Machine Learning Developer Guide

---

Overview

Due to the different hardware on each platform, the IoT Yocto provides different machine learning software stacks for the developer. Table 1 shows the hardware difference on different boards. Table 2 shows the difference in machine learning software stacks on different boards.

Table 1. Hardware Devices on Board

	Genio 350-EVK	Genio 510-EVK	Genio 700-EVK	Genio 1200-EVK
GPU	V	V	V	V
VPU	V	V	V	V
MDLA	X	V	V	V

Note

For the introduction of hardware devices, please refer to Hardware Devices

Table 2. Software Stack on Board

Software Stack	Backend	Genio 350-EVK	Genio 510-EVK	Genio 700-EVK	Genio 1200-EVK
Tensorflow-Lite	CPU	V	V	V	V
Tensorflow-Lite + GPU delegate	GPU	V	V	V	V
Tensorflow-Lite + ARMNN Delegate	GPU, CPU	V	V	V	V
Tensorflow-Lite + NNAPI Delegate	VPU	V	X	X	X
Tensorflow-Lite + Neuron Stable Delegate	MDLA, VPU	X	V	V	V
Neuron SDK	MDLA, VPU	X	V	V	V

---

Reference Boards

IoT Yocto provides different machine learning software stacks on different SoC platforms. Please find more details about machine learning on each reference board:

• Genio 350-EVK Machine Learning.

• Genio 510/700-EVK Machine Learning.

• Genio 1200-EVK Machine Learning.

Model Hub

IoT Yocto provides a list of models that are usable on G510, G700 and G1200. Please go to Model Hub section to download them.

Common Q&A

Frequently asked questions for machine learning are collected and record in:

• Common Q&A.

Appendix

Hardware Devices

GPU

The GPU provides neural network acceleration for floating point models.

• ARM-based platforms could support GPU neural network acceleration via Arm NN and the Arm Compute Library.

• Non-ARM platforms could support GPU neural network acceleration via Google’s TensorFlow Lite GPU delegate. This GPU delegate can accelerate a wide selection of TFLite operations.

Note

On IoT Yocto, we support both of the above GPU neural network accelerations.

VPU

The Vision Processing Unit (VPU) offers general-purpose Digital Signal Processing (DSP) capabilities, with special hardware for accelerating complex imaging and computer vision algorithms. The VPU also offers outstanding performance while running AI models.

MDLA

The MediaTek Deep Learning Accelerator (MDLA) is a powerful and efficient Convolutional Neural Network (CNN) accelerator. The MDLA is capable of achieving high AI benchmark results with high Multiply-Accumulate (MAC) utilization rates. The design integrates MAC units with dedicated function blocks, which handle activation functions, element-wise operations, and pooling layers.