glasses.models.classification.alexnet package

Module contents

class glasses.models.classification.alexnet.AlexNet(encoder: torch.nn.modules.module.Module = <class 'glasses.models.classification.alexnet.AlexNetEncoder'>, head: torch.nn.modules.module.Module = <class 'glasses.models.classification.alexnet.AlexNetHead'>, **kwargs)

Bases: glasses.models.classification.base.ClassificationModule

Implementation of AlexNet proposed in ImageNet Classification with Deep Convolutional Neural Networks, according to the variation implemented in torchvision.

net = AlexNet()

Examples

# change activation
AlexNet(activation = nn.SELU)
# change number of classes (default is 1000 )
AlexNet(n_classes=100)
# pass a different block
AlexNet(block=SENetBasicBlock)

Parameters

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

• n_classes (int, optional) – Number of classes. Default is 1000.

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

training: bool

class glasses.models.classification.alexnet.AlexNetEncoder(in_channels: int = 3, stem: torch.nn.modules.module.Module = <class 'glasses.models.classification.alexnet.AlexNetStem'>, widths: List[int] = [192, 384, 256, 256], activation: torch.nn.modules.module.Module = functools.partial(<class 'torch.nn.modules.activation.ReLU'>, inplace=True), block: torch.nn.modules.module.Module = functools.partial(<class 'glasses.nn.blocks.ConvBnAct'>, normalization=None, bias=True))

Bases: glasses.models.base.Encoder

AlexNet encoder

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

forward(x: torch.Tensor) → torch.Tensor

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training: bool

class glasses.models.classification.alexnet.AlexNetHead(in_features: int, n_classes: int, drop_p: float = 0.5)

Bases: torch.nn.modules.container.Sequential

This class represents the classifier of AlexNet. It converts the filters into 6x6 by means of the average pooling. Then, it maps the output to the correct class by means of fully connected layers. Dropout is used to decrease the overfitting.

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

class glasses.models.classification.alexnet.AlexNetStem(in_channels: int = 3, out_features: int = 192)

Bases: torch.nn.modules.container.Sequential

AlexNet stem which decreases the resolution of the filters by means of stride and bigger kernels.

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