dataeval.utils.data

Provides utility functions for interacting with Computer Vision datasets.

Submodules

datasets

Provides access to common Computer Vision datasets.

Output Classes

SplitDatasetOutput

Output class containing test indices and a list of TrainValSplits.

Functions

batch_voc(dataset, model[, batch_size, flatten_labels])

Iterates through the dataset to generate model embeddings and store labels

read_dataset(dataset)

Extract information from a dataset at each index into individual lists of each information position.

split_dataset(labels[, num_folds, stratify, split_on, ...])

Top level splitting function. Returns a dataclass containing a list of train and validation indices.