torch_quantize_per_tensor: Quantize_per_tensor

View source: R/wrapers.R

torch_quantize_per_tensorR Documentation

Quantize_per_tensor

Description

Quantize_per_tensor

Usage

torch_quantize_per_tensor(self, scale, zero_point, dtype)

Arguments

self

(Tensor) float tensor to quantize

scale

(float) scale to apply in quantization formula

zero_point

(int) offset in integer value that maps to float zero

dtype

(torch.dtype) the desired data type of returned tensor. Has to be one of the quantized dtypes: torch_quint8, torch.qint8, torch.qint32

quantize_per_tensor(input, scale, zero_point, dtype) -> Tensor

Converts a float tensor to quantized tensor with given scale and zero point.

Examples

if (torch_is_installed()) {
torch_quantize_per_tensor(torch_tensor(c(-1.0, 0.0, 1.0, 2.0)), 0.1, 10, torch_quint8())
torch_quantize_per_tensor(torch_tensor(c(-1.0, 0.0, 1.0, 2.0)), 0.1, 10, torch_quint8())$int_repr()
}

torch documentation built on June 7, 2023, 6:19 p.m.