NMSIS-NN  Version 1.3.1
NMSIS NN Software Library
Public

A collection of functions to perform basic operations for neural network layers. Functions with a _s8 suffix support TensorFlow Lite framework. More...

Modules

 Structure Types
 Enums and Data Structures used in public API.
 
 Activation Functions
 Perform activation layers, including ReLU (Rectified Linear Unit), sigmoid and tanh.
 
 Elementwise Functions
 Elementwise add and multiplication functions.
 
 Concatenation Functions
 
 Convolution Functions
 Collection of convolution, depthwise convolution functions and their variants.
 
 Fully-connected Layer Functions
 Collection of fully-connected and matrix multiplication functions.
 
 LSTM Layer Functions
 Get size of additional buffer required by riscv_svdf_s8() for Arm(R) Helium Architecture case. Refer to riscv_svdf_s8_get_buffer_size() for function argument details.
 
 Pooling Functions
 Perform pooling functions, including max pooling and average pooling.
 
 Reshape Functions
 
 Softmax Functions
 
 SVDF Functions
 

Detailed Description

A collection of functions to perform basic operations for neural network layers. Functions with a _s8 suffix support TensorFlow Lite framework.