MNISTData

class MNISTData

Class for loading MNIST dataset, inherits from deepchecks.vision.classification_data.ClassificationData.

Implement the necessary methods for the deepchecks.vision.classification_data.ClassificationData interface.

__init__(data_loader: DataLoader, num_classes: Optional[int] = None, label_map: Optional[Dict[int, str]] = None, transform_field: Optional[str] = 'transforms')

__new__(*args, **kwargs)

Attributes

MNISTData.classes_indices	Return dict of classes as keys, and list of corresponding indices (in Dataset) of samples that include this class (in the label).
MNISTData.data_dimension	Return how many dimensions the image data have.
MNISTData.data_loader	Return the data loader.
MNISTData.has_images	Return True if the data loader has images.
MNISTData.has_labels	Return True if the data loader has labels.
MNISTData.n_of_samples_per_class	Return a dictionary containing the number of samples per class.
MNISTData.num_classes	Return the number of classes in the dataset.
MNISTData.num_samples	Return the number of samples in the dataset.
MNISTData.original_num_samples	Return the number of samples in the original dataset.
MNISTData.task_type	Return the task type (classification).
MNISTData.transform_field	Return the data loader.

Methods

MNISTData.assert_images_valid()	Assert the image formatter defined is valid.
MNISTData.assert_labels_valid()	Assert the label formatter defined is valid.
MNISTData.batch_of_index(*indices)	Return batch samples of the given batch indices.
MNISTData.batch_to_images(batch)	Convert a batch of mnist data to images.
MNISTData.batch_to_labels(batch)	Convert a batch of mnist data to labels.
MNISTData.copy([n_samples, shuffle, ...])	Create new copy of this object, with the data-loader and dataset also copied, and altered by the given parameters.
MNISTData.from_dataset(data[, batch_size, ...])	Create VisionData instance from a Dataset instance.
MNISTData.get_augmented_dataset(aug)	Return a copy of the vision data object with the augmentation in the start of it.
MNISTData.get_classes(batch_labels)	Get a labels batch and return classes inside it.
MNISTData.get_transform_type()	Return transforms handler created from the transform field.
MNISTData.infer_on_batch(batch, model, device)	Infer on a batch of mnist data.
MNISTData.init_cache()	Initialize the cache of the classes' metadata info.
MNISTData.is_sampled()	Return whether the vision data is running on sample of the data.
MNISTData.label_id_to_name(class_id)	Return the name of the class with the given id.
MNISTData.to_batch(*samples)	Use the defined collate_fn to transform a few data items to batch format.
MNISTData.to_dataset_index(*batch_indices)	Return for the given batch_index the sample index in the dataset object.
MNISTData.update_cache(batch)	Get labels and update the classes' metadata info.
MNISTData.validate_format(model[, device])	Validate the correctness of the data class implementation according to the expected format.
MNISTData.validate_get_classes(batch)	Validate that the get_classes function returns data in the correct format.
MNISTData.validate_image_data(batch)	Validate that the data is in the required format.
MNISTData.validate_infered_batch_predictions(...)	Validate the infered predictions from the batch.
MNISTData.validate_label(batch)	Validate the label.
MNISTData.validate_prediction(batch, model, ...)	Validate the prediction.
MNISTData.validate_shared_label(other)	Verify presence of shared labels.

previous

MNIST.register_function

next

MNISTData.classes_indices