Layers

A layer representing an RNN cell that is the base class for implementing RNN cells with custom behavior.

A layer that applies an activation function to an output.

A regularization layer that applies an update to the cost function based on input activity.

aka AdaptiveAvgPool1D

A pooling layer that applies a 1D adaptive average pooling over an input signal composed of several input planes.

aka AdaptiveAvgPool2D

A pooling layer that applies a 2D adaptive average pooling over an input signal composed of several input planes.

aka AdaptiveAvgPool3D

A pooling layer that applies a 3D adaptive average pooling over an input signal composed of several input planes.

aka AdaptiveMaxPool1D

A pooling layer that applies a 1D adaptive max pooling over an input signal composed of several input planes.

aka AdaptiveMaxPool2D

A pooling layer that applies a 2D adaptive max pooling over an input signal composed of several input planes.

aka AdaptiveMaxPool3D

A pooling layer that applies a 3D adaptive max pooling over an input signal composed of several input planes.

A merging layer that adds a list of inputs taking as input a list of tensors all of the same shape.

A layer that adds inputs from one or more other layers to cells or neurons of a target layer.

An attention layer that implements additive attention also known as Bahdanau-style attention.

A regularization layer that applies Alpha Dropout to the input keeping mean and variance of inputs to ensure self-normalizing property.

A layer that implements dot-product attention also known as Luong-style attention.

A merging layer that averages a list of inputs element-wise taking as input a list of tensors all of the same shape.

aka AvgPool1D

A pooling layer that performs average pooling for temporal data.

aka AvgPool2D

A pooling layer that performs average pooling for spatial data.

aka AvgPool3D

A pooling layer that performs average pooling for 3D data (spatial or spatio-temporal).

aka AvgPool1D

A pooling layer that applies a 1D average pooling over an input signal composed of several input planes.

aka AvgPool2D

A pooling layer that applies a 2D average pooling over an input signal composed of several input planes.

aka AvgPool3D

A pooling layer that applies a 3D average pooling over an input signal composed of several input planes.

An input layer that receives values from another layer.

aka BatchNorm1D

A batch normalization layer that applies Batch Normalization over a 2D or 3D input.

aka BatchNorm2D

A batch normalization layer that applies Batch Normalization over a 4D input.

aka BatchNorm3D

A batch normalization layer that applies Batch Normalization over a 5D input.

aka BatchNorm

A normalization layer that normalizes its inputs applying a transformation that maintains the mean close to 0 and the standard deviation clo…

A recurrent layer that is a bidirectional wrapper for RNNs.

A layer that performs categorical data preprocessing operations.

A categorical features preprocessing layer that encodes integer features providing options for condensing data into a categorical encoding.

An image preprocessing layer that crops the central portion of images to a target size.

A merging layer that concatenates a list of inputs taking as input a list of tensors all of the same shape except for the concatenation axis…

A convolutional layer that implements a 1D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations.

A convolutional layer that implements a 2D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations.

A convolutional layer that implements a 3D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations.

aka Conv1D, Conv1D Layer…

A convolutional layer that implements 1D convolution (e.g. temporal convolution).

aka Conv1DTranspose Layer, ConvTranspose1D…

A convolutional layer that implements transposed 1D convolution sometimes called deconvolution.

aka Conv2D, Conv2D Layer…

A convolutional layer that implements 2D convolution (e.g. spatial convolution over images).

aka Conv2DTranspose Layer, ConvTranspose2D…

A convolutional layer that implements transposed 2D convolution

aka Conv3D, Conv3D Layer…

A convolutional layer that implements 3D convolution (e.g. spatial convolution over volumes).

aka Conv3DTranspose Layer, ConvTranspose3D…

A convolutional layer that implements transposed 3D convolution

A layer that contains a set of filters (or kernels) parameters of which are to be learned throughout the training.

A reshaping layer that crops along the time dimension (axis 1) for 1D input.

A layer that crops along spatial dimensions (i.e. height and width) for 2D input.

A layer that crops along spatial dimensions (depth, height and width) for 3D input.

A layer that is a regular densely-connected neural network layer.

A layer that produces a dense tensor based on given feature columns.

A convolutional layer that performs depthwise 1D convolution

A convolutional layer that performs depthwise 2D convolution

A numerical features preprocessing layer which buckets continuous features by ranges.

A layer that computes a dot product between samples in two tensors.

A regularization layer that applies Dropout to the input

An activation layer that applies the Exponential Linear Unit (ELU) function element-wise.

A layer that turns positive integers (indexes) into dense vectors of fixed size.

A reshaping layer that flattens the input

aka FractionalMaxPool2D

A pooling layer that applies a 2D fractional max pooling over an input signal composed of several input planes.

aka FractionalMaxPool3D

A pooling layer that applies a 3D fractional max pooling over an input signal composed of several input planes.

A regularization layer that applies multiplicative 1-centered Gaussian noise.

A regularization layer that applies additive zero-centered Gaussian noise.

aka GlobalAvgPool1D

A pooling layer that performs global average pooling operation for temporal data.

aka GlobalAvgPool2D

A pooling layer that performs global average pooling operation for spatial data.

aka GlobalAvgPool3D

A pooling layer that performs global average pooling operation for 3D data.

aka GlobalMaxPool1D

A pooling layer that performs global max pooling operation for temporal data.

aka GlobalMaxPool2D

A pooling layer that performs global max pooling operation for spatial data.

aka GlobalMaxPool3D

A pooling layer that performs global max pooling operation for 3D data.

aka GroupNorm

A normalization layer that applies Group Normalization over a mini-batch of inputs.

A recurrent layer that implements the Gated Recurrent Unit architecture.

A layer that processes one step within the whole time sequence input for a GRU layer.

A categorical features preprocessing layer which hashes and bins categorical features.

A layer located between the input and output that performs nonlinear transformations of the inputs entered into the network.

A layer that performs image data preprocessing augmentations.

A layer that performs image data preprocessing operations.

A layer composed of artificial input neurons that brings the initial data into the system for further processing by subsequent layers.

A layer to be used as an entry point into a Network (a graph of layers).

A layer that specifies the rank, dtype and shape of every input to a layer.

aka InstanceNorm1D

A normalization layer that applies Instance Normalization over a 2D (unbatched) or 3D (batched) input.

A normalization layer that applies Instance Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension).

aka InstanceNorm3D

A normalization layer that applies Instance Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension).

A categorical features preprocessing layer that maps integer features to contiguous ranges.

A layer that obtains the dot product of input values or subsets of input values.

A layer that wraps arbitrary expressions as a Layer object.

A structure or network topology in a deep learning model that takes information from previous layers and passes it to the next layer.

A layer from which other layers can inherit.

aka LayerNorm

A normalization layer that applies Layer Normalization over a mini-batch of inputs.

A normalization layer that applies Layer Normalization over the inputs.

aka LazyBatchNorm1D

A batch normalization layer that lazily initializes the num_features argument from the input size for 1D data.

aka LazyBatchNorm2D

A batch normalization layer that lazily initializes the num_features argument from the input size for 2D data.

aka LazyBatchNorm3D

A batch normalization layer that lazily initializes the num_features argument from the input size for 3D data.

aka LazyInstanceNorm1D

A normalization layer that lazily initializes the num_features argument from the input size for 1D data.

aka LazyInstanceNorm2D

A normalization layer that lazily initializes the num_features argument from the input size for 2D data.

aka LazyInstanceNorm3D

A normalization that lazily initializes the num_features argument from the input size for 3D data.

An activation layer that applies the leaky rectified linear unit function element-wise.

A layer that works similarly to the Convolution1D layer, except that weights are unshared, that is, a different set of filters is applied at…

A locally-connected layer for 1D inputs where each patch of the input is convolved with a different set of filters.

A locally-connected layer for 2D inputs where each patch of the input is convolved with a different set of filters.

aka LocalResponseNorm

A normalization layer that applies local response normalization over an input signal composed of several input planes.

aka LPPool1D

A pooling layer that applies 1D power-average pooling over an input signal composed of several input planes.

aka LPPool2D

A pooling layer that applies 2D power-average pooling over an input signal composed of several input planes.

A recurrent layer that implements the Long Short-Term Memory architecture.

A layer that processes one step within the whole time sequence input for an LSTM layer.

A layer that masks a sequence by using a mask value to skip timesteps.

An input layer with a shape corresponding to that of the output layer.

A merging layer that computes the maximum (element-wise) of a list of inputs.

aka MaxPool1D, MaxPooling1D

A pooling layer that performs max pooling operation for temporal data.

aka MaxPool2D, MaxPooling2D

A pooling layer that performs max pooling operation for spatial data.

aka MaxPool3D, MaxPooling3D

A pooling layer that performs max pooling operation for 3D data (spatial or spatio-temporal).

aka MaxUnpool1D

A pooling layer that computes a partial inverse of MaxPool1D.

aka MaxUnpool2D

A pooling layer that computes a partial inverse of MaxPool2D.

aka MaxUnpool3D

A pooling layer that computes a partial inverse of MaxPool3D.

A layer of cells, each with an internal state or weights.

A layer used to merge a list of inputs.

A merging layer that computes the minimum (element-wise) of a list of inputs.

An attention layer that allows the model to attend to information from different representation subspaces.

A merging layer that multiplies (element-wise) a list of inputs.

A layer that is a densely-connected neural network layer with added noise for regularization.

An input layer that adds noise to each value.

A numerical features preprocessing layer that normalizes continuous features.

A layer that performs numerical data preprocessing operations.

A layer containing the last neurons in the network that produces given outputs for the program.

A reshaping layer that permutes the dimensions of the input according to a given pattern.

A layer that, after taking a set of states or values as input, predicts a probability distribution of actions to take.

A layer that serves to mitigate the sensitivity of convolutional layers to location and spatially downsample representations.

An activation layer that applies parametric rectified linear unit function element-wise.

A layer that performs data preprocessing operations.

A hidden layer that estimates the probability of a sample being within a certain category.

An image preprocessing layer that randomly adjusts brightness during training.

An image preprocessing layer that randomly adjusts contrast during training.

An image preprocessing layer that randomly crops images during training.

An image preprocessing layer that randomly flips images during training.

An image preprocessing layer that randomly varies image height during training.

An image preprocessing layer that randomly rotates images during training.

An image preprocessing layer that randomly translates images during training.

An image preprocessing layer that randomly varies image width during training.

An image preprocessing layer that randomly zooms in or out on images during training.

A layer composed of recurrent units with the number equal to the hidden size of the layer.

A layer that applies penalties on layer parameters or layer activity during optimization summed into the loss function that the network opti…

An activation layer that applies the rectified linear unit function element-wise.

A reshaping layer that repeats the input n times.

An image preprocessing layer that rescales input values to a new range.

A reshaping layer that reshapes the inputs into the given shape.

aka Reshape Layer

A layer that is used to change the shape of the input.

An image preprocessing layer that resizes images to a target size.

The base class for recurrent layers.

aka SeparableConv1D Layer

A convolutional layer that performs depthwise separable 1D convolution.

aka SeparableConv2D Layer

A convolutional layer that performs depthwise separable 2D convolution.

A recurrent layer that implements a fully-connected RNN where the output is to be fed back to input.

A layer that processes one step within the whole time sequence input for a SimpleRNN layer.

An activation layer that applies the softmax function to the inputs.

A regularization layer that performs the same function as Dropout but drops entire 1D feature maps instead of individual elements.

A regularization layer that performs the same function as Dropout but drops entire 2D feature maps instead of individual elements.

A regularization layer that performs the same function as Dropout but drops entire 3D feature maps instead of individual elements.

A hidden layer that makes connections to an additional, heterogeneous hidden layer; modeled after biological neural networks.

A layer that allows a stack of RNN cells to behave as a single cell.

A categorical features preprocessing layer that maps string features to integer indices.

A merging layer that subtracts two inputs.

aka SyncBatchNorm

A batch normalization layer that applies synchronous Batch Normalization across multiple devices.

A layer that performs text data preprocessing operations.

A text preprocessing layer that maps text features to integer sequences.

An activation layer that applies the thresholded rectified linear unit function element-wise.

A recurrent layer that applies a layer to every temporal slice of an input.

A recurrent layer that normalizes a batch of inputs so that each input in the batch has a L2 norm equal to 1.

A reshaping layer that upsamples the input by repeating each temporal step size times along the time axis.

A layer that upsamples the input by repeating each row and column size times.

A layer that upsamples the input by repeating each depth, height and width size times.

A layer of values to be applied to other cells or neurons in a network.

A layer that augment the functionality of another layer.

A reshaping layer that zero-pads the input along the time axis.

A reshaping layer that zero-pads the input along the height and width dimensions.

A reshaping layer that zero-pads the input along the depth, height and width dimensions.