Learn R Programming

keras (version 2.16.0)

R Interface to 'Keras'

Description

Interface to 'Keras' , a high-level neural networks 'API'. 'Keras' was developed with a focus on enabling fast experimentation, supports both convolution based networks and recurrent networks (as well as combinations of the two), and runs seamlessly on both 'CPU' and 'GPU' devices.

Copy Link

Version

Install

install.packages('keras')

Version

2.16.0

License

MIT + file LICENSE

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/rstudio/keras3/tree/r2

Homepage

https://tensorflow.rstudio.com/

Maintainer

Tomasz Kalinowski

Last Published

August 18th, 2025

Functions in keras (2.16.0)

(Deprecated) Base R6 class for Keras callbacks

activation_relu

Activation functions

application_densenet

Instantiates the DenseNet architecture.

application_efficientnet

Instantiates the EfficientNetB0 architecture

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

(Deprecated) Create a custom Layer

(Deprecated) Base R6 class for Keras wrappers

(Deprecated) Base R6 class for Keras layers

KerasConstraint

(Deprecated) Base R6 class for Keras constraints

application_mobilenet

MobileNet model architecture.

application_vgg

VGG16 and VGG19 models for Keras.

application_xception

Instantiates the Xception architecture

application_inception_resnet_v2

Inception-ResNet v2 model, with weights trained on ImageNet

application_nasnet

Instantiates a NASNet model.

application_mobilenet_v2

MobileNetV2 model architecture

application_resnet

Instantiates the ResNet architecture

application_inception_v3

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

application_mobilenet_v3

Instantiates the MobileNetV3Large architecture

Keras backend tensor engine

callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.

callback_model_checkpoint

Save the model after every epoch.

callback_progbar_logger

Callback that prints metrics to stdout.

callback_learning_rate_scheduler

Learning rate scheduler.

callback_backup_and_restore

Callback to back up and restore the training state

callback_lambda

Create a custom callback

Bidirectional wrapper for RNNs

callback_early_stopping

Stop training when a monitored quantity has stopped improving.

callback_remote_monitor

Callback used to stream events to a server.

callback_csv_logger

Callback that streams epoch results to a csv file

Create a Keras Layer

callback_tensorboard

TensorBoard basic visualizations

Clone a model instance.

Custom metric function

Count the total number of scalars composing the weights.

create_layer_wrapper

Create a Keras Layer wrapper

Weight constraints

callback_terminate_on_naan

Callback that terminates training when a NaN loss is encountered.

compile.keras.engine.training.Model

Configure a Keras model for training

(Deprecated) Create a Keras Wrapper

dataset_cifar100

CIFAR100 small image classification

dataset_boston_housing

Boston housing price regression dataset

dataset_reuters

Reuters newswire topics classification

dataset_cifar10

CIFAR10 small image classification

dataset_fashion_mnist

Fashion-MNIST database of fashion articles

export_savedmodel.keras.engine.training.Model

Export a Saved Model

MNIST database of handwritten digits

evaluate_generator

(Deprecated) Evaluates the model on a data generator.

IMDB Movie reviews sentiment classification

evaluate.keras.engine.training.Model

Evaluate a Keras model

fit_image_data_generator

Fit image data generator internal statistics to some sample data.

Retrieve the next item from a generator

flow_images_from_directory

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

fit.keras.engine.training.Model

Train a Keras model

fit_text_tokenizer

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

Layer/Model configuration

Freeze and unfreeze weights

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

flow_images_from_dataframe

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

flow_images_from_data

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

image_dataset_from_directory

Create a dataset from a directory

image_data_generator

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

Layer/Model weights as R arrays

Retrieve tensors for layers with multiple nodes

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

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

Make a python class constructor

Make an Active Binding

Loads an image into PIL format.

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

initializer_glorot_normal

Glorot normal initializer, also called Xavier normal initializer.

imagenet_preprocess_input

Preprocesses a tensor or array encoding a batch of images.

imagenet_decode_predictions

Decodes the prediction of an ImageNet model.

initializer_constant

Initializer that generates tensors initialized to a constant value.

3D array representation of images

initializer_identity

Initializer that generates the identity matrix.

initializer_glorot_uniform

Glorot uniform initializer, also called Xavier uniform initializer.

initializer_he_normal

He normal initializer.

Keras implementation

initializer_he_uniform

He uniform variance scaling initializer.

initializer_variance_scaling

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

initializer_zeros

Initializer that generates tensors initialized to 0.

initializer_random_uniform

Initializer that generates tensors with a uniform distribution.

initializer_truncated_normal

Initializer that generates a truncated normal distribution.

initializer_lecun_uniform

LeCun uniform initializer.

initializer_random_normal

Initializer that generates tensors with a normal distribution.

initializer_ones

Initializer that generates tensors initialized to 1.

initializer_orthogonal

Initializer that generates a random orthogonal matrix.

Install TensorFlow and Legacy Keras, including all Python dependencies

initializer_lecun_normal

LeCun normal initializer.

Bitwise reduction (logical AND).

is_keras_available

Check if Keras is Available

Bitwise reduction (logical OR).

Creates a 1D tensor containing a sequence of integers.

Returns the index of the maximum value along an axis.

Batchwise dot product.

Element-wise absolute value.

k_batch_flatten

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

Active Keras backend

Returns the index of the minimum value along an axis.

k_cast_to_floatx

Cast an array to the default Keras float type.

k_categorical_crossentropy

Categorical crossentropy between an output tensor and a target tensor.

k_binary_crossentropy

Binary crossentropy between an output tensor and a target tensor.

Casts a tensor to a different dtype and returns it.

k_batch_set_value

Sets the values of many tensor variables at once.

Adds a bias vector to a tensor.

Element-wise value clipping.

k_clear_session

Destroys the current TF graph and creates a new one.

1D convolution.

k_conv2d_transpose

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

Concatenates a list of tensors alongside the specified axis.

k_batch_normalization

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

k_batch_get_value

Returns the value of more than one tensor variable.

Creates a constant tensor.

k_ctc_batch_cost

Runs CTC loss algorithm on each batch element.

3D convolution.

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

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

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

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

k_depthwise_conv2d

Depthwise 2D convolution with separable filters.

Computes cos of x element-wise.

k_conv3d_transpose

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

Exponential linear unit.

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

Decodes the output of a softmax.

k_ctc_label_dense_to_sparse

Converts CTC labels from dense to sparse.

2D convolution.

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

Fuzz factor used in numeric expressions.

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

Instantiate an identity matrix and returns it.

Instantiates a Keras function

Evaluates the value of a variable.

Adds a 1-sized dimension at index axis.

Element-wise exponential.

Element-wise equality between two tensors.

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

Flatten a tensor.

Default float type

k_get_variable_shape

Returns the shape of a variable.

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

Segment-wise linear approximation of sigmoid.

Retrieves the elements of indices indices in the tensor reference.

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

k_greater_equal

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

Get the uid for the default graph.

TF session to be used by the backend.

Returns the value of a variable.

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

k_image_data_format

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

k_is_placeholder

Returns whether x is a placeholder.

k_in_train_phase

Selects x in train phase, and alt otherwise.

Returns whether the targets are in the top k predictions.

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.

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

Returns whether a tensor is a sparse tensor.

Returns whether x is a symbolic tensor.

k_in_test_phase

Selects x in test phase, and alt otherwise.

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

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

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

Apply 2D conv with un-shared weights.

k_learning_phase

Returns the learning phase flag.

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

Element-wise log.

Apply 1D conv with un-shared weights.

k_manual_variable_initialization

Sets the manual variable initialization flag.

Element-wise maximum of two tensors.

Maximum value in a tensor.

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

k_moving_average_update

Compute the moving average of a variable.

k_normalize_batch_in_training

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

Element-wise inequality between two tensors.

Element-wise minimum of two tensors.

Minimum value in a tensor.

Computes the one-hot representation of an integer tensor.

Instantiates an all-ones tensor variable and returns it.

Mean of a tensor, alongside the specified axis.

Element-wise exponentiation.

Instantiates a placeholder tensor and returns it.

Prints message and the tensor value when evaluated.

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

k_permute_dimensions

Permutes axes in a tensor.

k_random_binomial

Returns a tensor with random binomial distribution of values.

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

k_random_normal

Returns a tensor with normal distribution of values.

Reshapes a tensor to the specified shape.

k_resize_images

Resizes the images contained in a 4D tensor.

k_repeat_elements

Repeats the elements of a tensor along an axis.

k_random_normal_variable

Instantiates a variable with values drawn from a normal distribution.

Reset graph identifiers.

k_random_uniform_variable

Instantiates a variable with values drawn from a uniform distribution.

Rectified linear unit.

Repeats a 2D tensor.

k_resize_volumes

Resizes the volume contained in a 5D tensor.

k_random_uniform

Returns a tensor with uniform distribution of values.

Returns the symbolic shape of a tensor or variable.

Element-wise sign.

k_set_learning_phase

Sets the learning phase to a fixed value.

k_separable_conv2d

2D convolution with separable filters.

Element-wise rounding to the closest integer.

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

Element-wise sigmoid.

Computes sin of x element-wise.

Reverse a tensor along the specified axes.

Iterates over the time dimension of a tensor

Softplus of a tensor.

Element-wise square root.

Softmax of a tensor.

k_spatial_2d_padding

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

k_sparse_categorical_crossentropy

Categorical crossentropy with integer targets.

k_spatial_3d_padding

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

Element-wise square.

Softsign of a tensor.

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

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

k_stop_gradient

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

Standard deviation of a tensor, alongside the specified axis.

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

Creates a tensor by tiling x by n.

Transposes a tensor and returns it.

k_truncated_normal

Returns a tensor with truncated random normal distribution of values.

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

Switches between two operations depending on a scalar value.

k_temporal_padding

Pads the middle dimension of a 3D tensor.

Element-wise tanh.

R interface to Keras

Unstack rank R tensor into a list of rank R-1 tensors.

Variance of a tensor, alongside the specified axis.

Main Keras module

Update the value of x by subtracting decrement.

Update the value of x to new_x.

Instantiates a variable and returns it.

Instantiates an all-zeros variable and returns it.

Update the value of x by adding increment.

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

layer_activation

Apply an activation function to an output.

layer_activation_selu

Scaled Exponential Linear Unit.

keras_model_sequential

Keras Model composed of a linear stack of layers

layer_activation_parametric_relu

Parametric Rectified Linear Unit.

layer_activation_elu

Exponential Linear Unit.

layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit.

Keras array object

keras_model_custom

(Deprecated) Create a Keras custom model

layer_activation_relu

Rectified Linear Unit activation function

layer_attention

Dot-product attention layer, a.k.a. Luong-style attention

layer_additive_attention

Additive attention layer, a.k.a. Bahdanau-style attention

layer_activity_regularization

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

Layer that averages a list of inputs.

layer_average_pooling_1d

Average pooling for temporal data.

layer_activation_thresholded_relu

Thresholded Rectified Linear Unit.

Layer that adds a list of inputs.

layer_average_pooling_2d

Average pooling operation for spatial data.

layer_alpha_dropout

Applies Alpha Dropout to the input.

layer_activation_softmax

Softmax activation function.

layer_average_pooling_3d

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

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

layer_center_crop

Crop the central portion of the images to target height and width

layer_conv_2d_transpose

Transposed 2D convolution layer (sometimes called Deconvolution).

layer_category_encoding

A preprocessing layer which encodes integer features.

layer_concatenate

Layer that concatenates a list of inputs.

layer_conv_1d_transpose

Transposed 1D convolution layer (sometimes called Deconvolution).

layer_batch_normalization

Layer that normalizes its inputs

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

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

layer_conv_lstm_1d

1D Convolutional LSTM

layer_cropping_2d

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

layer_cropping_1d

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

layer_conv_lstm_3d

3D Convolutional LSTM

layer_cropping_3d

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

layer_conv_lstm_2d

Convolutional LSTM.

layer_cudnn_gru

(Deprecated) Fast GRU implementation backed by CuDNN.

layer_conv_3d_transpose

Transposed 3D convolution layer (sometimes called Deconvolution).

Add a densely-connected NN layer to an output

layer_cudnn_lstm

(Deprecated) Fast LSTM implementation backed by CuDNN.

Applies Dropout to the input.

layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.

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

layer_embedding

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

layer_depthwise_conv_1d

Depthwise 1D convolution

layer_dense_features

Constructs a DenseFeatures.

layer_discretization

A preprocessing layer which buckets continuous features by ranges.

layer_depthwise_conv_2d

Depthwise separable 2D convolution.

layer_gaussian_noise

Apply additive zero-centered Gaussian noise.

Flattens an input

layer_global_average_pooling_1d

Global average pooling operation for temporal data.

layer_global_max_pooling_1d

Global max pooling operation for temporal data.

layer_global_max_pooling_3d

Global Max pooling operation for 3D data.

A preprocessing layer which hashes and bins categorical features.

layer_global_max_pooling_2d

Global max pooling operation for spatial data.

Gated Recurrent Unit - Cho et al.

layer_global_average_pooling_3d

Global Average pooling operation for 3D data.

Cell class for the GRU layer

layer_global_average_pooling_2d

Global average pooling operation for spatial data.

layer_locally_connected_2d

Locally-connected layer for 2D inputs.

layer_lstm_cell

Cell class for the LSTM layer

Wraps arbitrary expression as a layer

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

layer_integer_lookup

A preprocessing layer which maps integer features to contiguous ranges.

layer_max_pooling_2d

Max pooling operation for spatial data.

layer_locally_connected_1d

Locally-connected layer for 1D inputs.

layer_max_pooling_1d

Max pooling operation for temporal data.

Long Short-Term Memory unit - Hochreiter 1997.

layer_layer_normalization

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

Permute the dimensions of an input according to a given pattern

layer_random_brightness

A preprocessing layer which randomly adjusts brightness during training

layer_max_pooling_3d

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

layer_random_contrast

Adjust the contrast of an image or images by a random factor

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

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

layer_normalization

A preprocessing layer which normalizes continuous features.

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

layer_multi_head_attention

MultiHeadAttention layer

layer_random_crop

Randomly crop the images to target height and width

layer_repeat_vector

Repeats the input n times.

Reshapes an output to a certain shape.

layer_random_rotation

Randomly rotate each image

layer_random_translation

Randomly translate each image during training

layer_random_height

Randomly vary the height of a batch of images during training

layer_random_zoom

A preprocessing layer which randomly zooms images during training.

layer_random_width

Randomly vary the width of a batch of images during training

Image resizing layer

layer_rescaling

Multiply inputs by scale and adds offset

layer_random_flip

Randomly flip each image horizontally and vertically

layer_separable_conv_2d

Separable 2D convolution.

layer_stacked_rnn_cells

Wrapper allowing a stack of RNN cells to behave as a single cell

layer_simple_rnn

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

layer_string_lookup

A preprocessing layer which maps string features to integer indices.

Base class for recurrent layers

layer_spatial_dropout_1d

Spatial 1D version of Dropout.

layer_separable_conv_1d

Depthwise separable 1D convolution.

layer_spatial_dropout_3d

Spatial 3D version of Dropout.

layer_simple_rnn_cell

Cell class for SimpleRNN

layer_spatial_dropout_2d

Spatial 2D version of Dropout.

Layer that subtracts two inputs.

layer_zero_padding_1d

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

layer_zero_padding_3d

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

layer_upsampling_2d

Upsampling layer for 2D inputs.

layer_unit_normalization

Unit normalization layer

learning_rate_schedule_cosine_decay

A LearningRateSchedule that uses a cosine decay schedule

layer_text_vectorization

A preprocessing layer which maps text features to integer sequences.

layer_upsampling_3d

Upsampling layer for 3D inputs.

layer_upsampling_1d

Upsampling layer for 1D inputs.

layer_zero_padding_2d

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

learning_rate_schedule_cosine_decay_restarts

A LearningRateSchedule that uses a cosine decay schedule with restarts

learning_rate_schedule_piecewise_constant_decay

A LearningRateSchedule that uses a piecewise constant decay schedule

learning_rate_schedule_exponential_decay

A LearningRateSchedule that uses an exponential decay schedule

learning_rate_schedule_inverse_time_decay

A LearningRateSchedule that uses an inverse time decay schedule

make_sampling_table

Generates a word rank-based probabilistic sampling table.

metric-or-Metric

metric-or-Metric

learning_rate_schedule_polynomial_decay

A LearningRateSchedule that uses a polynomial decay schedule

metric_accuracy

Calculates how often predictions equal labels

loss_cosine_proximity

(Deprecated) loss_cosine_proximity

metric_cosine_similarity

Computes the cosine similarity between the labels and predictions

metric_binary_accuracy

Calculates how often predictions match binary labels

metric_false_negatives

Calculates the number of false negatives

Approximates the AUC (Area under the curve) of the ROC or PR curves

metric_categorical_accuracy

Calculates how often predictions match one-hot labels

metric_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions

metric_binary_crossentropy

Computes the crossentropy metric between the labels and predictions

metric_cosine_proximity

(Deprecated) metric_cosine_proximity

metric_categorical_hinge

Computes the categorical hinge metric between y_true and y_pred

metric_false_positives

Calculates the number of false positives

metric_mean_absolute_percentage_error

Computes the mean absolute percentage error between y_true and y_pred

metric_mean_squared_error

Computes the mean squared error between labels and predictions

metric_kullback_leibler_divergence

Computes Kullback-Leibler divergence

metric_logcosh_error

Computes the logarithm of the hyperbolic cosine of the prediction error

metric_mean_absolute_error

Computes the mean absolute error between the labels and predictions

Computes the hinge metric between y_true and y_pred

metric_mean_relative_error

Computes the mean relative error by normalizing with the given values

metric_mean_squared_logarithmic_error

Computes the mean squared logarithmic error

Computes the (weighted) mean of the given values

metric_mean_iou

Computes the mean Intersection-Over-Union metric

metric_sparse_categorical_accuracy

Calculates how often predictions match integer labels

Computes the Poisson metric between y_true and y_pred

metric_recall_at_precision

Computes best recall where precision is >= specified value

Computes the recall of the predictions with respect to the labels

metric_precision

Computes the precision of the predictions with respect to the labels

metric_root_mean_squared_error

Computes root mean squared error metric between y_true and y_pred

metric_mean_wrapper

Wraps a stateless metric function with the Mean metric

metric_precision_at_recall

Computes best precision where recall is >= specified value

metric_sensitivity_at_specificity

Computes best sensitivity where specificity is >= specified value

metric_mean_tensor

Computes the element-wise (weighted) mean of the given tensors

metric_specificity_at_sensitivity

Computes best specificity where sensitivity is >= specified value

metric_true_positives

Calculates the number of true positives

model_from_saved_model

Load a Keras model from the Saved Model format

metric_sparse_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions

metric_true_negatives

Calculates the number of true negatives

metric_sparse_top_k_categorical_accuracy

Computes how often integer targets are in the top K predictions

Model configuration as JSON

Computes the (weighted) sum of the given values

metric_squared_hinge

Computes the squared hinge metric

metric_top_k_categorical_accuracy

Computes how often targets are in the top K predictions

optimizer_adagrad

Optimizer that implements the Adagrad algorithm

Normalize a matrix or nd-array

model_to_saved_model

(Deprecated) Export to Saved Model format

Optimizer that implements the Adam algorithm

new_metric_class

Define new keras types

Model configuration as YAML

optimizer_adadelta

Optimizer that implements the Adadelta algorithm

new_learning_rate_schedule_class

Create a new learning rate schedule type

Assign values to names

multi_gpu_model

(Deprecated) Replicates a model on different GPUs.

Gradient descent (with momentum) optimizer

plot.keras_training_history

Plot training history

Pads sequences to the same length

optimizer_nadam

Optimizer that implements the Nadam algorithm

optimizer_adamax

Optimizer that implements the Adamax algorithm

Remove the last layer in a model

plot.keras.engine.training.Model

Plot a Keras model

optimizer_rmsprop

Optimizer that implements the RMSprop algorithm

Optimizer that implements the FTRL algorithm

Save/Load models using SavedModel format

regularizer_orthogonal

A regularizer that encourages input vectors to be orthogonal to each other

predict_on_batch

Returns predictions for a single batch of samples.

Objects exported from other packages

predict.keras.engine.training.Model

Generate predictions from a Keras model

L1 and L2 regularization

save_model_hdf5

Save/Load models using HDF5 files

Reset the states for a layer

predict_generator

(Deprecated) Generates predictions for the input samples from a data generator.

(Deprecated) Generates probability or class probability predictions for the input samples.

Generates skipgram word pairs.

sequences_to_matrix

Convert a list of sequences into a matrix.

save_model_weights_tf

Save model weights in the SavedModel format

sequential_model_input_layer

sequential_model_input_layer

save_text_tokenizer

Save a text tokenizer to an external file

text_dataset_from_directory

Generate a tf.data.Dataset from text files in a directory

serialize_model

Serialize a model to an R object

save_model_weights_hdf5

Save/Load model weights using HDF5 files

summary.keras.engine.training.Model

Print a summary of a Keras model

text_hashing_trick

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

texts_to_sequences

Transform each text in texts in a sequence of integers.

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

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

texts_to_sequences_generator

Transforms each text in texts in a sequence of integers.

timeseries_generator

Utility function for generating batches of temporal data.

text_to_word_sequence

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

timeseries_dataset_from_array

Creates a dataset of sliding windows over a timeseries provided as array

time_distributed

This layer wrapper allows to apply a layer to every temporal slice of an input

texts_to_matrix

Convert a list of texts to a matrix.

Text tokenization utility

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

with_custom_object_scope

Provide a scope with mappings of names to custom objects

use_implementation

Select a Keras implementation and backend