histocartography.ml.models.base_model module¶

Summary¶

Classes:

BaseModel

Functions:

get_number_of_classes

get_number_of_classes(class_split)[source]¶

class BaseModel(class_split: Optional[str] = None, num_classes: Optional[int] = None, pretrained: bool = False)[source]¶

Bases: torch.nn.modules.module.Module

__init__(class_split: Optional[str] = None, num_classes: Optional[int] = None, pretrained: bool = False) → None[source]¶

Base model constructor.

Parameters

class_split (str) – Class split. For instance in the BRACS dataset, one can specify a 3-class split as: “benign+pathologicalbenign+udhVSadh+feaVSdcis+malignant”. Defaults to None.
num_classes (int) – Number of classes. Used if class split is not provided. Defaults to None.
pretrained (bool) – If loading pretrained checkpoint. Currently all the pretrained were trained on the BRACS dataset. Defaults to False.

abstract forward(graph)[source]¶: Forward pass

set_forward_hook(module, layer)[source]¶

Reference¶

If you use histocartography in your projects, please cite the following:

@inproceedings{pati2021,
    title = {Hierarchical Graph Representations for Digital Pathology},
    author = {Pushpak Pati, Guillaume Jaume, Antonio Foncubierta, Florinda Feroce, Anna Maria Anniciello, Giosuè Scognamiglio, Nadia Brancati, Maryse Fiche, Estelle Dubruc, Daniel Riccio, Maurizio Di Bonito, Giuseppe De Pietro, Gerardo Botti, Jean-Philippe Thiran, Maria Frucci, Orcun Goksel, Maria Gabrani},
    booktitle = {https://arxiv.org/pdf/2102.11057},
    year = {2021}
}