tlt.datasets.image_classification.tfds_image_classification_dataset.TFDSImageClassificationDataset

class tlt.datasets.image_classification.tfds_image_classification_dataset.TFDSImageClassificationDataset(dataset_dir, dataset_name, split=['train'], as_supervised=True, shuffle_files=True, seed=None, **kwargs)

An image classification dataset from the TensorFlow datasets catalog

__init__(dataset_dir, dataset_name, split=['train'], as_supervised=True, shuffle_files=True, seed=None, **kwargs)

Class constructor

Methods

__init__(dataset_dir, dataset_name[, split, ...])	Class constructor
get_batch([subset])	Get a single batch of images and labels from the dataset.
get_inc_dataloaders()
preprocess(image_size, batch_size[, ...])	Preprocess the dataset to convert to float32, resize, and batch the images
shuffle_split([train_pct, val_pct, ...])	Randomly split the dataset into train, validation, and test subsets with a pseudo-random seed option.

Attributes

class_names	Returns the list of class names
dataset	Returns the framework dataset object (tf.data.Dataset)
dataset_catalog	The string name of the dataset catalog (or None)
dataset_dir	Host directory containing the dataset files
dataset_name	Name of the dataset
info	Returns a dictionary of information about the dataset
test_subset	A subset of the dataset held out for final testing/evaluation
train_subset	A subset of the dataset used for training
validation_subset	A subset of the dataset used for validation/evaluation