vertebrae.extractors.torchvision

Optional torchvision vision backbone extractor.

Classes

TorchvisionVisionExtractor

Wrap a torchvision image backbone as a vertebrae extractor.

Module Contents

class vertebrae.extractors.torchvision.TorchvisionVisionExtractor(name, model_name, weights=None, batch_size=16, preprocess_fn=None, output_fn=None, outputs=None, structured_outputs=None, image_mode='auto', alpha_mode='drop', device=None, model_kwargs=None, checkpoint_paths=None, cache_identity=None)[source]

Wrap a torchvision image backbone as a vertebrae extractor.

Parameters:

  • name (str)

  • model_name (str)

  • weights (Any)

  • batch_size (int)

  • preprocess_fn (Optional[Callable[[Any], Any]])

  • output_fn (Optional[Callable[[Any], Any]])

  • outputs (Optional[Sequence[Dict[str, Any]]])

  • structured_outputs (Optional[Sequence[Dict[str, Any]]])

  • image_mode (str)

  • alpha_mode (str)

  • device (Optional[str])

  • model_kwargs (Optional[Dict[str, Any]])

  • checkpoint_paths (Optional[Sequence[str]])

  • cache_identity (Optional[str])