change_detector

Module for change detection models

class ChangeDetector(criterion: Module | None = None, input_size: tuple[int] | None = None, n_classes: int = 1, scaler: GradScaler | None = None, fc_dim: int = 512, intermediate_dim: int = 256, encoder_on: bool = False, filter_dim: int = 0, freeze_backbone: bool = False, backbone_weight_path: str | Path | None = None, backbone_args: dict[str, Any] = {}, clamp_outputs: bool = False)

forward(x: Tensor) → Tensor

Performs a forward pass of the ResNet.

Can be called directly as a method (e.g. model.forward) or when data is parsed to model (e.g. model()).

Parameters:

x (Tensor) – Input data to network.

Returns:

Likelihoods the network places on the input x being of each class.

Return type:

Tensor