data

AlexNetConfig

extendsModelConfig

AlexNetConfig(num_classes: int = 1000, in_channels: int = 3, dropout: float = 0.5)

Configuration for AlexNet.

The canonical AlexNet takes 3×224×224 inputs and produces 4096-dim embeddings before the final classifier.

dropout controls the two dropout layers inside the classifier (0.5 in the original paper).

Constructors

dunder

→None

__init__(num_classes: int = 1000, in_channels: int = 3, dropout: float = 0.5)