plismbench.models.extractor module#
Core abstract method for feature extractors.
- class plismbench.models.extractor.Extractor(*args, **kwargs)[source]#
Bases:
ABC
A base class for
plismbench
extractors.- property feature_extractor: Module#
Feature extractor module.
- Returns:
feature_extractor
- Return type:
torch.nn.Module
- property transform: Callable[[ndarray], Tensor]#
Transform method to apply element wise. Inputs should be numpy.ndarray.
This function is applied on
numpy.ndarray
and notPIL.Image.Image
as HuggingFace data is stored as numpy arrays for pickle checking purposes. If your model needs image resizing, then you will need to add a firsttransforms.ToPILImage()
operation, then resizing and finallytransforms.ToTensor()
. If your model is best working on images of shape 224x224, then no need for rescaling as PLISM tiles have 224x224 shapes.Default is identity.
- Returns:
transform
- Return type:
collections.abc.Callable[[numpy.ndarray], torch.Tensor]