ResNet

torchgeo.models.resnet18(weights=None, *args, **kwargs)

ResNet-18 model.

If you use this model in your research, please cite the following paper:

• https://arxiv.org/pdf/1512.03385

Added in version 0.4.

Parameters:

• weights (ResNet18_Weights | None) – Pre-trained model weights to use.

• *args (Any) – Additional arguments to pass to timm.create_model()

• **kwargs (Any) – Additional keyword arguments to pass to timm.create_model()

Returns:

A ResNet-18 model.

Return type:

Module

torchgeo.models.resnet50(weights=None, *args, **kwargs)

ResNet-50 model.

If you use this model in your research, please cite the following paper:

• https://arxiv.org/pdf/1512.03385

Changed in version 0.4: Switched to multi-weight support API.

Parameters:

• weights (ResNet50_Weights | None) – Pre-trained model weights to use.

• *args (Any) – Additional arguments to pass to timm.create_model().

• **kwargs (Any) – Additional keyword arguments to pass to timm.create_model().

Returns:

A ResNet-50 model.

Return type:

Module

torchgeo.models.resnet152(weights=None, *args, **kwargs)

ResNet-152 model.

If you use this model in your research, please cite the following paper:

• https://arxiv.org/pdf/1512.03385

Added in version 0.6.

Parameters:

• weights (ResNet152_Weights | None) – Pre-trained model weights to use.

• *args (Any) – Additional arguments to pass to timm.create_model().

• **kwargs (Any) – Additional keyword arguments to pass to timm.create_model().

Returns:

A ResNet-152 model.

Return type:

Module

class torchgeo.models.ResNet18_Weights(*values)

Bases: WeightsEnum

ResNet-18 weights.

For timm resnet18 implementation.

Added in version 0.4.

__new__(value)

class torchgeo.models.ResNet50_Weights(*values)

Bases: WeightsEnum

ResNet-50 weights.

For timm resnet50 implementation.

Added in version 0.4.

__new__(value)

class torchgeo.models.ResNet152_Weights(*values)

Bases: WeightsEnum

ResNet-152 weights.

For timm resnet152 implementation.

Added in version 0.6.

__new__(value)