torch_dequantize

Provides functionality to define and train neural networks similar to
'PyTorch' by Paszke et al (2019) <doi:10.48550/arXiv.1912.01703> but written entirely in R
using the 'libtorch' library. Also supports low-level tensor operations and
'GPU' acceleration.

Daniel Falbel

torch

Tensors and Neural Networks with 'GPU' Acceleration

Javier Luraschi

Dmitriy Selivanov

Athos Damiani

Christophe Regouby

Krzysztof Joachimiak

Hamada S. Badr

Sebastian Fischer

Maximilian Pichler

 RStudio

torch_dequantize function

<dl><dt>tensor</dt>
<dd>(Tensor) A quantized Tensor or a list oof quantized tensors</dd></dl>

Arguments

Returns an fp32 Tensor by dequantizing a quantized Tensor

dequantize(tensor) -&gt; Tensor 

Given a list of quantized Tensors, dequantize them and return a list of fp32 Tensors

dequantize(tensors) -&gt; sequence of Tensors 

Dequantize — torch_dequantize

<dl>

<dt>tensor</dt>
<dd>(Tensor) A quantized Tensor or a list oof quantized tensors</dd>

</dl>

Returns an fp32 Tensor by dequantizing a quantized Tensor

Given a list of quantized Tensors, dequantize them and return a list of fp32 Tensors

torch_dequantize: Dequantize

Description

Usage

Arguments

dequantize(tensor) -> Tensor

dequantize(tensors) -> sequence of Tensors

Description

Usage

Arguments

dequantize(tensor) -&gt; Tensor

dequantize(tensors) -&gt; sequence of Tensors

dequantize(tensor) -> Tensor

dequantize(tensors) -> sequence of Tensors