tf.keras.preprocessing.image.Iterator

Class Iterator

Inherits From: Sequence

Defined in tensorflow/python/keras/_impl/keras/preprocessing/image.py.

Base class for image data iterators.

Every Iterator must implement the _get_batches_of_transformed_samples method.

Arguments:

• n: Integer, total number of samples in the dataset to loop over.
• batch_size: Integer, size of a batch.
• shuffle: Boolean, whether to shuffle the data between epochs.
• seed: Random seeding for data shuffling.

Methods

__init__

__init__(
    n,
    batch_size,
    shuffle,
    seed
)

Initialize self. See help(type(self)) for accurate signature.

__getitem__

__getitem__(idx)

Gets batch at position index.

Arguments:

• index: position of the batch in the Sequence.

Returns:

A batch

__iter__

__iter__()

Creates an infinite generator that iterate over the Sequence.

Yields:

Sequence items.

__len__

__len__()

Number of batch in the Sequence.

Returns:

The number of batches in the Sequence.

__next__

__next__(
    *args,
    **kwargs
)

on_epoch_end

on_epoch_end()

Method called at the end of every epoch.

reset

reset()