Sehen Sie sich Keynotes, Produktsitzungen, Workshops und mehr in Google I / O an. Siehe Wiedergabeliste

Module: tf.keras.layers.experimental.preprocessing

Public API for tf.keras.layers.experimental.preprocessing namespace.

Classes

class CategoryCrossing: Category crossing layer.

class CategoryEncoding: Category encoding layer.

class CenterCrop: Crop the central portion of the images to target height and width.

class Discretization: Buckets data into discrete ranges.

class Hashing: Implements categorical feature hashing, also known as "hashing trick".

class IntegerLookup: Reindex integer inputs to be in a contiguous range, via a dict lookup.

class Normalization: Feature-wise normalization of the data.

class PreprocessingLayer: Base class for Preprocessing Layers.

class RandomContrast: Adjust the contrast of an image or images by a random factor.

class RandomCrop: Randomly crop the images to target height and width.

class RandomFlip: Randomly flip each image horizontally and vertically.

class RandomHeight: Randomly vary the height of a batch of images during training.

class RandomRotation: Randomly rotate each image.

class RandomTranslation: Randomly translate each image during training.

class RandomWidth: Randomly vary the width of a batch of images during training.

class RandomZoom: Randomly zoom each image during training.

class Rescaling: Multiply inputs by scale and adds offset.

class Resizing: Image resizing layer.

class StringLookup: Maps strings from a vocabulary to integer indices.

class TextVectorization: Text vectorization layer.