"Fossies" - the Fresh Open Source Software Archive

Member "pytorch-1.8.2/docs/source/torch.nn.quantized.rst" (23 Jul 2021, 1935 Bytes) of package /linux/misc/pytorch-1.8.2.tar.gz:


As a special service "Fossies" has tried to format the requested source page into HTML format (assuming markdown format). Alternatively you can here view or download the uninterpreted source code file. A member file download can also be achieved by clicking within a package contents listing on the according byte size field.

torch.nn.quantized

This module implements the quantized versions of the nn modules and functionals.

Functional interface

torch.nn.quantized.functional

linear

conv1d

conv2d

conv3d

max_pool2d

adaptive_avg_pool2d

avg_pool2d

interpolate

hardswish

upsample

upsample_bilinear

upsample_nearest

torch.nn.quantized

ReLU6

ReLU6

ELU

ELU

Hardswish

Hardswish

Conv1d

Conv1d

Conv2d

Conv2d

Conv3d

Conv3d

FloatFunctional

FloatFunctional

QFunctional

QFunctional

Quantize

Quantize

DeQuantize

DeQuantize

Linear

Linear

BatchNorm2d

BatchNorm2d

BatchNorm3d

BatchNorm3d

LayerNorm

LayerNorm

GroupNorm

GroupNorm

InstanceNorm1d

InstanceNorm1d

InstanceNorm2d

InstanceNorm2d

InstanceNorm3d

InstanceNorm3d

Embedding

Embedding

EmbeddingBag

EmbeddingBag