mowl.base_models
Base model
- class mowl.base_models.model.Model(dataset, model_filepath=None)[source]
Bases:
object
Changed in version 0.1.0: Parameter
model_filepath
added in the base class for all models. Optional parameter that will use temporary files in case it is not set.- train()[source]
Abstract method for training the model. This method must be implemented in child classes
- property class_index_dict
Dictionary with class names as keys and class indexes as values.
- Return type
- property individual_index_dict
Dictionary with individual names as keys and indexes as values.
- Return type
Base \(\mathcal{EL}\) model
- class mowl.base_models.elmodel.EmbeddingELModel(dataset, batch_size, extended=True, model_filepath=None, device='cpu')[source]
Bases:
EmbeddingModel
Abstract class that provides basic functionalities for methods that aim to embed EL language.
- Parameters
extended (bool, optional) – If True, the model is supposed with 7 EL normal forms. This will be reflected on the
DataLoaders
that will be generated and also the model must contain 7 loss functions. If False, the model will work with 4 normal forms only, merging the 3 extra to their corresponding origin normal forms. Defaults to True
- property training_datasets
Returns the training datasets for each GCI type. Each dataset is an instance of
mowl.datasets.el.ELDataset
- Return type
- property validation_datasets
Returns the validation datasets for each GCI type. Each dataset is an instance of
mowl.datasets.el.ELDataset
- Return type
- property testing_datasets
Returns the testing datasets for each GCI type. Each dataset is an instance of
mowl.datasets.el.ELDataset
- Return type
- property training_dataloaders
Returns the training dataloaders for each GCI type. Each dataloader is an instance of
torch.utils.data.DataLoader
- Return type
- property validation_dataloaders
Returns the validation dataloaders for each GCI type. Each dataloader is an instance of
torch.utils.data.DataLoader
- Return type
- property testing_dataloaders
Returns the testing dataloaders for each GCI type. Each dataloader is an instance of
torch.utils.data.DataLoader
- Return type