datasets.avmnist package

Submodules

datasets.avmnist.get_data module

Implements dataloaders for the AVMNIST dataset.

Here, the data is assumed to be in a folder titled “avmnist”.

datasets.avmnist.get_data.get_dataloader(data_dir, batch_size=40, num_workers=8, train_shuffle=True, flatten_audio=False, flatten_image=False, unsqueeze_channel=True, generate_sample=False, normalize_image=True, normalize_audio=True)

Get dataloaders for AVMNIST.

Parameters:

  • data_dir (str) – Directory of data.

  • batch_size (int, optional) – Batch size. Defaults to 40.

  • num_workers (int, optional) – Number of workers. Defaults to 8.

  • train_shuffle (bool, optional) – Whether to shuffle training data or not. Defaults to True.

  • flatten_audio (bool, optional) – Whether to flatten audio data or not. Defaults to False.

  • flatten_image (bool, optional) – Whether to flatten image data or not. Defaults to False.

  • unsqueeze_channel (bool, optional) – Whether to unsqueeze any channels or not. Defaults to True.

  • generate_sample (bool, optional) – Whether to generate a sample and save it to file or not. Defaults to False.

  • normalize_image (bool, optional) – Whether to normalize the images before returning. Defaults to True.

  • normalize_audio (bool, optional) – Whether to normalize the audio before returning. Defaults to True.

Returns:

Tuple of (training dataloader, validation dataloader, test dataloader)

Return type:

tuple

Module contents