glasses.models.classification.wide_resnet package

Module contents

class glasses.models.classification.wide_resnet.WideResNet(encoder: torch.nn.modules.module.Module = <class 'glasses.models.classification.resnet.ResNetEncoder'>, head: torch.nn.modules.module.Module = <class 'glasses.models.classification.resnet.ResNetHead'>, **kwargs)

Bases: glasses.models.classification.resnet.ResNet

Implementation of Wide ResNet proposed in “Wide Residual Networks”

Create a default model

WideResNet.wide_resnet50_2()
WideResNet.wide_resnet101_2()
# create a wide_resnet18_4
WideResNet.resnet18(block=WideResNetBottleNeckBlock, width_factor=4)

Examples

# change activation
WideResNet.resnext50_32x4d(activation = nn.SELU)
# change number of classes (default is 1000 )
WideResNet.resnext50_32x4d(n_classes=100)
# pass a different block
WideResNet.resnext50_32x4d(block=SENetBasicBlock)
# change the initial convolution
model = WideResNet.resnext50_32x4d
model.encoder.gate.conv1 = nn.Conv2d(3, 64, kernel_size=3)
# store each feature
x = torch.rand((1, 3, 224, 224))
model = WideResNet.wide_resnet50_2()
features = []
x = model.encoder.gate(x)
for block in model.encoder.layers:
    x = block(x)
    features.append(x)
print([x.shape for x in features])
# [torch.Size([1, 64, 56, 56]), torch.Size([1, 128, 28, 28]), torch.Size([1, 256, 14, 14]), torch.Size([1, 512, 7, 7])]

Parameters

• in_channels (int, optional) – Number of channels in the input Image (3 for RGB and 1 for Gray). Defaults to 3.

• n_classes (int, optional) – Number of classes. Defaults to 1000.

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

training: bool

classmethod wide_resnet101_2(*args, **kwargs) → glasses.models.classification.wide_resnet.WideResNet

Creates a wide_resnet50_2 model

Returns

A wide_resnet50_2 model

Return type

ResNet

classmethod wide_resnet50_2(*args, **kwargs) → glasses.models.classification.wide_resnet.WideResNet

Creates a wide_resnet50_2 model

Returns

A wide_resnet50_2 model

Return type

ResNet

class glasses.models.classification.wide_resnet.WideResNetBottleNeckBlock(in_features: int, out_features: int, width_factor: int = 2, reduction: int = 4, **kwargs)

Bases: glasses.models.classification.resnet.ResNetBottleneckBlock

Wide resnet bottle neck block, you can control the width of the inner features with the width_factor parameter :param in_features: [description] :type in_features: int :param out_features: [description] :type out_features: int :param width_factor: Scales the 3x3 conv features in the bottle neck block. Defaults to 2. :type width_factor: int, optional

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

training: bool