Learn R Programming

⚠️There's a newer version (2.13.0) of this package.Take me there.

keras (version 2.2.5.0)

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')

Monthly Downloads

30,713

Version

2.2.5.0

License

MIT + file LICENSE

Maintainer

Daniel Falbel

Last Published

October 8th, 2019

Functions in keras (2.2.5.0)

KerasConstraint

Base R6 class for Keras constraints
application_mobilenet_v2

MobileNetV2 model architecture
KerasCallback

Base R6 class for Keras callbacks
application_densenet

Instantiates the DenseNet architecture.
application_inception_resnet_v2

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

Activation functions
KerasLayer

Base R6 class for Keras layers
KerasWrapper

Base R6 class for Keras wrappers
application_mobilenet

MobileNet model architecture.
application_inception_v3

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

Callback that streams epoch results to a csv file
application_xception

Xception V1 model for Keras.
application_vgg

VGG16 and VGG19 models for Keras.
callback_early_stopping

Stop training when a monitored quantity has stopped improving.
constraints

Weight constraints
count_params

Count the total number of scalars composing the weights.
backend

Keras backend tensor engine
callback_remote_monitor

Callback used to stream events to a server.
callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.
bidirectional

Bidirectional wrapper for RNNs.
callback_progbar_logger

Callback that prints metrics to stdout.
callback_model_checkpoint

Save the model after every epoch.
create_layer

Create a Keras Layer
create_wrapper

Create a Keras Wrapper
evaluate.keras.engine.training.Model

Evaluate a Keras model
dataset_reuters

Reuters newswire topics classification
dataset_fashion_mnist

Fashion-MNIST database of fashion articles
callback_lambda

Create a custom callback
dataset_cifar100

CIFAR100 small image classification
callback_terminate_on_naan

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

Learning rate scheduler.
callback_tensorboard

TensorBoard basic visualizations
application_nasnet

Instantiates a NASNet model.
clone_model

Clone a model instance.
compile.keras.engine.training.Model

Configure a Keras model for training
dataset_mnist

MNIST database of handwritten digits
dataset_imdb

IMDB Movie reviews sentiment classification
dataset_cifar10

CIFAR10 small image classification
dataset_boston_housing

Boston housing price regression dataset
application_resnet50

ResNet50 model for Keras.
flow_images_from_directory

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

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

Evaluates the model on a data generator.
fit.keras.engine.training.Model

Train a Keras model
flow_images_from_dataframe

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

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

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

Export a Saved Model
freeze_weights

Freeze and unfreeze weights
image_data_generator

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

Loads an image into PIL format.
fit_generator

Fits the model on data yielded batch-by-batch by a generator.
hdf5_matrix

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

Retrieve the next item from a generator
get_config

Layer/Model configuration
imagenet_decode_predictions

Decodes the prediction of an ImageNet model.
initializer_identity

Initializer that generates the identity matrix.
get_file

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

Keras implementation
initializer_glorot_normal

Glorot normal initializer, also called Xavier normal initializer.
image_to_array

3D array representation of images
initializer_glorot_uniform

Glorot uniform initializer, also called Xavier uniform initializer.
get_weights

Layer/Model weights as R arrays
get_layer

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

Install Keras and the TensorFlow backend
initializer_lecun_normal

LeCun normal initializer.
initializer_orthogonal

Initializer that generates a random orthogonal matrix.
initializer_random_normal

Initializer that generates tensors with a normal distribution.
imagenet_preprocess_input

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

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

Retrieve tensors for layers with multiple nodes
k_backend

Active Keras backend
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.
initializer_random_uniform

Initializer that generates tensors with a uniform distribution.
initializer_truncated_normal

Initializer that generates a truncated normal distribution.
k_argmin

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

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

He normal initializer.
initializer_he_uniform

He uniform variance scaling initializer.
is_keras_available

Check if Keras is Available
k_batch_set_value

Sets the values of many tensor variables at once.
k_constant

Creates a constant tensor.
k_any

Bitwise reduction (logical OR).
k_batch_dot

Batchwise dot product.
k_clip

Element-wise value clipping.
initializer_variance_scaling

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

Initializer that generates tensors initialized to 0.
k_abs

Element-wise absolute value.
k_all

Bitwise reduction (logical AND).
k_categorical_crossentropy

Categorical 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.
initializer_constant

Initializer that generates tensors initialized to a constant value.
k_concatenate

Concatenates a list of tensors alongside the specified axis.
k_conv1d

1D convolution.
k_clear_session

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

Decodes the output of a softmax.
k_ctc_batch_cost

Runs CTC loss algorithm on each batch element.
k_epsilon

Fuzz factor used in numeric expressions.
k_expand_dims

Adds a 1-sized dimension at index axis.
k_equal

Element-wise equality between two tensors.
k_conv3d

3D convolution.
k_conv3d_transpose

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

Evaluates the value of a variable.
k_depthwise_conv2d

Depthwise 2D convolution with separable filters.
k_cumsum

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

Element-wise exponential.
initializer_lecun_uniform

LeCun uniform initializer.
initializer_ones

Initializer that generates tensors initialized to 1.
k_conv2d

2D convolution.
k_get_value

Returns the value of a variable.
k_arange

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

Element-wise log.
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_get_variable_shape

Returns the shape of a variable.
k_logsumexp

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

Instantiate an identity matrix and returns it.
k_identity

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

Instantiates a Keras function
k_binary_crossentropy

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

Adds a bias vector to a tensor.
k_cos

Computes cos of x element-wise.
k_count_params

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

Selects x in train phase, and alt otherwise.
k_elu

Exponential linear unit.
k_int_shape

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

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

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

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

Multiplies 2 tensors (and/or variables) and returns a tensor.
k_conv2d_transpose

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

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

Instantiates an all-ones tensor variable and returns it.
k_flatten

Flatten a tensor.
k_floatx

Default float type
k_less

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

Get the uid for the default graph.
k_get_session

TF session to be used by the backend.
k_hard_sigmoid

Segment-wise linear approximation of sigmoid.
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_foldl

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

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

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

Mean of a tensor, alongside the specified axis.
k_permute_dimensions

Permutes axes in a tensor.
k_is_tensor

Returns whether x is a symbolic tensor.
k_local_conv2d

Apply 2D conv with un-shared weights.
k_one_hot

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

Element-wise exponentiation.
k_local_conv1d

Apply 1D conv with un-shared weights.
k_image_data_format

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

Returns whether a tensor is a sparse tensor.
k_not_equal

Element-wise inequality between two tensors.
k_foldr

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

Instantiates a placeholder tensor and returns it.
k_print_tensor

Prints message and the tensor value when evaluated.
k_greater

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

Element-wise maximum of two tensors.
k_is_placeholder

Returns whether x is a placeholder.
k_gradients

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

Maximum value in a tensor.
k_is_keras_tensor

Returns whether x is a Keras tensor.
k_set_learning_phase

Sets the learning phase to a fixed value.
k_separable_conv2d

2D convolution with separable filters.
k_spatial_3d_padding

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

Element-wise square root.
k_ndim

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

Switches between two operations depending on a scalar value.
k_round

Element-wise rounding to the closest integer.
k_resize_images

Resizes the images contained in a 4D tensor.
k_reshape

Reshapes a tensor to the specified shape.
k_rnn

Iterates over the time dimension of a tensor
k_min

Minimum value in a tensor.
k_l2_normalize

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

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

Sets the manual variable initialization flag.
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_minimum

Element-wise minimum of two tensors.
k_reverse

Reverse a tensor along the specified axes.
k_pool3d

3D Pooling.
k_pool2d

2D Pooling.
k_set_value

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

Resizes the volume contained in a 5D tensor.
k_shape

Returns the symbolic shape of a tensor or variable.
k_repeat_elements

Repeats the elements of a tensor along an axis.
k_square

Element-wise square.
k_squeeze

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

Rectified linear unit.
k_reset_uids

Reset graph identifiers.
keras_model

Keras Model
k_tile

Creates a tensor by tiling x by n.
layer_activity_regularization

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

Thresholded Rectified Linear Unit.
keras_model_custom

Create a Keras custom model
k_zeros_like

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

Repeats a 2D tensor.
k_zeros

Instantiates an all-zeros variable and returns it.
keras_model_sequential

Keras Model composed of a linear stack of layers
k_tanh

Element-wise tanh.
k_stack

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

Transposes a tensor and returns it.
keras_array

Keras array object
keras-package

R interface to Keras
k_to_dense

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

Compute the moving average of a variable.
layer_activation_selu

Scaled Exponential Linear Unit.
layer_max_pooling_1d

Max pooling operation for temporal data.
layer_masking

Masks a sequence by using a mask value to skip timesteps.
layer_upsampling_3d

Upsampling layer for 3D inputs.
layer_upsampling_2d

Upsampling layer for 2D inputs.
k_var

Variance of a tensor, alongside the specified axis.
k_variable

Instantiates a variable and returns it.
k_std

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

Parametric Rectified Linear Unit.
layer_activation_relu

Rectified Linear Unit activation function
k_prod

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

Softmax activation function.
layer_average_pooling_3d

Average pooling operation for 3D data (spatial or spatio-temporal).
layer_average_pooling_2d

Average pooling operation for spatial data.
layer_cropping_3d

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

layer_dense

Add a densely-connected NN layer to an output
layer_conv_2d

2D convolution layer (e.g. spatial convolution over images).
layer_depthwise_conv_2d

Depthwise separable 2D convolution.
layer_dense_features

Constructs a DenseFeatures.
layer_cudnn_lstm

layer_conv_1d

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

Returns a tensor with random binomial distribution of values.
layer_lstm

Long Short-Term Memory unit - Hochreiter 1997.
layer_locally_connected_2d

Locally-connected layer for 2D inputs.
layer_max_pooling_2d

Max pooling operation for spatial data.
layer_activation

Apply an activation function to an output.
layer_average_pooling_1d

Average pooling for temporal data.
layer_cropping_2d

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

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

Layer that averages a list of inputs.
layer_cropping_1d

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

Element-wise sigmoid.
layer_separable_conv_1d

Depthwise separable 1D convolution.
layer_separable_conv_2d

Separable 2D convolution.
layer_max_pooling_3d

Max pooling operation for 3D data (spatial or spatio-temporal).
layer_zero_padding_1d

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

Flattens an input
k_sign

Element-wise sign.
k_softplus

Softplus of a tensor.
k_softsign

Softsign of a tensor.
k_truncated_normal

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

Wraps arbitrary expression as a layer
model_to_saved_model

Export to Saved Model format
model_to_yaml

Model configuration as YAML
predict.keras.engine.training.Model

Generate predictions from a Keras model
predict_generator

Generates predictions for the input samples from a data generator.
layer_activation_elu

Exponential Linear Unit.
layer_add

Layer that adds a list of inputs.
k_update

Update the value of x to new_x.
layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit.
layer_zero_padding_2d

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

Applies Alpha Dropout to the input.
text_tokenizer

Text tokenization utility
save_text_tokenizer

Save a text tokenizer to an external file
text_to_word_sequence

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

Save model weights in the SavedModel format
layer_maximum

Layer that computes the maximum (element-wise) a list of inputs.
layer_locally_connected_1d

Locally-connected layer for 1D inputs.
layer_minimum

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

Fully-connected RNN where the output is to be fed back to input.
layer_spatial_dropout_1d

Spatial 1D version of Dropout.
train_on_batch

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

Returns a tensor with uniform distribution of values.
layer_conv_2d_transpose

Transposed 2D convolution layer (sometimes called Deconvolution).
layer_global_average_pooling_1d

Global average pooling operation for temporal 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.
optimizer_sgd

Stochastic gradient descent optimizer
predict_proba

Generates probability or class probability predictions for the input samples.
layer_spatial_dropout_3d

Spatial 3D version of Dropout.
reset_states

Reset the states for a layer
layer_spatial_dropout_2d

Spatial 2D version of Dropout.
layer_global_max_pooling_2d

Global max pooling operation for spatial data.
optimizer_rmsprop

RMSProp optimizer
predict_on_batch

Returns predictions for a single batch of samples.
layer_conv_3d

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

Adamax optimizer
save_model_hdf5

Save/Load models using HDF5 files
use_implementation

Select a Keras implementation and backend
k_stop_gradient

Returns variables but with zero gradient w.r.t. every other variable.
k_spatial_2d_padding

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

Categorical crossentropy with integer targets.
k_sin

Computes sin of x element-wise.
k_softmax

Softmax of a tensor.
k_random_uniform_variable

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

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

Apply multiplicative 1-centered Gaussian noise.
k_update_add

Update the value of x by adding increment.
layer_zero_padding_3d

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

Update the value of x by subtracting decrement.
layer_gaussian_noise

Apply additive zero-centered Gaussian noise.
layer_multiply

Layer that multiplies (element-wise) a list of inputs.
layer_global_max_pooling_1d

Global max pooling operation for temporal data.
layer_global_average_pooling_3d

Global Average pooling operation for 3D data.
layer_batch_normalization

Batch normalization layer (Ioffe and Szegedy, 2014).
layer_concatenate

Layer that concatenates a list of inputs.
layer_conv_3d_transpose

Transposed 3D convolution layer (sometimes called Deconvolution).
layer_conv_lstm_2d

Convolutional LSTM.
layer_dot

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

Applies Dropout to the input.
plot.keras_training_history

Plot training history
optimizer_nadam

Nesterov Adam optimizer
skipgrams

Generates skipgram word pairs.
pop_layer

Remove the last layer in a model
layer_gru

Gated Recurrent Unit - Cho et al.
make_sampling_table

Generates a word rank-based probabilistic sampling table.
layer_input

Input layer
layer_reshape

Reshapes an output to a certain shape.
layer_repeat_vector

Repeats the input n times.
metric_binary_accuracy

Model performance metrics
layer_permute

Permute the dimensions of an input according to a given pattern
layer_upsampling_1d

Upsampling layer for 1D inputs.
model_from_saved_model

Load a Keras model from the Saved Model format
layer_subtract

Layer that subtracts two inputs.
model_to_json

Model configuration as JSON
texts_to_sequences_generator

Transforms each text in texts in a sequence of integers.
%<-%

Assign values to names
multi_gpu_model

Replicates a model on different GPUs.
loss_mean_squared_error

Model loss functions
normalize

Normalize a matrix or nd-array
optimizer_adagrad

Adagrad optimizer.
optimizer_adam

Adam optimizer
reexports

Objects exported from other packages
regularizer_l1

L1 and L2 regularization
save_model_tf

Save/Load models using SavedModel format
time_distributed

Apply a layer to every temporal slice of an input.
with_custom_object_scope

Provide a scope with mappings of names to custom objects
optimizer_adadelta

Adadelta optimizer.
save_model_weights_hdf5

Save/Load model weights using HDF5 files
text_hashing_trick

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

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

Pads sequences to the same length
texts_to_sequences

Transform each text in texts in a sequence of integers.
summary.keras.engine.training.Model

Print a summary of a Keras model
texts_to_matrix

Convert a list of texts to a matrix.
%>%

Pipe operator
sequences_to_matrix

Convert a list of sequences into a matrix.
serialize_model

Serialize a model to an R object
timeseries_generator

Utility function for generating batches of temporal data.
to_categorical

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