Neural Network

This module contains primitive Neural Net (NN) operations.

use orion::operators::nn;

Data types

Orion supports currently these NN types.

Data type
dtype

32-bit integer (signed)

Tensor<i32>

8-bit integer (signed)

Tensor<i8>

32-bit integer (unsigned)

Tensor<u32>

Fixed point (signed)

Tensor<FP8x23 | FP16x16 | FP32x32 | FP64x64>

NNTrait

NNTrait contains the primitive functions to build a Neural Network.

function
description

Applies the rectified linear unit function element-wise.

Applies the leaky rectified linear unit (Leaky ReLU) activation function element-wise.

Applies the Sigmoid function to an n-dimensional input tensor.

Computes softmax activations.

Computes softmax zero.

Applies the natural log to Softmax function to an n-dimensional input Tensor.

Applies the Softsign function element-wise.

Applies the Softplus function element-wise.

Performs a linear transformation of the input tensor using the provided weights and bias.

Applies the Hard Sigmoid function to an n-dimensional input tensor.

Performs the thresholded relu activation function element-wise.

Performs General Matrix multiplication.

Computes the grid sample of the input tensor and input grid.

Rearranges column blocks back into a multidimensional image

Performs the convolution transpose of the input data tensor and weight tensor.

Performs the convolution of the input data tensor and weight tensor.

GlobalAveragePool consumes an input tensor X and applies average pooling across the values in the same channel.

Performs integer convolution

Last updated