DFBRFeatureExtractor#

tiatoolbox . tools . registration . wsi_registration . DFBRFeatureExtractor

class DFBRFeatureExtractor[source]#

Feature extractor for Deep Feature based Registration (DFBR).

This class extracts features from three different layers of VGG16. These features are processed in DFBRegister class for registration of a pair of images.

Methods

`forward`	Forward pass for feature extraction.
`forward_hook`	Register a hook.

Attributes

forward(x)[source]#

Forward pass for feature extraction.

Parameters:: x (torch.Tensor) – Batch of input images.
Returns:: A dictionary containing the multiscale features. The expected format is {layer_name: features}.
Return type:: dict

forward_hook(layer_name)[source]#

Parameters:: layer_name (str) – User-defined name for a layer.
Returns:: None
Return type:: None