AlexNet

class cv.backbones.AlexNet.model.AlexNet(num_classes, in_channels=3)

Bases: Module

AlexNet model for image classification based on the paper.

This class defines the AlexNet architecture, which consists of convolutional layers for feature extraction and fully connected layers for classification.

Parameters:

• num_classes (int) – The number of output classes for classification.

• in_channels (int, optional) – The number of input channels for the images, typically 3 for RGB (default: 3).

Example

>>> model = AlexNet(num_classes=1000, in_channels=3)

forward(x)

Defines the forward pass of the AlexNet model.

The input tensor passes through the feature extractor (convolutional layers), then is flattened and passed through the classifier (fully connected layers).

Parameters:

x (torch.Tensor) – Input tensor of shape (batch_size, in_channels, height, width).

Returns:

Output tensor after passing through the model, with shape (batch_size, num_classes).

Return type:

torch.Tensor

Example

>>> output = model(torch.randn(1, 3, 224, 224))  # Example input tensor of shape (batch_size, channels, height, width)