<br />

<button value="stable" default="">See Stable</button> <button value="nightly">See Nightly</button>

<br />

DO NOT EDIT.

This file was autogenerated. Do not edit it by hand,
since your modifications would be overwritten.

## Classes

[`class Activation`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Activation): Applies an activation function to an output.

[`class ActivityRegularization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/ActivityRegularization): Layer that applies an update to the cost function based input activity.

[`class AdaptiveAveragePooling1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AdaptiveAveragePooling1D): Adaptive average pooling operation for 1D temporal or spatial data.

[`class AdaptiveAveragePooling2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AdaptiveAveragePooling2D): Adaptive average pooling operation for 2D spatial data.

[`class AdaptiveAveragePooling3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AdaptiveAveragePooling3D): Adaptive average pooling operation for 3D volumetric data.

[`class AdaptiveMaxPooling1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AdaptiveMaxPooling1D): Adaptive max pooling operation for 1D temporal or spatial data.

[`class AdaptiveMaxPooling2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AdaptiveMaxPooling2D): Adaptive max pooling operation for 2D spatial data.

[`class AdaptiveMaxPooling3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AdaptiveMaxPooling3D): Adaptive max pooling operation for 3D volumetric data.

[`class Add`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Add): Performs elementwise addition operation.

[`class AdditiveAttention`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AdditiveAttention): Additive attention layer, a.k.a. Bahdanau-style attention.

[`class AlphaDropout`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AlphaDropout): DEPRECATED.

[`class Attention`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Attention): Dot-product attention layer, a.k.a. Luong-style attention.

[`class AugMix`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AugMix): Performs the AugMix data augmentation technique.

[`class AutoContrast`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AutoContrast): Performs the auto-contrast operation on an image.

[`class Average`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Average): Averages a list of inputs element-wise..

[`class AveragePooling1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling1D): Average pooling for temporal data.

[`class AveragePooling2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling2D): Average pooling operation for 2D spatial data.

[`class AveragePooling3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling3D): Average pooling operation for 3D data (spatial or spatio-temporal).

[`class AvgPool1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling1D): Average pooling for temporal data.

[`class AvgPool2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling2D): Average pooling operation for 2D spatial data.

[`class AvgPool3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling3D): Average pooling operation for 3D data (spatial or spatio-temporal).

[`class BatchNormalization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/BatchNormalization): Layer that normalizes its inputs.

[`class Bidirectional`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Bidirectional): Bidirectional wrapper for RNNs.

[`class CategoryEncoding`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/CategoryEncoding): A preprocessing layer which encodes integer features.

[`class CenterCrop`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/CenterCrop): A preprocessing layer which crops images.

[`class Concatenate`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Concatenate): Concatenates a list of inputs.

[`class ContrastLimitedAdaptiveHistogramEqualization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/ContrastLimitedAdaptiveHistogramEqualization): Contrast Limited Adaptive Histogram Equalization (CLAHE) layer.

[`class Conv1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv1D): 1D convolution layer (e.g. temporal convolution).

[`class Conv1DTranspose`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv1DTranspose): 1D transposed convolution layer.

[`class Conv2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2D): 2D convolution layer.

[`class Conv2DTranspose`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2DTranspose): 2D transposed convolution layer.

[`class Conv3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv3D): 3D convolution layer.

[`class Conv3DTranspose`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv3DTranspose): 3D transposed convolution layer.

[`class ConvLSTM1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/ConvLSTM1D): 1D Convolutional LSTM.

[`class ConvLSTM2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/ConvLSTM2D): 2D Convolutional LSTM.

[`class ConvLSTM3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/ConvLSTM3D): 3D Convolutional LSTM.

[`class Convolution1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv1D): 1D convolution layer (e.g. temporal convolution).

[`class Convolution1DTranspose`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv1DTranspose): 1D transposed convolution layer.

[`class Convolution2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2D): 2D convolution layer.

[`class Convolution2DTranspose`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2DTranspose): 2D transposed convolution layer.

[`class Convolution3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv3D): 3D convolution layer.

[`class Convolution3DTranspose`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv3DTranspose): 3D transposed convolution layer.

[`class Cropping1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Cropping1D): Cropping layer for 1D input (e.g. temporal sequence).

[`class Cropping2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Cropping2D): Cropping layer for 2D input (e.g. picture).

[`class Cropping3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Cropping3D): Cropping layer for 3D data (e.g. spatial or spatio-temporal).

[`class CutMix`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/CutMix): CutMix data augmentation technique.

[`class Dense`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dense): Just your regular densely-connected NN layer.

[`class DepthwiseConv1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/DepthwiseConv1D): 1D depthwise convolution layer.

[`class DepthwiseConv2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/DepthwiseConv2D): 2D depthwise convolution layer.

[`class Discretization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Discretization): A preprocessing layer which buckets continuous features by ranges.

[`class Dot`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dot): Computes element-wise dot product of two tensors.

[`class Dropout`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dropout): Applies dropout to the input.

[`class ELU`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/ELU): Applies an Exponential Linear Unit function to an output.

[`class EinsumDense`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/EinsumDense): A layer that uses `einsum` as the backing computation.

[`class Embedding`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Embedding): Turns nonnegative integers (indexes) into dense vectors of fixed size.

[`class Equalization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Equalization): Preprocessing layer for histogram equalization on image channels.

[`class Flatten`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Flatten): Flattens the input. Does not affect the batch size.

[`class FlaxLayer`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/FlaxLayer): Keras Layer that wraps a [Flax](https://flax.readthedocs.io) module.

[`class GRU`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GRU): Gated Recurrent Unit - Cho et al. 2014.

[`class GRUCell`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GRUCell): Cell class for the GRU layer.

[`class GaussianDropout`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GaussianDropout): Apply multiplicative 1-centered Gaussian noise.

[`class GaussianNoise`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GaussianNoise): Apply additive zero-centered Gaussian noise.

[`class GlobalAveragePooling1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling1D): Global average pooling operation for temporal data.

[`class GlobalAveragePooling2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling2D): Global average pooling operation for 2D data.

[`class GlobalAveragePooling3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling3D): Global average pooling operation for 3D data.

[`class GlobalAvgPool1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling1D): Global average pooling operation for temporal data.

[`class GlobalAvgPool2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling2D): Global average pooling operation for 2D data.

[`class GlobalAvgPool3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling3D): Global average pooling operation for 3D data.

[`class GlobalMaxPool1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPool1D): Global max pooling operation for temporal data.

[`class GlobalMaxPool2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPool2D): Global max pooling operation for 2D data.

[`class GlobalMaxPool3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPool3D): Global max pooling operation for 3D data.

[`class GlobalMaxPooling1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPool1D): Global max pooling operation for temporal data.

[`class GlobalMaxPooling2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPool2D): Global max pooling operation for 2D data.

[`class GlobalMaxPooling3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPool3D): Global max pooling operation for 3D data.

[`class GroupNormalization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GroupNormalization): Group normalization layer.

[`class GroupQueryAttention`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GroupQueryAttention): Grouped Query Attention layer.

[`class HashedCrossing`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/HashedCrossing): A preprocessing layer which crosses features using the "hashing trick".

[`class Hashing`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Hashing): A preprocessing layer which hashes and bins categorical features.

[`class Identity`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Identity): Identity layer.

[`class InputLayer`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/InputLayer): This is the class from which all layers inherit.

[`class InputSpec`](https://www.tensorflow.org/api_docs/python/tf/keras/InputSpec): Specifies the rank, dtype and shape of every input to a layer.

[`class IntegerLookup`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/IntegerLookup): A preprocessing layer that maps integers to (possibly encoded) indices.

[`class JaxLayer`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/JaxLayer): Keras Layer that wraps a JAX model.

[`class LSTM`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/LSTM): Long Short-Term Memory layer - Hochreiter 1997.

[`class LSTMCell`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/LSTMCell): Cell class for the LSTM layer.

[`class Lambda`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Lambda): Wraps arbitrary expressions as a `Layer` object.

[`class Layer`](https://www.tensorflow.org/api_docs/python/tf/keras/Layer): This is the class from which all layers inherit.

[`class LayerNormalization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/LayerNormalization): Layer normalization layer (Ba et al., 2016).

[`class LeakyReLU`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/LeakyReLU): Leaky version of a Rectified Linear Unit activation layer.

[`class Masking`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Masking): Masks a sequence by using a mask value to skip timesteps.

[`class MaxNumBoundingBoxes`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxNumBoundingBoxes): Ensure the maximum number of bounding boxes.

[`class MaxPool1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool1D): Max pooling operation for 1D temporal data.

[`class MaxPool2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool2D): Max pooling operation for 2D spatial data.

[`class MaxPool3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool3D): Max pooling operation for 3D data (spatial or spatio-temporal).

[`class MaxPooling1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool1D): Max pooling operation for 1D temporal data.

[`class MaxPooling2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool2D): Max pooling operation for 2D spatial data.

[`class MaxPooling3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool3D): Max pooling operation for 3D data (spatial or spatio-temporal).

[`class Maximum`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Maximum): Computes element-wise maximum on a list of inputs.

[`class MelSpectrogram`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/MelSpectrogram): A preprocessing layer to convert raw audio signals to Mel spectrograms.

[`class Minimum`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Minimum): Computes elementwise minimum on a list of inputs.

[`class MixUp`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/MixUp): MixUp implements the MixUp data augmentation technique.

[`class MultiHeadAttention`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/MultiHeadAttention): MultiHeadAttention layer.

[`class Multiply`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Multiply): Performs elementwise multiplication.

[`class Normalization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Normalization): A preprocessing layer that normalizes continuous features.

[`class PReLU`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/PReLU): Parametric Rectified Linear Unit activation layer.

[`class Permute`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Permute): Permutes the dimensions of the input according to a given pattern.

[`class Pipeline`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Pipeline): Applies a series of layers to an input.

[`class RMSNormalization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RMSNormalization): Root Mean Square (RMS) Normalization layer.

[`class RNN`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RNN): Base class for recurrent layers.

[`class RandAugment`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandAugment): RandAugment performs the Rand Augment operation on input images.

[`class RandomBrightness`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomBrightness): A preprocessing layer which randomly adjusts brightness during training.

[`class RandomColorDegeneration`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomColorDegeneration): Randomly performs the color degeneration operation on given images.

[`class RandomColorJitter`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomColorJitter): RandomColorJitter class randomly apply brightness, contrast, saturation and hue image processing operation sequentially and randomly on the input.

[`class RandomContrast`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomContrast): A preprocessing layer which randomly adjusts contrast during training.

[`class RandomCrop`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomCrop): A preprocessing layer which randomly crops images during training.

[`class RandomElasticTransform`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomElasticTransform): A preprocessing layer that applies random elastic transformations.

[`class RandomErasing`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomErasing): Random Erasing data augmentation technique.

[`class RandomFlip`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomFlip): A preprocessing layer which randomly flips images during training.

[`class RandomGaussianBlur`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomGaussianBlur): Applies random Gaussian blur to images for data augmentation.

[`class RandomGrayscale`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomGrayscale): Preprocessing layer for random conversion of RGB images to grayscale.

[`class RandomHeight`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomHeight): DEPRECATED.

[`class RandomHue`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomHue): Randomly adjusts the hue on given images.

[`class RandomInvert`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomInvert): Preprocessing layer for random inversion of image colors.

[`class RandomPerspective`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomPerspective): A preprocessing layer that applies random perspective transformations.

[`class RandomPosterization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomPosterization): Reduces the number of bits for each color channel.

[`class RandomRotation`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomRotation): A preprocessing layer which randomly rotates images during training.

[`class RandomSaturation`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomSaturation): Randomly adjusts the saturation on given images.

[`class RandomSharpness`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomSharpness): Randomly performs the sharpness operation on given images.

[`class RandomShear`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomShear): A preprocessing layer that randomly applies shear transformations to images.

[`class RandomTranslation`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomTranslation): A preprocessing layer which randomly translates images during training.

[`class RandomWidth`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomWidth): DEPRECATED.

[`class RandomZoom`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomZoom): A preprocessing layer which randomly zooms images during training.

[`class ReLU`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/ReLU): Rectified Linear Unit activation function layer.

[`class RepeatVector`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RepeatVector): Repeats the input n times.

[`class Rescaling`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Rescaling): A preprocessing layer which rescales input values to a new range.

[`class Reshape`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Reshape): Layer that reshapes inputs into the given shape.

[`class Resizing`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Resizing): A preprocessing layer which resizes images.

[`class ReversibleEmbedding`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/ReversibleEmbedding): An embedding layer which can project backwards to the input dim.

[`class STFTSpectrogram`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/STFTSpectrogram): Layer to compute the Short-Time Fourier Transform (STFT) on a 1D signal.

[`class SeparableConv1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/SeparableConv1D): 1D separable convolution layer.

[`class SeparableConv2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/SeparableConv2D): 2D separable convolution layer.

[`class SeparableConvolution1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/SeparableConv1D): 1D separable convolution layer.

[`class SeparableConvolution2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/SeparableConv2D): 2D separable convolution layer.

[`class SimpleRNN`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/SimpleRNN): Fully-connected RNN where the output is to be fed back as the new input.

[`class SimpleRNNCell`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/SimpleRNNCell): Cell class for SimpleRNN.

[`class Softmax`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Softmax): Softmax activation layer.

[`class Solarization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Solarization): Applies `(max_value - pixel + min_value)` for each pixel in the image.

[`class SpatialDropout1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/SpatialDropout1D): Spatial 1D version of Dropout.

[`class SpatialDropout2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/SpatialDropout2D): Spatial 2D version of Dropout.

[`class SpatialDropout3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/SpatialDropout3D): Spatial 3D version of Dropout.

[`class SpectralNormalization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/SpectralNormalization): Performs spectral normalization on the weights of a target layer.

[`class StackedRNNCells`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/StackedRNNCells): Wrapper allowing a stack of RNN cells to behave as a single cell.

[`class StringLookup`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/StringLookup): A preprocessing layer that maps strings to (possibly encoded) indices.

[`class Subtract`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Subtract): Performs elementwise subtraction.

[`class TFSMLayer`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/TFSMLayer): Reload a Keras model/layer that was saved via SavedModel / ExportArchive.

[`class TextVectorization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/TextVectorization): A preprocessing layer which maps text features to integer sequences.

[`class ThresholdedReLU`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/ThresholdedReLU): DEPRECATED.

[`class TimeDistributed`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/TimeDistributed): This wrapper allows to apply a layer to every temporal slice of an input.

[`class TorchModuleWrapper`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/TorchModuleWrapper): Torch module wrapper layer.

[`class UnitNormalization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/UnitNormalization): Unit normalization layer.

[`class UpSampling1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/UpSampling1D): Upsampling layer for 1D inputs.

[`class UpSampling2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/UpSampling2D): Upsampling layer for 2D inputs.

[`class UpSampling3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/UpSampling3D): Upsampling layer for 3D inputs.

[`class Wrapper`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Wrapper): Abstract wrapper base class.

[`class ZeroPadding1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/ZeroPadding1D): Zero-padding layer for 1D input (e.g. temporal sequence).

[`class ZeroPadding2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/ZeroPadding2D): Zero-padding layer for 2D input (e.g. picture).

[`class ZeroPadding3D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/ZeroPadding3D): Zero-padding layer for 3D data (spatial or spatio-temporal).

## Functions

[`Input(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/Input): Used to instantiate a Keras tensor.

[`add(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/add): Functional interface to the [`keras.layers.Add`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Add) layer.

[`average(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/average): Functional interface to the [`keras.layers.Average`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Average) layer.

[`concatenate(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/concatenate): Functional interface to the `Concatenate` layer.

[`deserialize(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/deserialize): Returns a Keras layer object via its configuration.

[`dot(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/dot): Functional interface to the `Dot` layer.

[`maximum(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/maximum): Functional interface to the [`keras.layers.Maximum`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Maximum) layer.

[`minimum(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/minimum): Functional interface to the [`keras.layers.Minimum`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Minimum) layer.

[`multiply(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/multiply): Functional interface to the [`keras.layers.Multiply`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Multiply) layer.

[`serialize(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/serialize): Returns the layer configuration as a Python dict.

[`subtract(...)`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/subtract): Functional interface to the [`keras.layers.Subtract`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Subtract) layer.