Class DataModuleFromConfig

main.py:148–189

class DataModuleFromConfig(pl.LightningDataModule):
    def __init__(self, batch_size, train=None, validation=None, test=None,
                 wrap=False, num_workers=None):
        super().__init__()
        self.batch_size = batch_size
        self.dataset_configs = dict()
        self.num_workers = num_workers if num_workers is not None else batch_size*2
        if train is not None:
            self.dataset_configs["train"] = train
            self.train_dataloader = self._train_dataloader
        if validation is not None:
            self.dataset_configs["validation"] = validation
            self.val_dataloader = self._val_dataloader
        if test is not None:
            self.dataset_configs["test"] = test
            self.test_dataloader = self._test_dataloader
        self.wrap = wrap

    def prepare_data(self):
        for data_cfg in self.dataset_configs.values():
            instantiate_from_config(data_cfg)

    def setup(self, stage=None):
        self.datasets = dict(
            (k, instantiate_from_config(self.dataset_configs[k]))
            for k in self.dataset_configs)
        if self.wrap:
            for k in self.datasets:
                self.datasets[k] = WrappedDataset(self.datasets[k])

    def _train_dataloader(self):
        return DataLoader(self.datasets["train"], batch_size=self.batch_size,
                          num_workers=self.num_workers, shuffle=True, collate_fn=custom_collate)

    def _val_dataloader(self):
        return DataLoader(self.datasets["validation"],
                          batch_size=self.batch_size,
                          num_workers=self.num_workers, collate_fn=custom_collate)

    def _test_dataloader(self):
        return DataLoader(self.datasets["test"], batch_size=self.batch_size,
                          num_workers=self.num_workers, collate_fn=custom_collate)


class DataModuleTemplateFromConfig(DataModuleFromConfig):