Edge-AI MCU Introduction

•

Introduction to Edge-AI MCUs.

Edge-AI MCU

Realtek AMB82-mini

RTL8735B: 32-bit Arm v8M, up to 500MHz, 768KB ROM, 512KB RAM, 16MB Flash (MCM embedded DDR2/DDR3L up to 128MB)
802.11 a/b/g/n WiFi 2.4GHz/5GHz, BLE 5.1, NN Engine 0.4 TOPS, Crypto Engine, Audo Codec, …

Ameba Arduino

Amebapro2 AMB82-mini Arduino Example Guides

Amebapro2 AMB82-mini Arduino getting started

Preferences = https://raw.githubusercontent.com/ambiot/ambpro2_arduino/dev/Arduino_package/package_realtek_amebapro2_early_index.json

Nvidia Jetson

Jetson Orin NXJetson Nano

Jetson module comparison

  • Jetson Nano 4G = 0.472 TOPs
  • Xavier NX 8GB = 21 TOPs
  • AGX Xavier = 32 TOPs
  • Orin NX 8GB = 70 TOPs
  • Orin NX 16GB = 100 TOPs
  • AGX Orin 32GB = 200 TOPs
  • AGX Orin 64GB = 275 TOPs

Kneron KL520

  • support Framework: ONNX, Tensorflow, Keras, Caffe
  • support Model: VGG16, GoogleNet, YOLO, Tiny YOLO, Lenet, MobileNet, DenseNet
  • memory type: LPDDR2
  • NPU power efficiency : 0.55TOPS/W
  • Overall power consumption : 0.5W
  • Camera: EUA1200: 1080p progressive scan CMOS sensor

ESP32-S3-BOX-3

Unboxing ESP32-S3-BOX-3
Hardware Overview



This site was last updated October 07, 2024.