ResNet18

Classes

class backbone.ResNet18.BasicBlock(in_planes, planes, stride=1)

Bases: Module

The basic block of ResNet.

expansion = 1

forward(x)

Compute a forward pass.

Parameters:

x (Tensor) – input tensor (batch_size, input_size)

Returns:

output tensor (10)

Return type:

Tensor

class backbone.ResNet18.ResNet(block, num_blocks, num_classes, nf)

Bases: MammothBackbone

ResNet network architecture. Designed for complex datasets.

forward(x, returnt='out')

Compute a forward pass.

Parameters:

• x (Tensor) – input tensor (batch_size, *input_shape)

• returnt – return type (a string among ‘out’, ‘features’, ‘both’, and ‘full’)

Returns:

output tensor (output_classes)

Return type:

Tensor

set_return_prerelu(enable=True)

to(device, **kwargs)

Functions

backbone.ResNet18.conv3x3(in_planes, out_planes, stride=1)

Instantiates a 3x3 convolutional layer with no bias.

Parameters:

• in_planes (int) – number of input channels

• out_planes (int) – number of output channels

• stride (int) – stride of the convolution

Returns:

convolutional layer

Return type:

conv2d

backbone.ResNet18.resnet18(nclasses, nf=64)

Instantiates a ResNet18 network.

Parameters:

• nclasses (int) – number of output classes

• nf (int) – number of filters

Returns:

ResNet network

Return type:

ResNet