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.

Note

• The first version of the VPU is known as the Cadence VP6.

• The second version of the VPU is known as the MediaTek Vision Processing Unit 2.0 (MVPU 2.0).

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.