# Function Reference

## Keras Models

keras_model

Keras Model

keras_model_sequential

Keras Model composed of a linear stack of layers

multi_gpu_model

Replicates a model on different GPUs.

summary

Print a summary of a Keras model

compile

Configure a Keras model for training

fit

Train a Keras model

evaluate

Evaluate a Keras model

export_savedmodel

Export a Saved Model

fit_generator

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

evaluate_generator

Evaluates the model on a data generator.

predict

Generate predictions from a Keras model

predict_proba predict_classes

Generates probability or class probability predictions for the input samples.

predict_on_batch

Returns predictions for a single batch of samples.

predict_generator

Generates predictions for the input samples from a data generator.

train_on_batch test_on_batch

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

get_layer

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

pop_layer

Remove the last layer in a model

save_model_hdf5 load_model_hdf5

serialize_model unserialize_model

Serialize a model to an R object

clone_model

Clone a model instance.

freeze_weights unfreeze_weights

Freeze and unfreeze weights

## Core Layers

layer_input

Input layer

layer_dense

Add a densely-connected NN layer to an output

layer_activation

Apply an activation function to an output.

layer_dropout

Applies Dropout to the input.

layer_reshape

Reshapes an output to a certain shape.

layer_permute

Permute the dimensions of an input according to a given pattern

layer_repeat_vector

Repeats the input n times.

layer_lambda

Wraps arbitrary expression as a layer

layer_activity_regularization

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

layer_masking

layer_flatten

Flattens an input

## Convolutional Layers

layer_conv_1d

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

layer_conv_2d_transpose

Transposed 2D convolution layer (sometimes called Deconvolution).

layer_conv_2d

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

layer_conv_3d_transpose

Transposed 3D convolution layer (sometimes called Deconvolution).

layer_conv_3d

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

layer_conv_lstm_2d

Convolutional LSTM.

layer_separable_conv_2d

Depthwise separable 2D convolution.

layer_upsampling_1d

Upsampling layer for 1D inputs.

layer_upsampling_2d

Upsampling layer for 2D inputs.

layer_upsampling_3d

Upsampling layer for 3D inputs.

layer_zero_padding_1d

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

layer_zero_padding_2d

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

layer_zero_padding_3d

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

layer_cropping_1d

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

layer_cropping_2d

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

layer_cropping_3d

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

## Pooling Layers

layer_max_pooling_1d

Max pooling operation for temporal data.

layer_max_pooling_2d

Max pooling operation for spatial data.

layer_max_pooling_3d

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

layer_average_pooling_1d

Average pooling for temporal data.

layer_average_pooling_2d

Average pooling operation for spatial data.

layer_average_pooling_3d

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

layer_global_max_pooling_1d

Global max pooling operation for temporal data.

layer_global_average_pooling_1d

Global average pooling operation for temporal data.

layer_global_max_pooling_2d

Global max pooling operation for spatial data.

layer_global_average_pooling_2d

Global average pooling operation for spatial data.

layer_global_max_pooling_3d

Global Max pooling operation for 3D data.

layer_global_average_pooling_3d

Global Average pooling operation for 3D data.

## Activation Layers

layer_activation

Apply an activation function to an output.

layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit.

layer_activation_parametric_relu

Parametric Rectified Linear Unit.

layer_activation_thresholded_relu

Thresholded Rectified Linear Unit.

layer_activation_elu

Exponential Linear Unit.

## Dropout Layers

layer_dropout

Applies Dropout to the input.

layer_spatial_dropout_1d

Spatial 1D version of Dropout.

layer_spatial_dropout_2d

Spatial 2D version of Dropout.

layer_spatial_dropout_3d

Spatial 3D version of Dropout.

## Locally-connected Layers

layer_locally_connected_1d

Locally-connected layer for 1D inputs.

layer_locally_connected_2d

Locally-connected layer for 2D inputs.

## Recurrent Layers

layer_simple_rnn

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

layer_gru

Gated Recurrent Unit - Cho et al.

layer_cudnn_gru

Fast GRU implementation backed by CuDNN.

layer_lstm

Long-Short Term Memory unit - Hochreiter 1997.

layer_cudnn_lstm

Fast LSTM implementation backed by CuDNN.

## Embedding Layers

layer_embedding

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

## Normalization Layers

layer_batch_normalization

Batch normalization layer (Ioffe and Szegedy, 2014).

## Noise Layers

layer_gaussian_noise

layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.

layer_alpha_dropout

Applies Alpha Dropout to the input.

## Merge Layers

layer_add

Layer that adds a list of inputs.

layer_subtract

Layer that subtracts two inputs.

layer_multiply

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

layer_average

Layer that averages a list of inputs.

layer_maximum

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

layer_minimum

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

layer_concatenate

Layer that concatenates a list of inputs.

layer_dot

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

## Layer Wrappers

time_distributed

Apply a layer to every temporal slice of an input.

bidirectional

Bidirectional wrapper for RNNs.

## Layer Methods

get_config from_config

Layer/Model configuration

get_weights set_weights

Layer/Model weights as R arrays

get_input_at get_output_at get_input_shape_at get_output_shape_at get_input_mask_at get_output_mask_at

Retrieve tensors for layers with multiple nodes

count_params

Count the total number of scalars composing the weights.

reset_states

Reset the states for a layer

## Custom Layers

KerasLayer

Base R6 class for Keras layers

create_layer

Create a Keras Layer

## Model Persistence

save_model_hdf5 load_model_hdf5

save_model_weights_hdf5 load_model_weights_hdf5

Save/Load model weights using HDF5 files

serialize_model unserialize_model

Serialize a model to an R object

get_weights set_weights

Layer/Model weights as R arrays

get_config from_config

Layer/Model configuration

model_to_json model_from_json

Model configuration as JSON

model_to_yaml model_from_yaml

Model configuration as YAML

## Datasets

dataset_cifar10

CIFAR10 small image classification

dataset_cifar100

CIFAR100 small image classification

dataset_imdb dataset_imdb_word_index

IMDB Movie reviews sentiment classification

dataset_reuters dataset_reuters_word_index

Reuters newswire topics classification

dataset_mnist

MNIST database of handwritten digits

dataset_fashion_mnist

Fashion-MNIST database of fashion articles

dataset_boston_housing

Boston housing price regression dataset

## Applications

application_xception xception_preprocess_input

Xception V1 model for Keras.

application_inception_v3 inception_v3_preprocess_input

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

application_inception_resnet_v2 inception_resnet_v2_preprocess_input

Inception-ResNet v2 model, with weights trained on ImageNet

application_vgg16 application_vgg19

VGG16 and VGG19 models for Keras.

application_resnet50

ResNet50 model for Keras.

application_mobilenet mobilenet_preprocess_input mobilenet_decode_predictions mobilenet_load_model_hdf5

MobileNet model architecture.

imagenet_preprocess_input

Preprocesses a tensor encoding a batch of images.

imagenet_decode_predictions

Decodes the prediction of an ImageNet model.

## Sequence Preprocessing

pad_sequences

Pads each sequence to the same length (length of the longest sequence).

skipgrams

Generates skipgram word pairs.

make_sampling_table

Generates a word rank-based probabilistic sampling table.

## Text Preprocessing

text_tokenizer

Text tokenization utility

fit_text_tokenizer

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

save_text_tokenizer load_text_tokenizer

Save a text tokenizer to an external file

texts_to_sequences

Transform each text in texts in a sequence of integers.

texts_to_sequences_generator

Transforms each text in texts in a sequence of integers.

texts_to_matrix

Convert a list of texts to a matrix.

sequences_to_matrix

Convert a list of sequences into a matrix.

text_one_hot

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

text_hashing_trick

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

text_to_word_sequence

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

## Image Preprocessing

image_load

Loads an image into PIL format.

image_to_array image_array_resize image_array_save

3D array representation of images

image_data_generator

Generate minibatches of image data with real-time data augmentation.

fit_image_data_generator

Fit image data generator internal statistics to some sample data.

flow_images_from_data

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

flow_images_from_directory

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

generator_next

Retrieve the next item from a generator

## Optimizers

optimizer_sgd

optimizer_rmsprop

RMSProp optimizer

optimizer_adagrad

optimizer_adadelta

optimizer_adam

optimizer_adamax

optimizer_nadam

## Callbacks

callback_progbar_logger

Callback that prints metrics to stdout.

callback_model_checkpoint

Save the model after every epoch.

callback_early_stopping

Stop training when a monitored quantity has stopped improving.

callback_remote_monitor

Callback used to stream events to a server.

callback_learning_rate_scheduler

Learning rate scheduler.

callback_tensorboard

TensorBoard basic visualizations

callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.

callback_terminate_on_naan

Callback that terminates training when a NaN loss is encountered.

callback_csv_logger

Callback that streams epoch results to a csv file

callback_lambda

Create a custom callback

KerasCallback

Base R6 class for Keras callbacks

## Initializers

initializer_zeros

Initializer that generates tensors initialized to 0.

initializer_ones

Initializer that generates tensors initialized to 1.

initializer_constant

Initializer that generates tensors initialized to a constant value.

initializer_random_normal

Initializer that generates tensors with a normal distribution.

initializer_random_uniform

Initializer that generates tensors with a uniform distribution.

initializer_truncated_normal

Initializer that generates a truncated normal distribution.

initializer_variance_scaling

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

initializer_orthogonal

Initializer that generates a random orthogonal matrix.

initializer_identity

Initializer that generates the identity matrix.

initializer_glorot_normal

Glorot normal initializer, also called Xavier normal initializer.

initializer_glorot_uniform

Glorot uniform initializer, also called Xavier uniform initializer.

initializer_he_normal

He normal initializer.

initializer_he_uniform

He uniform variance scaling initializer.

initializer_lecun_uniform

LeCun uniform initializer.

initializer_lecun_normal

LeCun normal initializer.

## Constraints

constraint_maxnorm

MaxNorm weight constraint

constraint_nonneg

NonNeg weight constraint

constraint_unitnorm

UnitNorm weight constraint

constraint_minmaxnorm

MinMaxNorm weight constraint

## Utils

plot

Plot training history

to_categorical

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

normalize

Normalize a matrix or nd-array

with_custom_object_scope

Provide a scope with mappings of names to custom objects

keras_array

Keras array object

hdf5_matrix

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

get_file

reexports

Objects exported from other packages

install_keras

Install Keras and the TensorFlow backend

is_keras_available

Check if Keras is Available

backend

Keras backend tensor engine

implementation

Keras implementation

use_implementation use_backend

Select a Keras implementation and backend

## Losses

loss_mean_squared_error loss_mean_absolute_error loss_mean_absolute_percentage_error loss_mean_squared_logarithmic_error loss_squared_hinge loss_hinge loss_categorical_hinge loss_logcosh loss_categorical_crossentropy loss_sparse_categorical_crossentropy loss_binary_crossentropy loss_kullback_leibler_divergence loss_poisson loss_cosine_proximity

Model loss functions

## Metrics

metric_binary_accuracy metric_binary_crossentropy metric_categorical_accuracy metric_categorical_crossentropy metric_cosine_proximity metric_hinge metric_kullback_leibler_divergence metric_mean_absolute_error metric_mean_absolute_percentage_error metric_mean_squared_error metric_mean_squared_logarithmic_error metric_poisson metric_sparse_categorical_crossentropy metric_squared_hinge metric_top_k_categorical_accuracy metric_sparse_top_k_categorical_accuracy

Model performance metrics

## Regularizers

regularizer_l1 regularizer_l2 regularizer_l1_l2

L1 and L2 regularization

## Activations

activation_relu activation_elu activation_selu activation_hard_sigmoid activation_linear activation_sigmoid activation_softmax activation_softplus activation_softsign activation_tanh

Activation functions

## Backend

k_abs

Element-wise absolute value.

k_all

Bitwise reduction (logical AND).

k_any

Bitwise reduction (logical OR).

k_arange

Creates a 1D tensor containing a sequence of integers.

k_argmax

Returns the index of the maximum value along an axis.

k_argmin

Returns the index of the minimum value along an axis.

k_backend

Active Keras backend

k_batch_dot

Batchwise dot product.

k_batch_flatten

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

k_batch_get_value

Returns the value of more than one tensor variable.

k_batch_normalization

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

k_batch_set_value

Sets the values of many tensor variables at once.

k_bias_add

Adds a bias vector to a tensor.

k_binary_crossentropy

Binary crossentropy between an output tensor and a target tensor.

k_cast_to_floatx

Cast an array to the default Keras float type.

k_cast

Casts a tensor to a different dtype and returns it.

k_categorical_crossentropy

Categorical crossentropy between an output tensor and a target tensor.

k_clear_session

Destroys the current TF graph and creates a new one.

k_clip

Element-wise value clipping.

k_concatenate

Concatenates a list of tensors alongside the specified axis.

k_constant

Creates a constant tensor.

k_conv1d

1D convolution.

k_conv2d_transpose

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

k_conv2d

2D convolution.

k_conv3d_transpose

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

k_conv3d

3D convolution.

k_cos

Computes cos of x element-wise.

k_count_params

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

k_ctc_batch_cost

Runs CTC loss algorithm on each batch element.

k_ctc_decode

Decodes the output of a softmax.

k_ctc_label_dense_to_sparse

Converts CTC labels from dense to sparse.

k_cumprod

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

k_cumsum

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

k_depthwise_conv2d

Depthwise 2D convolution with separable filters.

k_dot

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

k_dropout

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

k_dtype

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

k_elu

Exponential linear unit.

k_epsilon k_set_epsilon

Fuzz factor used in numeric expressions.

k_equal

Element-wise equality between two tensors.

k_eval

Evaluates the value of a variable.

k_exp

Element-wise exponential.

k_expand_dims

Adds a 1-sized dimension at index axis.

k_eye

Instantiate an identity matrix and returns it.

k_flatten

Flatten a tensor.

k_floatx k_set_floatx

Default float type

k_foldl

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

k_foldr

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

k_function

Instantiates a Keras function

k_gather

Retrieves the elements of indices indices in the tensor reference.

k_get_session k_set_session

TF session to be used by the backend.

k_get_uid

Get the uid for the default graph.

k_get_value

Returns the value of a variable.

k_get_variable_shape

Returns the shape of a variable.

k_gradients

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

k_greater_equal

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

k_greater

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

k_hard_sigmoid

Segment-wise linear approximation of sigmoid.

k_identity

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

k_image_data_format k_set_image_data_format

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

k_in_test_phase

Selects x in test phase, and alt otherwise.

k_in_top_k

Returns whether the targets are in the top k predictions.

k_in_train_phase

Selects x in train phase, and alt otherwise.

k_int_shape

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

k_is_keras_tensor

Returns whether x is a Keras tensor.

k_is_placeholder

Returns whether x is a placeholder.

k_is_sparse

Returns whether a tensor is a sparse tensor.

k_l2_normalize

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

k_learning_phase

Returns the learning phase flag.

k_less_equal

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

k_less

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

k_local_conv1d

Apply 1D conv with un-shared weights.

k_local_conv2d

Apply 2D conv with un-shared weights.

k_log

Element-wise log.

k_logsumexp

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

k_manual_variable_initialization

Sets the manual variable initialization flag.

k_map_fn

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

k_max

Maximum value in a tensor.

k_maximum

Element-wise maximum of two tensors.

k_mean

Mean of a tensor, alongside the specified axis.

k_min

Minimum value in a tensor.

k_minimum

Element-wise minimum of two tensors.

k_moving_average_update

Compute the moving average of a variable.

k_ndim

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

k_normalize_batch_in_training

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

k_not_equal

Element-wise inequality between two tensors.

k_one_hot

Computes the one-hot representation of an integer tensor.

k_ones_like

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

k_ones

Instantiates an all-ones tensor variable and returns it.

k_permute_dimensions

Permutes axes in a tensor.

k_placeholder

Instantiates a placeholder tensor and returns it.

k_pool2d

2D Pooling.

k_pool3d

3D Pooling.

k_pow

Element-wise exponentiation.

k_print_tensor

Prints message and the tensor value when evaluated.

k_prod

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

k_random_binomial

Returns a tensor with random binomial distribution of values.

k_random_normal_variable

Instantiates a variable with values drawn from a normal distribution.

k_random_normal

Returns a tensor with normal distribution of values.

k_random_uniform_variable

Instantiates a variable with values drawn from a uniform distribution.

k_random_uniform

Returns a tensor with uniform distribution of values.

k_relu

Rectified linear unit.

k_repeat_elements

Repeats the elements of a tensor along an axis.

k_repeat

Repeats a 2D tensor.

k_reset_uids

Reset graph identifiers.

k_reshape

Reshapes a tensor to the specified shape.

k_resize_images

Resizes the images contained in a 4D tensor.

k_resize_volumes

Resizes the volume contained in a 5D tensor.

k_reverse

Reverse a tensor along the specified axes.

k_rnn

Iterates over the time dimension of a tensor

k_round

Element-wise rounding to the closest integer.

k_separable_conv2d

2D convolution with separable filters.

k_set_learning_phase

Sets the learning phase to a fixed value.

k_set_value

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

k_shape

Returns the symbolic shape of a tensor or variable.

k_sigmoid

Element-wise sigmoid.

k_sign

Element-wise sign.

k_sin

Computes sin of x element-wise.

k_softmax

Softmax of a tensor.

k_softplus

Softplus of a tensor.

k_softsign

Softsign of a tensor.

k_sparse_categorical_crossentropy

Categorical crossentropy with integer targets.

k_spatial_2d_padding

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

k_spatial_3d_padding

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

k_sqrt

Element-wise square root.

k_square

Element-wise square.

k_squeeze

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

k_stack

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

k_std

Standard deviation of a tensor, alongside the specified axis.

k_stop_gradient

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

k_sum

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

k_switch

Switches between two operations depending on a scalar value.

k_tanh

Element-wise tanh.

k_temporal_padding

Pads the middle dimension of a 3D tensor.

k_tile

Creates a tensor by tiling x by n.

k_to_dense

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

k_transpose

Transposes a tensor and returns it.

k_truncated_normal

Returns a tensor with truncated random normal distribution of values.

k_update_add

Update the value of x by adding increment.

k_update_sub

Update the value of x by subtracting decrement.

k_update

Update the value of x to new_x.

k_var

Variance of a tensor, alongside the specified axis.

k_variable

Instantiates a variable and returns it.

k_zeros_like

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

k_zeros

Instantiates an all-zeros variable and returns it.