`install.packages('keras')`

21,377

2.7.0

MIT + file LICENSE

November 9th, 2021

KerasWrapper

(Deprecated) Base R6 class for Keras wrappers

Metric

Metric

adapt

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

KerasConstraint

(Deprecated) Base R6 class for Keras constraints

KerasLayer

(Deprecated) Base R6 class for Keras layers

KerasCallback

(Deprecated) Base R6 class for Keras callbacks

activation_relu

Activation functions

Layer

Create a custom Layer

application_densenet

Instantiates the DenseNet architecture.

application_efficientnet

Instantiates the EfficientNetB0 architecture

application_mobilenet

MobileNet model architecture.

application_mobilenet_v3

Instantiates the MobileNetV3Large architecture

compile.keras.engine.training.Model

Configure a Keras model for training

application_mobilenet_v2

MobileNetV2 model architecture

constraints

Weight constraints

application_inception_v3

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

callback_remote_monitor

Callback used to stream events to a server.

count_params

Count the total number of scalars composing the weights.

callback_tensorboard

TensorBoard basic visualizations

application_inception_resnet_v2

Inception-ResNet v2 model, with weights trained on ImageNet

application_resnet

Instantiates the ResNet architecture

application_nasnet

Instantiates a NASNet model.

bidirectional

Bidirectional wrapper for RNNs

create_layer

Create a Keras Layer

dataset_cifar10

CIFAR10 small image classification

application_xception

Instantiates the Xception architecture

fit_generator

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

fit_image_data_generator

Fit image data generator internal statistics to some sample data.

dataset_cifar100

CIFAR100 small image classification

freeze_weights

Freeze and unfreeze weights

generator_next

Retrieve the next item from a generator

get_input_at

Retrieve tensors for layers with multiple nodes

get_weights

Layer/Model weights as R arrays

callback_progbar_logger

Callback that prints metrics to stdout.

callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.

backend

Keras backend tensor engine

callback_model_checkpoint

Save the model after every epoch.

callback_learning_rate_scheduler

Learning rate scheduler.

get_layer

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

create_layer_wrapper

Create a Keras Layer wrapper

fit.keras.engine.training.Model

Train a Keras model

create_wrapper

(Deprecated) Create a Keras Wrapper

export_savedmodel.keras.engine.training.Model

Export a Saved Model

callback_csv_logger

Callback that streams epoch results to a csv file

image_data_generator

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

custom_metric

Custom metric function

callback_early_stopping

Stop training when a monitored quantity has stopped improving.

callback_lambda

Create a custom callback

application_vgg

VGG16 and VGG19 models for Keras.

dataset_boston_housing

Boston housing price regression dataset

install_keras

Install TensorFlow and Keras, including all Python dependencies

image_dataset_from_directory

Create a dataset from a directory

k_abs

Element-wise absolute value.

is_keras_available

Check if Keras is Available

%py_class%

Make a python class constructor

initializer_he_normal

He normal initializer.

initializer_he_uniform

He uniform variance scaling initializer.

callback_terminate_on_naan

Callback that terminates training when a NaN loss is encountered.

evaluate.keras.engine.training.Model

Evaluate a Keras model

clone_model

Clone a model instance.

initializer_orthogonal

Initializer that generates a random orthogonal matrix.

evaluate_generator

Evaluates the model on a data generator.

initializer_glorot_uniform

Glorot uniform initializer, also called Xavier uniform initializer.

initializer_glorot_normal

Glorot normal initializer, also called Xavier normal initializer.

dataset_fashion_mnist

Fashion-MNIST database of fashion articles

fit_text_tokenizer

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

dataset_imdb

IMDB Movie reviews sentiment classification

initializer_random_normal

Initializer that generates tensors with a normal distribution.

initializer_variance_scaling

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

initializer_zeros

Initializer that generates tensors initialized to 0.

dataset_reuters

Reuters newswire topics classification

dataset_mnist

MNIST database of handwritten digits

k_any

Bitwise reduction (logical OR).

flow_images_from_dataframe

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

get_config

Layer/Model configuration

flow_images_from_directory

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

imagenet_decode_predictions

Decodes the prediction of an ImageNet model.

imagenet_preprocess_input

Preprocesses a tensor or array encoding a batch of images.

image_to_array

3D array representation of images

get_file

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

image_load

Loads an image into PIL format.

initializer_identity

Initializer that generates the identity matrix.

k_argmax

Returns the index of the maximum value along an axis.

initializer_lecun_normal

LeCun normal initializer.

flow_images_from_data

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

initializer_lecun_uniform

LeCun uniform initializer.

%<-active%

Make an Active Binding

hdf5_matrix

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

k_backend

Active Keras backend

k_batch_get_value

Returns the value of more than one tensor variable.

initializer_ones

Initializer that generates tensors initialized to 1.

k_batch_flatten

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

implementation

Keras implementation

k_conv3d

3D convolution.

k_batch_dot

Batchwise dot product.

k_bias_add

Adds a bias vector to a tensor.

k_arange

Creates a 1D tensor containing a sequence of integers.

k_binary_crossentropy

Binary crossentropy between an output tensor and a target tensor.

initializer_constant

Initializer that generates tensors initialized to a constant value.

k_clear_session

Destroys the current TF graph and creates a new one.

k_categorical_crossentropy

Categorical crossentropy between an output tensor and a target tensor.

k_argmin

Returns the index of the minimum value along an axis.

initializer_random_uniform

Initializer that generates tensors with a uniform distribution.

initializer_truncated_normal

Initializer that generates a truncated normal distribution.

k_ctc_batch_cost

Runs CTC loss algorithm on each batch element.

k_all

Bitwise reduction (logical AND).

k_cast

Casts a tensor to a different dtype and returns it.

k_cast_to_floatx

Cast an array to the default Keras float type.

k_concatenate

Concatenates a list of tensors alongside the specified axis.

k_conv1d

1D convolution.

k_clip

Element-wise value clipping.

k_constant

Creates a constant tensor.

k_conv3d_transpose

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

k_ctc_label_dense_to_sparse

Converts CTC labels from dense to sparse.

k_ctc_decode

Decodes the output of a softmax.

k_cos

Computes cos of x element-wise.

k_count_params

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

k_batch_normalization

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

k_function

Instantiates a Keras function

k_cumprod

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

k_batch_set_value

Sets the values of many tensor variables at once.

k_flatten

Flatten a tensor.

k_cumsum

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

k_floatx

Default float type

k_gather

Retrieves the elements of indices

`indices`

in the tensor `reference`

.k_gradients

Returns the gradients of

`variables`

w.r.t. `loss`

.k_conv2d

2D convolution.

k_epsilon

Fuzz factor used in numeric expressions.

k_dtype

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

k_depthwise_conv2d

Depthwise 2D convolution with separable filters.

k_eval

Evaluates the value of a variable.

k_identity

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

k_exp

Element-wise exponential.

k_ones_like

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

k_reset_uids

Reset graph identifiers.

k_ones

Instantiates an all-ones tensor variable and returns it.

k_image_data_format

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

k_repeat_elements

Repeats the elements of a tensor along an axis.

k_greater

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

k_sin

Computes sin of x element-wise.

k_l2_normalize

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

k_conv2d_transpose

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

k_dot

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

k_get_session

TF session to be used by the backend.

k_elu

Exponential linear unit.

k_is_keras_tensor

Returns whether

`x`

is a Keras tensor.k_foldl

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

k_max

Maximum value in a tensor.

k_foldr

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

k_get_uid

Get the uid for the default graph.

k_is_placeholder

Returns whether

`x`

is a placeholder.k_softmax

Softmax of a tensor.

k_greater_equal

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

k_maximum

Element-wise maximum of two tensors.

k_random_binomial

Returns a tensor with random binomial distribution of values.

k_prod

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

k_sigmoid

Element-wise sigmoid.

k_ndim

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

k_is_sparse

Returns whether a tensor is a sparse tensor.

k_is_tensor

Returns whether

`x`

is a symbolic tensor.k_local_conv1d

Apply 1D conv with un-shared weights.

k_hard_sigmoid

Segment-wise linear approximation of sigmoid.

k_local_conv2d

Apply 2D conv with un-shared weights.

k_learning_phase

Returns the learning phase flag.

k_normalize_batch_in_training

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

k_temporal_padding

Pads the middle dimension of a 3D tensor.

k_pool2d

2D Pooling.

k_sign

Element-wise sign.

layer_dense_features

Constructs a DenseFeatures.

layer_activation_softmax

Softmax activation function.

layer_additive_attention

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

k_tile

Creates a tensor by tiling

`x`

by `n`

.layer_activation_thresholded_relu

Thresholded Rectified Linear Unit.

layer_alpha_dropout

Applies Alpha Dropout to the input.

layer_depthwise_conv_2d

Depthwise separable 2D convolution.

k_in_test_phase

Selects

`x`

in test phase, and `alt`

otherwise.k_dropout

Sets entries in

`x`

to zero at random, while scaling the entire tensor.k_stack

Stacks a list of rank

`R`

tensors into a rank `R+1`

tensor.k_in_top_k

Returns whether the

`targets`

are in the top `k`

`predictions`

.layer_global_max_pooling_3d

Global Max pooling operation for 3D data.

k_equal

Element-wise equality between two tensors.

k_expand_dims

Adds a 1-sized dimension at index

`axis`

.k_manual_variable_initialization

Sets the manual variable initialization flag.

k_mean

Mean of a tensor, alongside the specified axis.

k_map_fn

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

k_pool3d

3D Pooling.

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_std

Standard deviation of a tensor, alongside the specified axis.

k_logsumexp

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

k_log

Element-wise log.

k_pow

Element-wise exponentiation.

k_set_value

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

k_min

Minimum value in a tensor.

k_print_tensor

Prints

`message`

and the tensor value when evaluated.k_reverse

Reverse a tensor along the specified axes.

k_resize_volumes

Resizes the volume contained in a 5D tensor.

k_truncated_normal

Returns a tensor with truncated random normal distribution of values.

layer_gru

Gated Recurrent Unit - Cho et al.

layer_lstm

Long Short-Term Memory unit - Hochreiter 1997.

k_placeholder

Instantiates a placeholder tensor and returns it.

k_one_hot

Computes the one-hot representation of an integer tensor.

k_repeat

Repeats a 2D tensor.

k_permute_dimensions

Permutes axes in a tensor.

k_not_equal

Element-wise inequality between two tensors.

k_relu

Rectified linear unit.

k_shape

Returns the symbolic shape of a tensor or variable.

k_softsign

Softsign of a tensor.

k_softplus

Softplus of a tensor.

k_update

Update the value of

`x`

to `new_x`

.k_rnn

Iterates over the time dimension of a tensor

k_tanh

Element-wise tanh.

layer_activation_parametric_relu

Parametric Rectified Linear Unit.

layer_average

Layer that averages a list of inputs.

keras_model

Keras Model

layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit.

k_switch

Switches between two operations depending on a scalar value.

layer_attention

Creates attention layer

keras_array

Keras array object

layer_category_encoding

A preprocessing layer which encodes integer features.

layer_lstm_cell

Cell class for the LSTM layer

layer_reshape

Reshapes an output to a certain shape.

k_eye

Instantiate an identity matrix and returns it.

k_less

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

k_in_train_phase

Selects

`x`

in train phase, and `alt`

otherwise.k_get_value

Returns the value of a variable.

k_get_variable_shape

Returns the shape of a variable.

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_update_add

Update the value of

`x`

by adding `increment`

.k_square

Element-wise square.

layer_resizing

Image resizing layer

k_round

Element-wise rounding to the closest integer.

k_minimum

Element-wise minimum of two tensors.

k_moving_average_update

Compute the moving average of a variable.

k_random_normal

Returns a tensor with normal distribution of values.

k_update_sub

Update the value of

`x`

by subtracting `decrement`

.layer_discretization

A preprocessing layer which buckets continuous features by ranges.

layer_center_crop

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

layer_conv_lstm_2d

Convolutional LSTM.

layer_conv_lstm_3d

3D Convolutional LSTM

layer_dot

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

layer_input

Input layer

k_sparse_categorical_crossentropy

Categorical crossentropy with integer targets.

k_reshape

Reshapes a tensor to the specified shape.

metric_categorical_accuracy

Calculates how often predictions match one-hot labels

k_random_normal_variable

Instantiates a variable with values drawn from a normal distribution.

layer_activation

Apply an activation function to an output.

layer_activation_elu

Exponential Linear Unit.

k_spatial_2d_padding

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

layer_integer_lookup

A preprocessing layer which maps integer features to contiguous ranges.

layer_locally_connected_2d

Locally-connected layer for 2D inputs.

layer_locally_connected_1d

Locally-connected layer for 1D inputs.

k_resize_images

Resizes the images contained in a 4D tensor.

layer_conv_1d

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

layer_average_pooling_3d

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

layer_batch_normalization

Batch normalization layer (Ioffe and Szegedy, 2014).

layer_concatenate

Layer that concatenates a list of inputs.

k_separable_conv2d

2D convolution with separable filters.

layer_cropping_3d

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

layer_flatten

Flattens an input

metric_mean

Computes the (weighted) mean of the given values

layer_cudnn_gru

metric_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions

k_set_learning_phase

Sets the learning phase to a fixed value.

k_zeros_like

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

keras_model_custom

Create a Keras custom model

k_zeros

Instantiates an all-zeros variable and returns it.

metric_top_k_categorical_accuracy

Computes how often targets are in the top

`K`

predictionsmetric_mean_absolute_error

Computes the mean absolute error between the labels and predictions

metric_precision

Computes the precision of the predictions with respect to the labels

metric_precision_at_recall

Computes best precision where recall is >= specified value

layer_random_flip

Randomly flip each image horizontally and vertically

layer_separable_conv_2d

Separable 2D convolution.

layer_random_height

Randomly vary the height of a batch of images during training

layer_simple_rnn

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

layer_upsampling_2d

Upsampling layer for 2D inputs.

layer_upsampling_1d

Upsampling layer for 1D inputs.

k_squeeze

Removes a 1-dimension from the tensor at index

`axis`

.optimizer_adam

Adam optimizer

metric_true_negatives

Calculates the number of true negatives

optimizer_adamax

Adamax optimizer

keras_model_sequential

Keras Model composed of a linear stack of layers

k_sqrt

Element-wise square root.

k_transpose

Transposes a tensor and returns it.

k_to_dense

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

k_spatial_3d_padding

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

keras-package

R interface to Keras

predict_generator

Generates predictions for the input samples from a data generator.

layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.

layer_conv_2d_transpose

Transposed 2D convolution layer (sometimes called Deconvolution).

keras

Main Keras module

layer_upsampling_3d

Upsampling layer for 3D inputs.

layer_global_max_pooling_1d

Global max pooling operation for temporal data.

layer_cudnn_lstm

layer_global_average_pooling_2d

Global average pooling operation for spatial data.

layer_dense

Add a densely-connected NN layer to an output

layer_conv_3d

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

layer_global_average_pooling_3d

Global Average pooling operation for 3D data.

layer_zero_padding_1d

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

metric_cosine_similarity

Computes the cosine similarity between the labels and predictions

predict_on_batch

Returns predictions for a single batch of samples.

layer_lambda

Wraps arbitrary expression as a layer

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.

metric_false_negatives

Calculates the number of false negatives

k_var

Variance of a tensor, alongside the specified axis.

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 directorylayer_activity_regularization

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

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

k_variable

Instantiates a variable and returns it.

metric_recall

Computes the recall of the predictions with respect to the labels

layer_add

Layer that adds a list of inputs.

layer_conv_lstm_1d

1D Convolutional LSTM

layer_conv_3d_transpose

Transposed 3D convolution layer (sometimes called Deconvolution).

layer_global_max_pooling_2d

Global max pooling operation for spatial data.

layer_layer_normalization

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

layer_normalization

A preprocessing layer which normalizes continuous features.

layer_permute

Permute the dimensions of an input according to a given pattern

metric_recall_at_precision

Computes best recall where precision is >= specified value

optimizer_adadelta

Adadelta optimizer.

layer_dropout

Applies Dropout to the input.

layer_activation_selu

Scaled Exponential Linear Unit.

layer_activation_relu

Rectified Linear Unit activation function

layer_average_pooling_1d

Average pooling for temporal data.

layer_separable_conv_1d

Depthwise separable 1D convolution.

layer_rnn

Base class for recurrent layers

layer_stacked_rnn_cells

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

layer_max_pooling_1d

Max pooling operation for temporal data.

layer_masking

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

layer_multi_head_attention

MultiHeadAttention layer

layer_random_width

Randomly vary the width of a batch of images during training

layer_random_zoom

A preprocessing layer which randomly zooms images during training.

layer_multiply

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

layer_simple_rnn_cell

Cell class for SimpleRNN

optimizer_sgd

Stochastic gradient descent optimizer

optimizer_adagrad

Adagrad optimizer.

layer_string_lookup

A preprocessing layer which maps string features to integer indices.

loss_cosine_proximity

(Deprecated) loss_cosine_proximity

loss-functions

Loss functions

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_max_pooling_2d

Max pooling operation for spatial data.

layer_embedding

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

metric_binary_accuracy

Calculates how often predictions match binary labels

layer_conv_1d_transpose

Transposed 1D convolution layer (sometimes called Deconvolution).

layer_average_pooling_2d

Average pooling operation for spatial data.

layer_random_crop

Randomly crop the images to target height and width

layer_spatial_dropout_1d

Spatial 1D version of Dropout.

metric_binary_crossentropy

Computes the crossentropy metric between the labels and predictions

make_sampling_table

Generates a word rank-based probabilistic sampling table.

metric_false_positives

Calculates the number of false positives

metric-or-Metric

metric-or-Metric

layer_cropping_1d

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

layer_conv_2d

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

metric_hinge

Computes the hinge metric between

`y_true`

and `y_pred`

metric_kullback_leibler_divergence

Computes Kullback-Leibler divergence

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_sparse_top_k_categorical_accuracy

Computes how often integer targets are in the top

`K`

predictionslayer_subtract

Layer that subtracts two inputs.

layer_cropping_2d

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

layer_gaussian_noise

Apply additive zero-centered Gaussian noise.

pad_sequences

Pads sequences to the same length

regularizer_l1

L1 and L2 regularization

metric_specificity_at_sensitivity

Computes best specificity where sensitivity is >= specified value

metric_logcosh_error

Computes the logarithm of the hyperbolic cosine of the prediction error

layer_global_average_pooling_1d

Global average pooling operation for temporal data.

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_text_vectorization

A preprocessing layer which maps text features to integer sequences.

reset_states

Reset the states for a layer

metric_mean_tensor

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

metric_mean_squared_logarithmic_error

Computes the mean squared logarithmic error

metric_sparse_categorical_accuracy

Calculates how often predictions match integer labels

layer_gru_cell

Cell class for the GRU layer

metric_mean_wrapper

Wraps a stateless metric function with the Mean metric

predict_proba

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

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.

metric_sparse_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions

layer_hashing

A preprocessing layer which hashes and bins categorical features.

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.

timeseries_generator

Utility function for generating batches of temporal data.

layer_random_rotation

Randomly rotate each image

reexports

Objects exported from other packages

metric_accuracy

Calculates how often predictions equal labels

layer_repeat_vector

Repeats the input n times.

layer_spatial_dropout_2d

Spatial 2D version of Dropout.

layer_random_translation

Randomly translate each image during training

layer_spatial_dropout_3d

Spatial 3D version of Dropout.

layer_rescaling

Multiply inputs by

`scale`

and adds `offset`

metric_poisson

Computes the Poisson metric between

`y_true`

and `y_pred`

metric_squared_hinge

Computes the squared hinge metric

sequential_model_input_layer

sequential_model_input_layer

metric_sum

Computes the (weighted) sum of the given values

train_on_batch

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

optimizer_rmsprop

RMSProp optimizer

optimizer_nadam

Nesterov Adam optimizer

serialize_model

Serialize a model to an R object

save_model_weights_hdf5

Save/Load model weights using HDF5 files

save_model_weights_tf

Save model weights in the SavedModel format

to_categorical

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

metric_auc

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

model_to_json

Model configuration as JSON

metric_sensitivity_at_specificity

Computes best sensitivity where specificity is >= specified value

metric_root_mean_squared_error

Computes root mean squared error metric between

`y_true`

and `y_pred`

metric_cosine_proximity

(Deprecated) metric_cosine_proximity

metric_categorical_hinge

Computes the categorical hinge metric between

`y_true`

and `y_pred`

metric_true_positives

Calculates the number of true positives

texts_to_sequences

Transform each text in texts in a sequence of integers.

model_from_saved_model

Load a Keras model from the Saved Model format

texts_to_sequences_generator

Transforms each text in texts in a sequence of integers.

use_implementation

Select a Keras implementation and backend

model_to_saved_model

Export to Saved Model format

multi_gpu_model

Replicates a model on different GPUs.

normalize

Normalize a matrix or nd-array

plot.keras_training_history

Plot training history

save_text_tokenizer

Save a text tokenizer to an external file

%>%

Pipe operator

pop_layer

Remove the last layer in a model

model_to_yaml

Model configuration as YAML

%<-%

Assign values to names

predict.keras.engine.training.Model

Generate predictions from a Keras model

save_model_hdf5

Save/Load models using HDF5 files

sequences_to_matrix

Convert a list of sequences into a matrix.

summary.keras.engine.training.Model

Print a summary of a Keras model

skipgrams

Generates skipgram word pairs.

save_model_tf

Save/Load models using SavedModel format

with_custom_object_scope

Provide a scope with mappings of names to custom objects

text_tokenizer

Text tokenization utility

time_distributed

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

timeseries_dataset_from_array

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

texts_to_matrix

Convert a list of texts to a matrix.