resnet_34

lucid.models.resnet_34(num_classes: int = 1000, **kwargs) ResNet

Overview

The resnet_34 function constructs a ResNet-34 model, a deeper residual network suitable for image classification tasks with more complex datasets.

It uses BasicBlock as the building block and is designed for datasets with num_classes categories.

Total Parameters: 21,797,672

Function Signature

@register_model
def resnet_34(num_classes: int = 1000, **kwargs) -> ResNet:

Parameters

  • num_classes (int, optional): Number of output classes for the classification task. Default is 1000.

  • kwargs: Additional keyword arguments to customize the model.

Returns

  • ResNet: An instance of the ResNet-34 model.

Examples

Creating a ResNet-34 model for 1000 classes:

model = resnet_34(num_classes=1000)
print(model)

Note

  • ResNet-34 uses a configuration of [3, 4, 6, 3] for its layers.

  • By default, it initializes weights internally unless specified otherwise through kwargs.