Overview

Introduction

This user manual describes the NMSIS NN software library, a collection of efficient neural network kernels developed to maximize the performance and minimize the memory footprint of neural networks on Nuclei N/NX Class Processors cores.

The library is divided into a number of functions each covering a specific category:

• Activation Functions

• BasicMath Functions

• Concatenation Functions

• Convolution Functions

• Fully-Connected Functions

• LSTM Functions

• NNSupport Functions

• Pooling Functions

• Reshape Functions

• Softmax Functions

• SVD Functions

The library has separate functions for operating on different weight and activation data types including 8-bit integers (q7_t) and 16-bit integers (q15_t). The descrition of the kernels are included in the function description.

The implementation details are also described in this paper CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs .

Block Diagram

NMSIS NN Block Diagram

Examples

The library ships with a number of examples which demonstrate how to use the library functions.

• Convolutional Neural Network Example

• Gated Recurrent Unit Example

Pre-processor Macros

Each library project have different pre-processor macros controlled via CMakeLists.txt.

This library is only built for little endian targets.