Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

kerasR

R Interface to the Keras Deep Learning Library

Provides a consistent interface to the 'Keras' Deep Learning Library directly from within R. 'Keras' provides specifications for describing dense neural networks, convolution neural networks (CNN) and recurrent neural networks (RNN) running on top of either 'TensorFlow' or 'Theano'. Type conversions between Python and R are automatically handled correctly, even when the default choices would otherwise lead to errors. Includes complete R documentation and many working examples.

Functions (55)

Activation

Applies an activation function to an output.

ActivityRegularization

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

AdvancedActivation

Advanced activation layers

Applications

Load pre-trained models

AveragePooling

Average pooling operation

BatchNormalization

Batch normalization layer

CSVLogger

Callback that streams epoch results to a csv file.

Constraints

Apply penalties on layer parameters

Conv

Convolution layers

Cropping

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

Datasets

Load datasets

Dense

Regular, densely-connected NN layer.

Dropout

Applies Dropout to the input.

EarlyStopping

Stop training when a monitored quantity has stopped improving.

Embedding

Embedding layer

Flatten

Flattens the input. Does not affect the batch size.

GaussianNoise

Apply Gaussian noise layer

GlobalPooling

Global pooling operations

Initalizers

Define the way to set the initial random weights of Keras layers.

LayerWrapper

Layer wrappers

LoadSave

Load and save keras models

LocallyConnected

Locally-connected layer

Masking

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

MaxPooling

Max pooling operations

ModelCheckpoint

Save the model after every epoch.

Optimizers

Optimizers

Permute

Permutes the dimensions of the input according to a given pattern.

Predict

Predict values from a keras model

RNN

Recurrent neural network layers

ReduceLROnPlateau

Reduce learning rate when a metric has stopped improving.

Regularizers

Apply penalties on layer parameters

RepeatVector

Repeats the input n times.

Reshape

Reshapes an output to a certain shape.

Sequential

Initialize sequential model

TensorBoard

Tensorboard basic visualizations.

Tokenizer

Tokenizer

UpSampling

UpSampling layers.

ZeroPadding

Zero-padding layers

decode_predictions

Decode predictions from pre-defined imagenet networks

expand_dims

Expand dimensions of an array

img_to_array

Converts a PIL Image instance to a Numpy array.

kerasR

Keras Models in R

keras_available

Tests if keras is available on the system.

keras_compile

Compile a keras model

keras_fit

Fit a keras model

keras_init

Initialise connection to the keras python libraries.

load_img

Load image from a file as PIL object

normalize

Normalize a Numpy array.

one_hot

One-hot encode a text into a list of word indexes

pad_sequences

Pad a linear sequence for an RNN input

plot_model

Plot model architecture to a file

preprocess_input

Preprocess input for pre-defined imagenet networks

run_examples

Should examples be run on this system

text_to_word_sequence

Split a sentence into a list of words.

to_categorical

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

kerasR

R Interface to the Keras Deep Learning Library

v0.6.1

LGPL-2

Authors

Taylor Arnold [aut, cre]

Initial release

kerasR

Functions (55)

kerasR

We don't support your browser anymore