WE-I Plus EVB Board

WE-I Plus EVB board with 40mmx40mm dimension provides flexible vision, voice, PIR, and ambient analog sensors fusion interfaces and several serial control peripherals to connect with SoC. It is industrial leading ultra-low power and best performance platform to fit blooming AIoT applications.

SDK & Documents

SDK Documentation

EVB Boards Documentation

TFLu WE-I Plus EVB Board

This new WE-I Plus EVB board is optimized for TFLu target applications, and it integrates AoS™ VGA camera, L/R microphones, 3-axis accelerometer, and USB to SPI/I2C/UART bridge into one board with 40mmx27mm dimension. It is the best leading ultra-low power and performance solution for TFLu applications in this industry.

SDK.AI

• Collaboration with Google TFL micro & Synopsys MLI teams
• Support INT8 data format

MLI Optimized Kernels

• Optimized operators
  • CONV_2D
  • DEPTHWISE_CONV_2D
  • FULLY_CONNECTED
• Unique XY memory allocation to boost convolution performance

Reference

• TensorFlow Lite for Microcontroller(TFLu)

  https://www.tensorflow.org/lite/microcontrollers

• TFLu Person Detection Example

  https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/person_detection_experimental/README.md

• Install the Synopsys DesignWare ARC MetaWare Development Toolkit

  https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/tools/make/targets/arc/README.md#install-the-synopsys-designware-arc-metaware-development-toolkit

• TFLu Person Detection Example Codes

  https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/examples/person_detection_experimental

• Synopsys embARC MLI Library

  https://github.com/foss-for-synopsys-dwc-arc-processors/embarc_mli