plismbench.models.owkin module#

Models from Owkin, Inc. company.

class plismbench.models.owkin.Phikon(device: int | list[int] | None = -1, mixed_precision: bool = False)[source]#

Bases: Extractor

Phikon model developped by Owkin available on Hugging-Face (1).

Note

  1. https://huggingface.co/owkin/phikon

Parameters:

  • device (int | list[int] | None = DEFAULT_DEVICE,) – Compute resources to use. If None, will use all available GPUs. If -1, extraction will run on CPU.

  • mixed_precision (bool = True) – Whether to use mixed_precision.

process(image) → Tensor[source]#

Process input images.

property transform: Lambda#

Transform method to apply element wise.

class plismbench.models.owkin.PhikonV2(device: int | list[int] | None = -1, mixed_precision: bool = False)[source]#

Bases: Extractor

Phikon V2 model developped by Owkin available on Hugging-Face (1).

You will need to be granted access to be able to use this model.

Note

  1. https://huggingface.co/owkin/phikon-v2

Parameters:

  • device (int | list[int] | None = DEFAULT_DEVICE,) – Compute resources to use. If None, will use all available GPUs. If -1, extraction will run on CPU.

  • mixed_precision (bool = True) – Whether to use mixed_precision.

process(image) → Tensor[source]#

Process input images.

property transform: Lambda#

Transform method to apply element wise.