torchsig.datasets.datamodules.OfficialNarrowbandDataModule¶

class torchsig.datasets.datamodules.OfficialNarrowbandDataModule(root: str, impairment_level: int, batch_size: int = 1, num_workers: int = 1, collate_fn: ~typing.Callable | None = None, create_batch_size: int = 8, create_num_workers: int = 4, file_handler: ~torchsig.utils.file_handlers.base_handler.TorchSigFileHandler = <class 'torchsig.utils.file_handlers.zarr.ZarrFileHandler'>, transforms: list = [], target_transforms: list = [])[source]¶

Bases: OfficialTorchSigDataModdule

A DataModule for the official Narrowband dataset.

This class extends OfficialTorchSigDataModdule and sets the dataset type to ‘narrowband’. It initializes the necessary parameters for the dataset and loads the train and validation metadata accordingly.

Parameters:

root (str) – Root directory where the dataset is stored.
impairment_level (int) – Defines the impairment level of the dataset.
batch_size (int, optional) – Batch size for the dataloaders. Default is 1.
num_workers (int, optional) – Number of workers for data loading. Default is 1.
collate_fn (Callable, optional) – Function to merge a list of samples into a batch. Default is None.
create_batch_size (int, optional) – Batch size used during dataset creation. Default is 8.
create_num_workers (int, optional) – Number of workers used during dataset creation. Default is 4.
file_handler (TorchSigFileHandler, optional) – File handler used to read/write dataset. Default is ZarrFileHandler.
transforms (list, optional) – List of transforms applied to dataset. Default is empty list.
target_transforms (list, optional) – List of transforms applied to targets. Default is empty list.

Methods

`from_datasets`	Create an instance from torch.utils.data.Dataset.
`load_from_checkpoint`	Primary way of loading a datamodule from a checkpoint.
`load_state_dict`	Called when loading a checkpoint, implement to reload datamodule state given datamodule state_dict.
`on_after_batch_transfer`	Override to alter or apply batch augmentations to your batch after it is transferred to the device.
`on_before_batch_transfer`	Override to alter or apply batch augmentations to your batch before it is transferred to the device.
`on_exception`	Called when the trainer execution is interrupted by an exception.
`predict_dataloader`	An iterable or collection of iterables specifying prediction samples.
`prepare_data`	Prepares the dataset by creating new datasets if they do not exist on disk.
`remove_ignored_hparams`	Remove ignored hyperparameters from the stored state.
`save_hyperparameters`	Save arguments to `hparams` attribute.
`setup`	Sets up the train and validation datasets for the given stage.
`state_dict`	Called when saving a checkpoint, implement to generate and save datamodule state.
`teardown`	Called at the end of fit (train + validate), validate, test, or predict.
`test_dataloader`	An iterable or collection of iterables specifying test samples.
`train_dataloader`	Returns the DataLoader for the training dataset.
`transfer_batch_to_device`	Override this hook if your `DataLoader` returns tensors wrapped in a custom data structure.
`val_dataloader`	Returns the DataLoader for the validation dataset.

Attributes

`CHECKPOINT_HYPER_PARAMS_KEY`
`CHECKPOINT_HYPER_PARAMS_NAME`
`CHECKPOINT_HYPER_PARAMS_TYPE`
`hparams`	The collection of hyperparameters saved with `save_hyperparameters()`.
`hparams_initial`	The collection of hyperparameters saved with `save_hyperparameters()`.
`name`

__init__(root: str, impairment_level: int, batch_size: int = 1, num_workers: int = 1, collate_fn: ~typing.Callable | None = None, create_batch_size: int = 8, create_num_workers: int = 4, file_handler: ~torchsig.utils.file_handlers.base_handler.TorchSigFileHandler = <class 'torchsig.utils.file_handlers.zarr.ZarrFileHandler'>, transforms: list = [], target_transforms: list = [])[source]¶

Initializes the TorchSigDataModule with the provided parameters.

Parameters:

root (str) – The root directory where datasets are stored or created.
dataset (str) – The name of the dataset (either ‘narrowband’ or ‘wideband’).
train_metadata (DatasetMetadata | str | dict) – Metadata for the training dataset.
val_metadata (DatasetMetadata | str | dict) – Metadata for the validation dataset.
batch_size (int, optional) – The batch size for data loading. Defaults to 1.
num_workers (int, optional) – The number of worker processes for data loading. Defaults to 1.
collate_fn (Callable, optional) – A function to collate data into batches.
create_batch_size (int, optional) – The batch size used during dataset creation. Defaults to 8.
create_num_workers (int, optional) – The number of workers used during dataset creation. Defaults to 4.
file_handler (TorchSigFileHandler, optional) – The file handler for managing data storage. Defaults to ZarrFileHandler.
transforms (list, optional) – A list of transformations to apply to the input data. Defaults to an empty list.
target_transforms (list, optional) – A list of transformations to apply to the target labels. Defaults to an empty list.

__str__() → str¶

Return a string representation of the datasets that are set up.

Returns:: A string representation of the datasets that are setup.

Create an instance from torch.utils.data.Dataset.

Parameters:

train_dataset – Optional dataset or iterable of datasets to be used for train_dataloader()
val_dataset – Optional dataset or iterable of datasets to be used for val_dataloader()
test_dataset – Optional dataset or iterable of datasets to be used for test_dataloader()
predict_dataset – Optional dataset or iterable of datasets to be used for predict_dataloader()
batch_size – Batch size to use for each dataloader. Default is 1. This parameter gets forwarded to the __init__ if the datamodule has such a name defined in its signature.
num_workers – Number of subprocesses to use for data loading. 0 means that the data will be loaded in the main process. Number of CPUs available. This parameter gets forwarded to the __init__ if the datamodule has such a name defined in its signature.
**datamodule_kwargs – Additional parameters that get passed down to the datamodule’s __init__.

property hparams: AttributeDict | MutableMapping¶

The collection of hyperparameters saved with save_hyperparameters(). It is mutable by the user. For the frozen set of initial hyperparameters, use hparams_initial.

Returns:: Mutable hyperparameters dictionary

property hparams_initial: AttributeDict¶

The collection of hyperparameters saved with save_hyperparameters(). These contents are read-only. Manual updates to the saved hyperparameters can instead be performed through hparams.

Returns:: immutable initial hyperparameters
Return type:: AttributeDict

Primary way of loading a datamodule from a checkpoint. When Lightning saves a checkpoint it stores the arguments passed to __init__ in the checkpoint under "datamodule_hyper_parameters".

Any arguments specified through **kwargs will override args stored in "datamodule_hyper_parameters".

Parameters:

checkpoint_path – Path to checkpoint. This can also be a URL, or file-like object
map_location – If your checkpoint saved a GPU model and you now load on CPUs or a different number of GPUs, use this to map to the new setup. The behaviour is the same as in torch.load().
hparams_file –
Optional path to a .yaml or .csv file with hierarchical structure as in this example:
```
dataloader:
    batch_size: 32
```
You most likely won’t need this since Lightning will always save the hyperparameters to the checkpoint. However, if your checkpoint weights don’t have the hyperparameters saved, use this method to pass in a .yaml file with the hparams you’d like to use. These will be converted into a dict and passed into your LightningDataModule for use.

If your datamodule’s hparams argument is Namespace and .yaml file has hierarchical structure, you need to refactor your datamodule to treat hparams as dict.
weights_only – If True, restricts loading to state_dicts of plain torch.Tensor and other primitive types. If loading a checkpoint from a trusted source that contains an nn.Module, use weights_only=False. If loading checkpoint from an untrusted source, we recommend using weights_only=True. For more information, please refer to the PyTorch Developer Notes on Serialization Semantics.
**kwargs – Any extra keyword args needed to init the datamodule. Can also be used to override saved hyperparameter values.

Returns:

LightningDataModule instance with loaded weights and hyperparameters (if available).

Note

load_from_checkpoint is a class method. You must use your LightningDataModule class to call it instead of the LightningDataModule instance, or a TypeError will be raised.

Example:

# load weights without mapping ...
datamodule = MyLightningDataModule.load_from_checkpoint('path/to/checkpoint.ckpt')

# or load weights and hyperparameters from separate files.
datamodule = MyLightningDataModule.load_from_checkpoint(
    'path/to/checkpoint.ckpt',
    hparams_file='/path/to/hparams_file.yaml'
)

# override some of the params with new values
datamodule = MyLightningDataModule.load_from_checkpoint(
    PATH,
    batch_size=32,
    num_workers=10,
)

load_state_dict(state_dict: dict[str, Any]) → None¶

Called when loading a checkpoint, implement to reload datamodule state given datamodule state_dict.

Parameters:: state_dict – the datamodule state returned by state_dict.

on_after_batch_transfer(batch: Any, dataloader_idx: int) → Any¶

Override to alter or apply batch augmentations to your batch after it is transferred to the device.

Note

To check the current state of execution of this hook you can use self.trainer.training/testing/validating/predicting so that you can add different logic as per your requirement.

Parameters:

batch – A batch of data that needs to be altered or augmented.
dataloader_idx – The index of the dataloader to which the batch belongs.

Returns:

A batch of data

Example:

def on_after_batch_transfer(self, batch, dataloader_idx):
    batch['x'] = gpu_transforms(batch['x'])
    return batch

See also

on_after_batch_transfer()
transfer_batch_to_device()

on_exception(exception: BaseException) → None¶: Called when the trainer execution is interrupted by an exception.

predict_dataloader() → Any¶

An iterable or collection of iterables specifying prediction samples.

For more information about multiple dataloaders, see this section.

It’s recommended that all data downloads and preparation happen in prepare_data().

predict()
prepare_data()
setup()

Note

Lightning tries to add the correct sampler for distributed and arbitrary hardware There is no need to set it yourself.

Returns:: A torch.utils.data.DataLoader or a sequence of them specifying prediction samples.

prepare_data() → None¶

Prepares the dataset by creating new datasets if they do not exist on disk. The datasets are created using the DatasetCreator class.

If the dataset already exists on disk, it is loaded back into memory.

remove_ignored_hparams(ignore_list: list[str]) → None¶

Remove ignored hyperparameters from the stored state.

This allows derived classes to drop hyperparameters previously saved by base classes.

Parameters:: ignore_list – Names of hyperparameters to remove.

save_hyperparameters(*args: Any, ignore: Sequence[str] | str | None = None, frame: FrameType | None = None, logger: bool = True) → None¶

Save arguments to hparams attribute.

Parameters:

args – single object of dict, NameSpace or OmegaConf or string names or arguments from class __init__
ignore – an argument name or a list of argument names from class __init__ to be ignored
frame – a frame object. Default is None
logger – Whether to send the hyperparameters to the logger. Default: True

Example::

>>> from pytorch_lightning.core.mixins import HyperparametersMixin
>>> class ManuallyArgsModel(HyperparametersMixin):
...     def __init__(self, arg1, arg2, arg3):
...         super().__init__()
...         # manually assign arguments
...         self.save_hyperparameters('arg1', 'arg3')
...     def forward(self, *args, **kwargs):
...         ...
>>> model = ManuallyArgsModel(1, 'abc', 3.14)
>>> model.hparams
"arg1": 1
"arg3": 3.14

>>> from pytorch_lightning.core.mixins import HyperparametersMixin
>>> class AutomaticArgsModel(HyperparametersMixin):
...     def __init__(self, arg1, arg2, arg3):
...         super().__init__()
...         # equivalent automatic
...         self.save_hyperparameters()
...     def forward(self, *args, **kwargs):
...         ...
>>> model = AutomaticArgsModel(1, 'abc', 3.14)
>>> model.hparams
"arg1": 1
"arg2": abc
"arg3": 3.14

>>> from pytorch_lightning.core.mixins import HyperparametersMixin
>>> class SingleArgModel(HyperparametersMixin):
...     def __init__(self, params):
...         super().__init__()
...         # manually assign single argument
...         self.save_hyperparameters(params)
...     def forward(self, *args, **kwargs):
...         ...
>>> model = SingleArgModel(Namespace(p1=1, p2='abc', p3=3.14))
>>> model.hparams
"p1": 1
"p2": abc
"p3": 3.14

>>> from pytorch_lightning.core.mixins import HyperparametersMixin
>>> class ManuallyArgsModel(HyperparametersMixin):
...     def __init__(self, arg1, arg2, arg3):
...         super().__init__()
...         # pass argument(s) to ignore as a string or in a list
...         self.save_hyperparameters(ignore='arg2')
...     def forward(self, *args, **kwargs):
...         ...
>>> model = ManuallyArgsModel(1, 'abc', 3.14)
>>> model.hparams
"arg1": 1
"arg3": 3.14

setup(stage: str = 'train') → None¶

Sets up the train and validation datasets for the given stage.

Parameters:: stage (str, optional) – The stage of the DataModule, typically ‘train’ or ‘test’. Defaults to ‘train’.

state_dict() → dict[str, Any]¶

Called when saving a checkpoint, implement to generate and save datamodule state.

Returns:: A dictionary containing datamodule state.

teardown(stage: str) → None¶

Called at the end of fit (train + validate), validate, test, or predict.

Parameters:: stage – either 'fit', 'validate', 'test', or 'predict'

test_dataloader() → Any¶

An iterable or collection of iterables specifying test samples.

For more information about multiple dataloaders, see this section.

For data processing use the following pattern:

download in prepare_data()

process and split in setup()

However, the above are only necessary for distributed processing.

Warning

do not assign state in prepare_data

test()
prepare_data()
setup()

Note

Lightning tries to add the correct sampler for distributed and arbitrary hardware. There is no need to set it yourself.

Note

If you don’t need a test dataset and a test_step(), you don’t need to implement this method.

train_dataloader() → DataLoader¶

Returns the DataLoader for the training dataset.

Returns:: A PyTorch DataLoader for the training dataset.
Return type:: DataLoader

transfer_batch_to_device(batch: Any, device: device, dataloader_idx: int) → Any¶

Override this hook if your DataLoader returns tensors wrapped in a custom data structure.

The data types listed below (and any arbitrary nesting of them) are supported out of the box:

torch.Tensor or anything that implements .to(…)
list
dict
tuple

For anything else, you need to define how the data is moved to the target device (CPU, GPU, TPU, …).

Note

This hook should only transfer the data and not modify it, nor should it move the data to any other device than the one passed in as argument (unless you know what you are doing). To check the current state of execution of this hook you can use self.trainer.training/testing/validating/predicting so that you can add different logic as per your requirement.

Parameters:

batch – A batch of data that needs to be transferred to a new device.
device – The target device as defined in PyTorch.
dataloader_idx – The index of the dataloader to which the batch belongs.

Returns:

A reference to the data on the new device.

Example:

def transfer_batch_to_device(self, batch, device, dataloader_idx):
    if isinstance(batch, CustomBatch):
        # move all tensors in your custom data structure to the device
        batch.samples = batch.samples.to(device)
        batch.targets = batch.targets.to(device)
    elif dataloader_idx == 0:
        # skip device transfer for the first dataloader or anything you wish
        pass
    else:
        batch = super().transfer_batch_to_device(batch, device, dataloader_idx)
    return batch