAM reduction effect is 4.5 times.
Mechanism of 8-bit quantization and influence on inference accuracy
8-bit quantization changes the parameters and operations used in the AI model from the 32-bit float format to the 8-bit integer format.
As a result, it is possible to reduce the ROM usage for storing parameters and the RAM usage required for calculation.
On the other hand, there is a concern that the inference accuracy will decrease because the expressiveness of parameters and operations will decrease due to the reduction in the number of bits.
Then, please check how much the inference accuracy actually decreases.
As shown in the table below, there are differences depending on the model structure, but even the MobileNet v1 model, which has the largest accuracy difference, has a decrease in inference accuracy of about 1%.
8-bit quantization, which has a large effect of reducing ROM/RAM usage and has little decrease in accuracy, is an ideal function for MCUs.
Various networks can be executed on the MCU by using 8-bit quantization as shown in the figure below.
- +1 Like
- Add to Favorites
Recommend
- Silicon Labs Expands MCU Platform with a 50MHz Core Frequency New BB5 8-bit MCU Family
- New MCU RL78/G23 Operates with 30% Lower Power Consumption than The Conventional MCU
- Renesas Extends RA MCU Family with RA6T1 MCU Group for Motor Control and AI-based Endpoint Predictive Maintenance
- Using Example Projects to Support RA MCU Designs
- Renesas Expands Low-Power Industrial and IoT Applications Reach With New RA4M2 MCU Group in Arm Cortex-Based MCU Family
- Renesas Extends Arm Cortex-Based MCU Family with RA4M3 MCU Group for Industrial and IoT Applications
- Renesas Strategic Partners Presented Many of the RX MCU Solutions at ET ＆ IoT Expo 2021
- Easy Expansion of MCU Code Area! Introducing Example of Program Execution from Serial ROM Using QSPI XIP Mode
This document is provided by Sekorm Platform for VIP exclusive service. The copyright is owned by Sekorm. Without authorization, any medias, websites or individual are not allowed to reprint. When authorizing the reprint, the link of www.sekorm.com must be indicated.
Integrated Circuits
Discrete Components
Connectors & Structural Components
Assembly UnitModules & Accessories
Power Supplies & Power Modules
Electronic Materials
Instrumentation & Test Kit
Electrical Tools & Materials
Mechatronics
Processing & Customization
