keras

Base R6 class for Keras callbacks

Base R6 class for Keras constraints

Base R6 class for Keras layers

Base R6 class for Keras wrappers

Create a custom Layer

Activation functions

Fits the state of the preprocessing layer to the data being passed.

Instantiates the DenseNet architecture.

Inception-ResNet v2 model, with weights trained on ImageNet

Inception V3 model, with weights pre-trained on ImageNet.

MobileNet model architecture.

MobileNetV2 model architecture

Instantiates a NASNet model.

ResNet50 model for Keras.

VGG16 and VGG19 models for Keras.

Xception V1 model for Keras.

Keras backend tensor engine

Bidirectional wrapper for RNNs.

Callback that streams epoch results to a csv file

Stop training when a monitored quantity has stopped improving.

Create a custom callback

Learning rate scheduler.

Save the model after every epoch.

Callback that prints metrics to stdout.

Reduce learning rate when a metric has stopped improving.

Callback used to stream events to a server.

TensorBoard basic visualizations

Callback that terminates training when a NaN loss is encountered.

Clone a model instance.

Configure a Keras model for training

Weight constraints

Count the total number of scalars composing the weights.

Create a Keras Layer

Create a Keras Wrapper

Boston housing price regression dataset

CIFAR10 small image classification

CIFAR100 small image classification

Fashion-MNIST database of fashion articles

IMDB Movie reviews sentiment classification

MNIST database of handwritten digits

Reuters newswire topics classification

Evaluate a Keras model

Evaluates the model on a data generator.

Export a Saved Model

Train a Keras model

Fits the model on data yielded batch-by-batch by a generator.

Fit image data generator internal statistics to some sample data.

Update tokenizer internal vocabulary based on a list of texts or list of sequences.

Generates batches of augmented/normalized data from image data and labels

Takes the dataframe and the path to a directory and generates batches of augmented/normalized data.

Generates batches of data from images in a directory (with optional augmented/normalized data)

Freeze and unfreeze weights

Retrieve the next item from a generator

Layer/Model configuration

Downloads a file from a URL if it not already in the cache.

Retrieve tensors for layers with multiple nodes

Retrieves a layer based on either its name (unique) or index.

Get the vocabulary for text vectorization layers

Layer/Model weights as R arrays

Representation of HDF5 dataset to be used instead of an R array

Generate batches of image data with real-time data augmentation. The data will be looped over (in batches).

Create a dataset from a directory

Loads an image into PIL format.

3D array representation of images

Decodes the prediction of an ImageNet model.

Preprocesses a tensor or array encoding a batch of images.

Keras implementation

Initializer that generates tensors initialized to a constant value.

Glorot normal initializer, also called Xavier normal initializer.

Glorot uniform initializer, also called Xavier uniform initializer.

He normal initializer.

He uniform variance scaling initializer.

Initializer that generates the identity matrix.

LeCun normal initializer.

LeCun uniform initializer.

Initializer that generates tensors initialized to 1.

Initializer that generates a random orthogonal matrix.

Initializer that generates tensors with a normal distribution.

Initializer that generates tensors with a uniform distribution.

Initializer that generates a truncated normal distribution.

Initializer capable of adapting its scale to the shape of weights.

Initializer that generates tensors initialized to 0.

Install Keras and the TensorFlow backend

Check if Keras is Available

Element-wise absolute value.

Bitwise reduction (logical AND).

Bitwise reduction (logical OR).

Creates a 1D tensor containing a sequence of integers.

Returns the index of the maximum value along an axis.

Returns the index of the minimum value along an axis.

Active Keras backend

Batchwise dot product.

Turn a nD tensor into a 2D tensor with same 1st dimension.

Returns the value of more than one tensor variable.

Applies batch normalization on x given mean, var, beta and gamma.

Sets the values of many tensor variables at once.

Adds a bias vector to a tensor.

Binary crossentropy between an output tensor and a target tensor.

Casts a tensor to a different dtype and returns it.

Cast an array to the default Keras float type.

Categorical crossentropy between an output tensor and a target tensor.

Destroys the current TF graph and creates a new one.

Element-wise value clipping.

Concatenates a list of tensors alongside the specified axis.

Creates a constant tensor.

1D convolution.

2D convolution.

2D deconvolution (i.e. transposed convolution).

3D convolution.

3D deconvolution (i.e. transposed convolution).

Computes cos of x element-wise.

Returns the static number of elements in a Keras variable or tensor.

Runs CTC loss algorithm on each batch element.

Decodes the output of a softmax.

Converts CTC labels from dense to sparse.

Cumulative product of the values in a tensor, alongside the specified axis.

Cumulative sum of the values in a tensor, alongside the specified axis.

Depthwise 2D convolution with separable filters.

Multiplies 2 tensors (and/or variables) and returns a tensor.

Sets entries in x to zero at random, while scaling the entire tensor.

Returns the dtype of a Keras tensor or variable, as a string.

Exponential linear unit.

Fuzz factor used in numeric expressions.

Element-wise equality between two tensors.

Evaluates the value of a variable.

Element-wise exponential.

Adds a 1-sized dimension at index axis.

Instantiate an identity matrix and returns it.

Flatten a tensor.

Default float type

Reduce elems using fn to combine them from left to right.

Reduce elems using fn to combine them from right to left.

Instantiates a Keras function

Retrieves the elements of indices indices in the tensor reference.

TF session to be used by the backend.

Get the uid for the default graph.

Returns the value of a variable.

Returns the shape of a variable.

Returns the gradients of variables w.r.t. loss.

Element-wise truth value of (x > y).

Element-wise truth value of (x >= y).

Segment-wise linear approximation of sigmoid.

Returns a tensor with the same content as the input tensor.

Default image data format convention ('channels_first' or 'channels_last').

Selects x in test phase, and alt otherwise.

Returns whether the targets are in the top k predictions.

Selects x in train phase, and alt otherwise.

Returns the shape of tensor or variable as a list of int or NULL entries.

Returns whether x is a Keras tensor.

Returns whether x is a placeholder.

Returns whether a tensor is a sparse tensor.

Returns whether x is a symbolic tensor.

Normalizes a tensor wrt the L2 norm alongside the specified axis.

Returns the learning phase flag.

Element-wise truth value of (x < y).

Element-wise truth value of (x <= y).

Apply 1D conv with un-shared weights.

Apply 2D conv with un-shared weights.

Element-wise log.

Computes log(sum(exp(elements across dimensions of a tensor))).

Sets the manual variable initialization flag.

Map the function fn over the elements elems and return the outputs.

Maximum value in a tensor.

Element-wise maximum of two tensors.

Mean of a tensor, alongside the specified axis.

Minimum value in a tensor.

Element-wise minimum of two tensors.

Compute the moving average of a variable.

Returns the number of axes in a tensor, as an integer.

Computes mean and std for batch then apply batch_normalization on batch.

Element-wise inequality between two tensors.

Computes the one-hot representation of an integer tensor.

Instantiates an all-ones tensor variable and returns it.

Instantiates an all-ones variable of the same shape as another tensor.

Permutes axes in a tensor.

Instantiates a placeholder tensor and returns it.

2D Pooling.

3D Pooling.

Element-wise exponentiation.

Prints message and the tensor value when evaluated.

Multiplies the values in a tensor, alongside the specified axis.

Returns a tensor with random binomial distribution of values.

Returns a tensor with normal distribution of values.

Instantiates a variable with values drawn from a normal distribution.

Returns a tensor with uniform distribution of values.

Instantiates a variable with values drawn from a uniform distribution.

Rectified linear unit.

Repeats a 2D tensor.

Repeats the elements of a tensor along an axis.

Reset graph identifiers.

Reshapes a tensor to the specified shape.

Resizes the images contained in a 4D tensor.

Resizes the volume contained in a 5D tensor.

Reverse a tensor along the specified axes.

Iterates over the time dimension of a tensor

Element-wise rounding to the closest integer.

2D convolution with separable filters.

Sets the learning phase to a fixed value.

Sets the value of a variable, from an R array.

Returns the symbolic shape of a tensor or variable.

Element-wise sigmoid.

Element-wise sign.

Computes sin of x element-wise.

Softmax of a tensor.

Softplus of a tensor.

Softsign of a tensor.

Categorical crossentropy with integer targets.

Pads the 2nd and 3rd dimensions of a 4D tensor.

Pads 5D tensor with zeros along the depth, height, width dimensions.

Element-wise square root.

Element-wise square.

Removes a 1-dimension from the tensor at index axis.

Stacks a list of rank R tensors into a rank R+1 tensor.

Standard deviation of a tensor, alongside the specified axis.

Returns variables but with zero gradient w.r.t. every other variable.

Sum of the values in a tensor, alongside the specified axis.

Switches between two operations depending on a scalar value.

Element-wise tanh.

Pads the middle dimension of a 3D tensor.

Creates a tensor by tiling x by n.

Converts a sparse tensor into a dense tensor and returns it.

Transposes a tensor and returns it.

Returns a tensor with truncated random normal distribution of values.

Update the value of x to new_x.

Update the value of x by adding increment.

Update the value of x by subtracting decrement.

Variance of a tensor, alongside the specified axis.

Instantiates a variable and returns it.

Instantiates an all-zeros variable and returns it.

Instantiates an all-zeros variable of the same shape as another tensor.

R interface to Keras

Keras array object

Keras Model

Create a Keras custom model

Keras Model composed of a linear stack of layers

Apply an activation function to an output.

Exponential Linear Unit.

Leaky version of a Rectified Linear Unit.

Parametric Rectified Linear Unit.

Rectified Linear Unit activation function

Scaled Exponential Linear Unit.

Softmax activation function.

Thresholded Rectified Linear Unit.

Layer that applies an update to the cost function based input activity.

Layer that adds a list of inputs.

Applies Alpha Dropout to the input.

Creates attention layer

Layer that averages a list of inputs.

Average pooling for temporal data.

Average pooling operation for spatial data.

Average pooling operation for 3D data (spatial or spatio-temporal).

Batch normalization layer (Ioffe and Szegedy, 2014).

Layer that concatenates a list of inputs.

1D convolution layer (e.g. temporal convolution).

Transposed 1D convolution layer (sometimes called Deconvolution).

2D convolution layer (e.g. spatial convolution over images).

Transposed 2D convolution layer (sometimes called Deconvolution).

3D convolution layer (e.g. spatial convolution over volumes).

Transposed 3D convolution layer (sometimes called Deconvolution).

Convolutional LSTM.

Cropping layer for 1D input (e.g. temporal sequence).

Cropping layer for 2D input (e.g. picture).

Cropping layer for 3D data (e.g. spatial or spatio-temporal).

Fast GRU implementation backed by CuDNN.

Fast LSTM implementation backed by CuDNN.

Add a densely-connected NN layer to an output

Constructs a DenseFeatures.

Depthwise separable 2D convolution.

Layer that computes a dot product between samples in two tensors.

Applies Dropout to the input.

Turns positive integers (indexes) into dense vectors of fixed size.

Flattens an input

Apply multiplicative 1-centered Gaussian noise.

Apply additive zero-centered Gaussian noise.

Global average pooling operation for temporal data.

Global average pooling operation for spatial data.

Global Average pooling operation for 3D data.

Global max pooling operation for temporal data.

Global max pooling operation for spatial data.

Global Max pooling operation for 3D data.

Gated Recurrent Unit - Cho et al.

Input layer

Wraps arbitrary expression as a layer

Layer normalization layer (Ba et al., 2016).

Locally-connected layer for 1D inputs.

Locally-connected layer for 2D inputs.

Long Short-Term Memory unit - Hochreiter 1997.

Masks a sequence by using a mask value to skip timesteps.

Max pooling operation for temporal data.

Max pooling operation for spatial data.

Max pooling operation for 3D data (spatial or spatio-temporal).

Layer that computes the maximum (element-wise) a list of inputs.

Layer that computes the minimum (element-wise) a list of inputs.

MultiHeadAttention layer

Layer that multiplies (element-wise) a list of inputs.

Permute the dimensions of an input according to a given pattern

Repeats the input n times.

Reshapes an output to a certain shape.

Depthwise separable 1D convolution.

Separable 2D convolution.

Fully-connected RNN where the output is to be fed back to input.

Spatial 1D version of Dropout.

Spatial 2D version of Dropout.

Spatial 3D version of Dropout.

Layer that subtracts two inputs.

Text vectorization layer

Upsampling layer for 1D inputs.

Upsampling layer for 2D inputs.

Upsampling layer for 3D inputs.

Zero-padding layer for 1D input (e.g. temporal sequence).

Zero-padding layer for 2D input (e.g. picture).

Zero-padding layer for 3D data (spatial or spatio-temporal).

Computes the binary crossentropy loss.

Model loss functions

Generates a word rank-based probabilistic sampling table.

Model performance metrics

Load a Keras model from the Saved Model format

Model configuration as JSON

Export to Saved Model format

Model configuration as YAML

Assign values to names

Replicates a model on different GPUs.

Normalize a matrix or nd-array

Adadelta optimizer.

Adagrad optimizer.

Adam optimizer

Adamax optimizer

Nesterov Adam optimizer

RMSProp optimizer

Stochastic gradient descent optimizer

Pads sequences to the same length

Pipe operator

Plot training history

Remove the last layer in a model

Generate predictions from a Keras model

Generates predictions for the input samples from a data generator.

Returns predictions for a single batch of samples.

Generates probability or class probability predictions for the input samples.

Objects exported from other packages

L1 and L2 regularization

Reset the states for a layer

Save/Load models using HDF5 files

Save/Load models using SavedModel format

Save/Load model weights using HDF5 files

Save model weights in the SavedModel format

Save a text tokenizer to an external file

Convert a list of sequences into a matrix.

Serialize a model to an R object

Sets vocabulary (and optionally document frequency) data for the layer

Generates skipgram word pairs.

Print a summary of a Keras model

Converts a text to a sequence of indexes in a fixed-size hashing space.

One-hot encode a text into a list of word indexes in a vocabulary of size n.

Convert text to a sequence of words (or tokens).

Text tokenization utility

Convert a list of texts to a matrix.

Transform each text in texts in a sequence of integers.

Transforms each text in texts in a sequence of integers.

Apply a layer to every temporal slice of an input.

Utility function for generating batches of temporal data.

Converts a class vector (integers) to binary class matrix.

Single gradient update or model evaluation over one batch of samples.

Select a Keras implementation and backend

Provide a scope with mappings of names to custom objects