Learn R Programming

keras (version 2.13.0)

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

2.13.0

License

MIT + file LICENSE

Last Published

August 15th, 2023

Functions in keras (2.13.0)

application_efficientnet

Instantiates the EfficientNetB0 architecture
Layer

(Deprecated) Create a custom Layer
adapt

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

Metric
application_densenet

Instantiates the DenseNet architecture.
activation_relu

Activation functions
KerasLayer

(Deprecated) Base R6 class for Keras layers
KerasCallback

(Deprecated) Base R6 class for Keras callbacks
KerasConstraint

(Deprecated) Base R6 class for Keras constraints
KerasWrapper

(Deprecated) Base R6 class for Keras wrappers
application_inception_resnet_v2

Inception-ResNet v2 model, with weights trained on ImageNet
application_resnet

Instantiates the ResNet architecture
application_inception_v3

Inception V3 model, with weights pre-trained on ImageNet.
application_mobilenet_v2

MobileNetV2 model architecture
application_xception

Instantiates the Xception architecture
backend

Keras backend tensor engine
application_mobilenet

MobileNet model architecture.
application_mobilenet_v3

Instantiates the MobileNetV3Large architecture
application_vgg

VGG16 and VGG19 models for Keras.
application_nasnet

Instantiates a NASNet model.
callback_model_checkpoint

Save the model after every epoch.
bidirectional

Bidirectional wrapper for RNNs
callback_backup_and_restore

Callback to back up and restore the training state
callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.
callback_early_stopping

Stop training when a monitored quantity has stopped improving.
callback_lambda

Create a custom callback
callback_csv_logger

Callback that streams epoch results to a csv file
callback_progbar_logger

Callback that prints metrics to stdout.
callback_remote_monitor

Callback used to stream events to a server.
callback_learning_rate_scheduler

Learning rate scheduler.
callback_tensorboard

TensorBoard basic visualizations
constraints

Weight constraints
callback_terminate_on_naan

Callback that terminates training when a NaN loss is encountered.
count_params

Count the total number of scalars composing the weights.
compile.keras.engine.training.Model

Configure a Keras model for training
clone_model

Clone a model instance.
create_layer_wrapper

Create a Keras Layer wrapper
create_layer

Create a Keras Layer
dataset_mnist

MNIST database of handwritten digits
dataset_imdb

IMDB Movie reviews sentiment classification
dataset_reuters

Reuters newswire topics classification
evaluate.keras.engine.training.Model

Evaluate a Keras model
custom_metric

Custom metric function
dataset_cifar100

CIFAR100 small image classification
create_wrapper

(Deprecated) Create a Keras Wrapper
dataset_fashion_mnist

Fashion-MNIST database of fashion articles
dataset_cifar10

CIFAR10 small image classification
dataset_boston_housing

Boston housing price regression dataset
export_savedmodel.keras.engine.training.Model

Export a Saved Model
evaluate_generator

(Deprecated) Evaluates the model on a data generator.
fit_text_tokenizer

Update tokenizer internal vocabulary based on a list of texts or list of sequences.
fit.keras.engine.training.Model

Train a Keras model
flow_images_from_data

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

Fit image data generator internal statistics to some sample data.
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
flow_images_from_dataframe

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

Freeze and unfreeze weights
fit_generator

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

Layer/Model configuration
hdf5_matrix

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

Retrieve tensors for layers with multiple nodes
get_file

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

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

Layer/Model weights as R arrays
get_layer

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

Make a python class constructor
%<-active%

Make an Active Binding
image_load

Loads an image into PIL format.
image_dataset_from_directory

Create a dataset from a directory
initializer_glorot_uniform

Glorot uniform initializer, also called Xavier uniform initializer.
initializer_constant

Initializer that generates tensors initialized to a constant value.
implementation

Keras implementation
imagenet_decode_predictions

Decodes the prediction of an ImageNet model.
initializer_identity

Initializer that generates the identity matrix.
initializer_he_uniform

He uniform variance scaling initializer.
imagenet_preprocess_input

Preprocesses a tensor or array encoding a batch of images.
image_to_array

3D array representation of images
initializer_glorot_normal

Glorot normal initializer, also called Xavier normal initializer.
initializer_he_normal

He normal initializer.
initializer_lecun_normal

LeCun normal initializer.
initializer_lecun_uniform

LeCun uniform initializer.
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_random_normal

Initializer that generates tensors with a normal distribution.
initializer_zeros

Initializer that generates tensors initialized to 0.
install_keras

Install TensorFlow and Keras, including all Python dependencies
initializer_random_uniform

Initializer that generates tensors with a uniform distribution.
k_argmax

Returns the index of the maximum value along an axis.
k_arange

Creates a 1D tensor containing a sequence of integers.
k_batch_dot

Batchwise dot product.
k_batch_flatten

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

Active Keras backend
k_bias_add

Adds a bias vector to a tensor.
k_batch_set_value

Sets the values of many tensor variables at once.
k_argmin

Returns the index of the minimum value along an axis.
k_batch_normalization

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

Casts a tensor to a different dtype and returns it.
k_binary_crossentropy

Binary crossentropy between an output tensor and a target tensor.
k_batch_get_value

Returns the value of more than one tensor variable.
k_all

Bitwise reduction (logical AND).
k_any

Bitwise reduction (logical OR).
k_abs

Element-wise absolute value.
is_keras_available

Check if Keras is Available
k_clip

Element-wise value clipping.
k_clear_session

Destroys the current TF graph and creates a new one.
initializer_ones

Initializer that generates tensors initialized to 1.
initializer_orthogonal

Initializer that generates a random orthogonal matrix.
k_conv2d

2D convolution.
k_conv1d

1D convolution.
k_conv2d_transpose

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

Runs CTC loss algorithm on each batch element.
k_count_params

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

Concatenates a list of tensors alongside the specified axis.
k_conv3d_transpose

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

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

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

Computes cos of x element-wise.
k_ctc_label_dense_to_sparse

Converts CTC labels from dense to sparse.
k_ctc_decode

Decodes the output of a softmax.
k_epsilon

Fuzz factor used in numeric expressions.
k_elu

Exponential linear unit.
k_exp

Element-wise exponential.
k_conv3d

3D convolution.
k_depthwise_conv2d

Depthwise 2D convolution with separable filters.
k_expand_dims

Adds a 1-sized dimension at index axis.
k_get_value

Returns the value of a variable.
k_get_uid

Get the uid for the default graph.
k_eye

Instantiate an identity matrix and returns it.
k_function

Instantiates a Keras function
k_foldr

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

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

Creates a constant tensor.
k_is_tensor

Returns whether x is a symbolic tensor.
k_identity

Returns a tensor with the same content as the input tensor.
k_l2_normalize

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

Segment-wise linear approximation of sigmoid.
k_flatten

Flatten a tensor.
k_is_placeholder

Returns whether x is a placeholder.
k_is_sparse

Returns whether a tensor is a sparse tensor.
k_gradients

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

Returns the shape of a variable.
k_less

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

Returns the learning phase flag.
k_dtype

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

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

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

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

TF session to be used by the backend.
k_in_test_phase

Selects x in test phase, and alt otherwise.
k_gather

Retrieves the elements of indices indices in the tensor reference.
k_floatx

Default float type
k_eval

Evaluates the value of a variable.
k_equal

Element-wise equality between two tensors.
k_int_shape

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

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

Returns whether x is a Keras tensor.
k_greater

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

Maximum value in a tensor.
k_maximum

Element-wise maximum of two tensors.
k_map_fn

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

Selects x in train phase, and alt otherwise.
k_pool3d

3D Pooling.
k_greater_equal

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

Returns whether the targets are in the top k predictions.
k_ndim

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

Compute the moving average of a variable.
k_mean

Mean of a tensor, alongside the specified axis.
k_local_conv2d

Apply 2D conv with un-shared weights.
k_log

Element-wise log.
k_random_normal_variable

Instantiates a variable with values drawn from a normal distribution.
k_pow

Element-wise exponentiation.
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_random_uniform_variable

Instantiates a variable with values drawn from a uniform distribution.
k_relu

Rectified linear unit.
k_manual_variable_initialization

Sets the manual variable initialization flag.
k_logsumexp

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

Element-wise inequality between two tensors.
k_normalize_batch_in_training

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

Returns a tensor with random binomial distribution of values.
k_shape

Returns the symbolic shape of a tensor or variable.
k_random_uniform

Returns a tensor with uniform distribution of values.
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_print_tensor

Prints message and the tensor value when evaluated.
k_one_hot

Computes the one-hot representation of an integer tensor.
k_squeeze

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

Multiplies the values in a tensor, alongside the specified axis.
k_local_conv1d

Apply 1D conv with un-shared weights.
k_round

Element-wise rounding to the closest integer.
k_random_normal

Returns a tensor with normal distribution of values.
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.
k_permute_dimensions

Permutes axes in a tensor.
k_resize_images

Resizes the images contained in a 4D tensor.
layer_activation_parametric_relu

Parametric Rectified Linear Unit.
k_resize_volumes

Resizes the volume contained in a 5D tensor.
k_sigmoid

Element-wise sigmoid.
keras_model

Keras Model
keras_array

Keras array object
k_softmax

Softmax of a tensor.
k_softplus

Softplus of a 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.
layer_additive_attention

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

Applies Alpha Dropout to the input.
k_separable_conv2d

2D convolution with separable filters.
k_min

Minimum value in a tensor.
k_reset_uids

Reset graph identifiers.
keras_model_sequential

Keras Model composed of a linear stack of layers
keras-package

R interface to Keras
k_sin

Computes sin of x element-wise.
k_sign

Element-wise sign.
k_reshape

Reshapes a tensor to the specified shape.
layer_attention

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

Main Keras module
k_std

Standard deviation of a tensor, alongside the specified axis.
k_stack

Stacks a list of rank R tensors into a rank R+1 tensor.
layer_conv_1d_transpose

Transposed 1D convolution layer (sometimes called Deconvolution).
k_minimum

Element-wise minimum of two tensors.
layer_conv_2d

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

Iterates over the time dimension of a tensor
keras_model_custom

(Deprecated) Create a Keras custom model
k_var

Variance of a tensor, alongside the specified axis.
k_sqrt

Element-wise square root.
k_sum

Sum of the values in a tensor, alongside the specified axis.
layer_conv_3d

3D convolution layer (e.g. spatial convolution over volumes).
layer_conv_2d_transpose

Transposed 2D convolution layer (sometimes called Deconvolution).
k_square

Element-wise square.
k_reverse

Reverse a tensor along the specified axes.
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_placeholder

Instantiates a placeholder tensor and returns it.
layer_activity_regularization

Layer that applies an update to the cost function based input activity.
k_pool2d

2D Pooling.
k_switch

Switches between two operations depending on a scalar value.
k_update_add

Update the value of x by adding increment.
k_transpose

Transposes a tensor and returns it.
k_truncated_normal

Returns a tensor with truncated random normal distribution of values.
layer_average_pooling_1d

Average pooling for temporal data.
layer_average_pooling_3d

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

Scaled Exponential Linear Unit.
k_variable

Instantiates a variable and returns it.
layer_average_pooling_2d

Average pooling operation for spatial data.
layer_batch_normalization

Layer that normalizes its inputs
layer_activation_relu

Rectified Linear Unit activation function
k_softsign

Softsign of a tensor.
k_repeat

Repeats a 2D tensor.
layer_gaussian_noise

Apply additive zero-centered Gaussian noise.
layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.
layer_cudnn_gru

layer_cropping_3d

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

Repeats the elements of a tensor along an axis.
layer_conv_lstm_2d

Convolutional LSTM.
layer_conv_lstm_3d

3D Convolutional LSTM
k_stop_gradient

Returns variables but with zero gradient w.r.t. every other variable.
layer_depthwise_conv_1d

Depthwise 1D convolution
layer_discretization

A preprocessing layer which buckets continuous features by ranges.
layer_gru

Gated Recurrent Unit - Cho et al.
layer_gru_cell

Cell class for the GRU layer
layer_depthwise_conv_2d

Depthwise separable 2D convolution.
layer_dense

Add a densely-connected NN layer to an output
layer_dense_features

Constructs a DenseFeatures.
layer_average

Layer that averages a list of inputs.
layer_concatenate

Layer that concatenates a list of inputs.
layer_global_max_pooling_1d

Global max pooling operation for temporal data.
layer_conv_1d

1D convolution layer (e.g. temporal convolution).
layer_global_average_pooling_3d

Global Average pooling operation for 3D data.
layer_cudnn_lstm

k_sparse_categorical_crossentropy

Categorical crossentropy with integer targets.
layer_flatten

Flattens an input
layer_global_max_pooling_2d

Global max pooling operation for spatial data.
layer_embedding

Turns positive integers (indexes) into dense vectors of fixed size
layer_global_max_pooling_3d

Global Max pooling operation for 3D data.
k_unstack

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

Update the value of x to new_x.
k_tanh

Element-wise tanh.
layer_activation

Apply an activation function to an output.
k_temporal_padding

Pads the middle dimension of a 3D tensor.
layer_activation_softmax

Softmax activation function.
layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit.
layer_dot

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

Thresholded Rectified Linear Unit.
layer_lambda

Wraps arbitrary expression as a layer
layer_lstm_cell

Cell class for the LSTM layer
layer_masking

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

Applies Dropout to the input.
layer_conv_lstm_1d

1D Convolutional LSTM
layer_integer_lookup

A preprocessing layer which maps integer features to contiguous ranges.
layer_max_pooling_1d

Max pooling operation for temporal data.
layer_global_average_pooling_2d

Global average pooling operation for spatial data.
layer_conv_3d_transpose

Transposed 3D convolution layer (sometimes called Deconvolution).
layer_global_average_pooling_1d

Global average pooling operation for temporal data.
layer_max_pooling_2d

Max pooling operation for spatial data.
layer_add

Layer that adds a list of inputs.
layer_minimum

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

Layer that computes the maximum (element-wise) a list of inputs.
layer_max_pooling_3d

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

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

A preprocessing layer which normalizes continuous features.
layer_layer_normalization

Layer normalization layer (Ba et al., 2016).
layer_locally_connected_1d

Locally-connected layer for 1D inputs.
layer_permute

Permute the dimensions of an input according to a given pattern
layer_random_brightness

A preprocessing layer which randomly adjusts brightness during training
layer_random_crop

Randomly crop the images to target height and width
layer_random_contrast

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

MultiHeadAttention layer
layer_reshape

Reshapes an output to a certain shape.
layer_resizing

Image resizing layer
layer_random_height

Randomly vary the height of a batch of images during training
layer_random_flip

Randomly flip each image horizontally and vertically
layer_random_rotation

Randomly rotate each image
layer_repeat_vector

Repeats the input n times.
layer_random_translation

Randomly translate each image during training
layer_rescaling

Multiply inputs by scale and adds offset
layer_cropping_2d

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

Update the value of x by subtracting decrement.
layer_category_encoding

A preprocessing layer which encodes integer features.
layer_activation_elu

Exponential Linear Unit.
layer_cropping_1d

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

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

Long Short-Term Memory unit - Hochreiter 1997.
layer_hashing

A preprocessing layer which hashes and bins categorical features.
layer_input

Input layer
layer_locally_connected_2d

Locally-connected layer for 2D inputs.
layer_spatial_dropout_1d

Spatial 1D version of Dropout.
layer_simple_rnn_cell

Cell class for SimpleRNN
layer_spatial_dropout_2d

Spatial 2D version of Dropout.
layer_string_lookup

A preprocessing layer which maps string features to integer indices.
layer_simple_rnn

Fully-connected RNN where the output is to be fed back to input.
layer_separable_conv_1d

Depthwise separable 1D convolution.
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_rnn

Base class for recurrent layers
layer_unit_normalization

Unit normalization layer
layer_upsampling_1d

Upsampling layer for 1D inputs.
layer_subtract

Layer that subtracts two inputs.
layer_spatial_dropout_3d

Spatial 3D version of Dropout.
learning_rate_schedule_cosine_decay

A LearningRateSchedule that uses a cosine decay schedule
layer_zero_padding_3d

Zero-padding layer for 3D data (spatial or spatio-temporal).
layer_upsampling_3d

Upsampling layer for 3D inputs.
layer_text_vectorization

A preprocessing layer which maps text features to integer sequences.
layer_upsampling_2d

Upsampling layer for 2D 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).
learning_rate_schedule_inverse_time_decay

A LearningRateSchedule that uses an inverse time decay schedule
learning_rate_schedule_exponential_decay

A LearningRateSchedule that uses an exponential decay schedule
loss_cosine_proximity

(Deprecated) loss_cosine_proximity
learning_rate_schedule_piecewise_constant_decay

A LearningRateSchedule that uses a piecewise constant decay schedule
metric-or-Metric

metric-or-Metric
make_sampling_table

Generates a word rank-based probabilistic sampling table.
learning_rate_schedule_polynomial_decay

A LearningRateSchedule that uses a polynomial decay schedule
loss-functions

Loss functions
learning_rate_schedule_cosine_decay_restarts

A LearningRateSchedule that uses a cosine decay schedule with restarts
metric_accuracy

Calculates how often predictions equal labels
metric_cosine_proximity

(Deprecated) metric_cosine_proximity
metric_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions
metric_auc

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

Computes the cosine similarity between the labels and predictions
metric_false_negatives

Calculates the number of false negatives
metric_false_positives

Calculates the number of false positives
metric_categorical_hinge

Computes the categorical hinge metric between y_true and y_pred
metric_binary_accuracy

Calculates how often predictions match binary labels
metric_categorical_accuracy

Calculates how often predictions match one-hot labels
metric_binary_crossentropy

Computes the crossentropy metric between the labels and predictions
metric_hinge

Computes the hinge metric between y_true and y_pred
metric_kullback_leibler_divergence

Computes Kullback-Leibler divergence
metric_mean_absolute_error

Computes the mean absolute error between the labels and predictions
metric_mean_absolute_percentage_error

Computes the mean absolute percentage error between y_true and y_pred
metric_mean_iou

Computes the mean Intersection-Over-Union metric
metric_mean

Computes the (weighted) mean of the given values
metric_logcosh_error

Computes the logarithm of the hyperbolic cosine of the prediction error
metric_mean_relative_error

Computes the mean relative error by normalizing with the given values
metric_mean_squared_error

Computes the mean squared error between labels and predictions
metric_mean_squared_logarithmic_error

Computes the mean squared logarithmic error
metric_sparse_categorical_accuracy

Calculates how often predictions match integer labels
metric_precision_at_recall

Computes best precision where recall is >= specified value
metric_recall_at_precision

Computes best recall where precision is >= specified value
metric_mean_tensor

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

Computes the recall of the predictions with respect to the labels
metric_sensitivity_at_specificity

Computes best sensitivity where specificity is >= specified value
metric_poisson

Computes the Poisson metric between y_true and y_pred
metric_precision

Computes the precision of the predictions with respect to the labels
metric_mean_wrapper

Wraps a stateless metric function with the Mean metric
metric_root_mean_squared_error

Computes root mean squared error metric between y_true and y_pred
metric_squared_hinge

Computes the squared hinge metric
metric_top_k_categorical_accuracy

Computes how often targets are in the top K predictions
metric_sum

Computes the (weighted) sum of the given values
model_from_saved_model

Load a Keras model from the Saved Model format
metric_specificity_at_sensitivity

Computes best specificity where sensitivity is >= specified value
metric_true_positives

Calculates the number of true positives
metric_sparse_top_k_categorical_accuracy

Computes how often integer targets are in the top K predictions
metric_true_negatives

Calculates the number of true negatives
metric_sparse_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions
model_to_json

Model configuration as JSON
%<-%

Assign values to names
new_learning_rate_schedule_class

Create a new learning rate schedule type
optimizer_adam

Optimizer that implements the Adam algorithm
model_to_saved_model

(Deprecated) Export to Saved Model format
optimizer_adagrad

Optimizer that implements the Adagrad algorithm
new_metric_class

Define new keras types
normalize

Normalize a matrix or nd-array
optimizer_adadelta

Optimizer that implements the Adadelta algorithm
model_to_yaml

Model configuration as YAML
multi_gpu_model

(Deprecated) Replicates a model on different GPUs.
optimizer_sgd

Gradient descent (with momentum) optimizer
optimizer_nadam

Optimizer that implements the Nadam algorithm
pop_layer

Remove the last layer in a model
optimizer_rmsprop

Optimizer that implements the RMSprop algorithm
pad_sequences

Pads sequences to the same length
plot.keras.engine.training.Model

Plot a Keras model
%>%

Pipe operator
optimizer_adamax

Optimizer that implements the Adamax algorithm
plot.keras_training_history

Plot training history
optimizer_ftrl

Optimizer that implements the FTRL algorithm
save_model_tf

Save/Load models using SavedModel format
save_model_hdf5

Save/Load models using HDF5 files
predict_on_batch

Returns predictions for a single batch of samples.
predict_proba

(Deprecated) Generates probability or class probability predictions for the input samples.
regularizer_l1

L1 and L2 regularization
reset_states

Reset the states for a layer
regularizer_orthogonal

A regularizer that encourages input vectors to be orthogonal to each other
predict.keras.engine.training.Model

Generate predictions from a Keras model
reexports

Objects exported from other packages
predict_generator

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

Generates skipgram word pairs.
summary.keras.engine.training.Model

Print a summary of a Keras model
serialize_model

Serialize a model to an R object
save_model_weights_tf

Save model weights in the SavedModel format
save_model_weights_hdf5

Save/Load model weights using HDF5 files
sequential_model_input_layer

sequential_model_input_layer
text_hashing_trick

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

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

Convert a list of sequences into a matrix.
save_text_tokenizer

Save a text tokenizer to an external file
text_to_word_sequence

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

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

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

Text tokenization utility
time_distributed

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

Transform each text in texts in a sequence of integers.
timeseries_generator

Utility function for generating batches of temporal data.
timeseries_dataset_from_array

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

Provide a scope with mappings of names to custom objects
zip_lists

zip lists
train_on_batch

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

Select a Keras implementation and backend