Custom dataset

[clementchadebec]

New features:

• Allow custom Dataset inheriting from torch.utils.data.Dataset to be passed as inputs in the training_pipeline.

def __call__(
        self,
        train_data: Union[np.ndarray, torch.Tensor, torch.utils.data.Dataset],
        eval_data: Union[np.ndarray, torch.Tensor, torch.utils.data.Dataset] = None,
        callbacks: List[TrainingCallback] = None,
    ):

• Update tests and add a tutorial on custom datasets.

Minor changes

• Unify data handling in FactorVAE with other models. (half of the batch is used for reconstruction and the other one for factorial representation)
• Change model sanity check method in trainers (use loaders in check instead of datasets)
• Update README