TensorFlow 1 version

View source on GitHub

Base class for image data iterators.

Inherits From: Sequence

tf.keras.preprocessing.image.Iterator(
    n, batch_size, shuffle, seed
)

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

next

next()

For python 2.x.

Returns

The next batch.

on_epoch_end

on_epoch_end()

Method called at the end of every epoch.

reset

reset()

__getitem__

__getitem__(
    idx
)

Gets batch at position index.

__iter__

__iter__()

Create a generator that iterate over the Sequence.

__len__

__len__()

Number of batch in the Sequence.

Class Variables

• white_list_formats