bitorch.models.resnet.Resnet

class bitorch.models.resnet.Resnet(resnet_version: int, resnet_num_layers: int, input_shape: List[int], num_classes: int = 0)

Methods

__init__	Initializes internal Module state, shared by both nn.Module and ScriptModule.
add_argparse_arguments	allows additions to the argument parser if required, e.g.
create_resnet	Creates a resnet complying to given version and layer number.

Attributes

name
resnet_block_versions
resnet_net_versions
resnet_spec

__init__(resnet_version: int, resnet_num_layers: int, input_shape: List[int], num_classes: int = 0) → None

Initializes internal Module state, shared by both nn.Module and ScriptModule.

static add_argparse_arguments(parser: ArgumentParser) → None

allows additions to the argument parser if required, e.g. to add layer count, etc.

! please note that the inferred variable names of additional cli arguments are passed as keyword arguments to the constructor of this class !

Parameters:

parser (ArgumentParser) – the argument parser

create_resnet(version: int, num_layers: int) → Module

Creates a resnet complying to given version and layer number.

Parameters:

• version (int) – version of resnet to be used. availavle versions are 1 or 2

• num_layers (int) – number of layers to be build.

Raises:

• ValueError – raised if no resnet specification for given num_layers is listed in the resnet_spec dict above

• ValueError – raised if invalid resnet version was passed

Returns:

resnet model

Return type:

Module