kerasR: R Interface to the Keras Deep Learning Library

Provides a consistent interface to the 'Keras' Deep Learning Library directly from within R. 'Keras' (see <https://keras.io/> for more information) provides specifications for describing dense neural networks, convolution neural networks (CNN) and recurrent neural networks (RNN) running on top of either 'TensorFlow' (<https://www.tensorflow.org/>) or 'Theano' (<http://deeplearning.net/software/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.

Install the latest version of this package by entering the following in R:
install.packages("kerasR")
AuthorTaylor Arnold [aut, cre]
Date of publication2017-03-20 17:34:39 UTC
MaintainerTaylor Arnold <taylor.arnold@acm.org>
LicenseLGPL-2
Version0.4.1
https://github.com/statsmaths/kerasR

View on CRAN

Man pages

Activation: Applies an activation function to an output.

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

AdvancedActivation: Advanced activation layers

Applications: Load pre-trained models

AveragePooling: Average pooling operation

BatchNormalization: Batch normalization layer

Constraints: Apply penalties on layer parameters

Conv: Convolution layers

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

CSVLogger: Callback that streams epoch results to a csv file.

Datasets: Load datasets

decode_predictions: Decode predictions from pre-defined imagenet networks

Dense: Regular, densely-connected NN layer.

Dropout: Applies Dropout to the input.

EarlyStopping: Stop training when a monitored quantity has stopped...

Embedding: Embedding layer

expand_dims: Expand dimensions of an array

Flatten: Flattens the input. Does not affect the batch size.

GaussianNoise: Apply Gaussian noise layer

GlobalPooling: Global pooling operations

img_to_array: Converts a PIL Image instance to a Numpy array.

Initalizers: Define the way to set the initial random weights of Keras...

keras_compile: Compile a keras model

keras_fit: Fit a keras model

kerasR: Keras Models in R

LayerWrapper: Layer wrappers

load_img: Load image from a file as PIL object

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.

normalize: Normalize a Numpy array.

one_hot: One-hot encode a text into a list of word indexes in a...

Optimizers: Optimizers

pad_sequences: Pad a linear sequence for an RNN input

Permute: Permutes the dimensions of the input according to a given...

plot_model: Plot model architecture to a file

Predict: Predict values from a keras model

preprocess_input: Preprocess input for pre-defined imagenet networks

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.

RNN: Recurrent neural network layers

run_examples: Should examples be run on this system

Sequential: Initialize sequential model

TensorBoard: Tensorboard basic visualizations.

text_to_word_sequence: Split a sentence into a list of words.

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

Tokenizer: Tokenizer

UpSampling: UpSampling layers.

ZeroPadding: Zero-padding layers

Functions

Activation Man page
ActivityRegularization Man page
Adadelta Man page
Adagrad Man page
Adam Man page
Adamax Man page
AdvancedActivation Man page
Applications Man page
AveragePooling Man page
AveragePooling1D Man page
AveragePooling2D Man page
AveragePooling3D Man page
BatchNormalization Man page
Bidirectional Man page
Constant Man page
Constraints Man page
Conv Man page
Conv1D Man page
Conv2D Man page
Conv2DTranspose Man page
Conv3D Man page
Cropping Man page
Cropping1D Man page
Cropping2D Man page
Cropping3D Man page
CSVLogger Man page
Datasets Man page
decode_predictions Man page
Dense Man page
Dropout Man page
EarlyStopping Man page
ELU Man page
Embedding Man page
expand_dims Man page
Flatten Man page
GaussianDropout Man page
GaussianNoise Man page
GlobalAveragePooling1D Man page
GlobalAveragePooling2D Man page
GlobalMaxPooling1D Man page
GlobalMaxPooling2D Man page
GlobalPooling Man page
glorot_normal Man page
glorot_uniform Man page
GRU Man page
he_normal Man page
he_uniform Man page
Identity Man page
img_to_array Man page
InceptionV3 Man page
Initalizers Man page
keras_compile Man page
keras_fit Man page
keras_load Man page
keras_load_weights Man page
keras_model_from_json Man page
keras_model_to_json Man page
keras_predict Man page
keras_predict_classes Man page
keras_predict_proba Man page
kerasR Man page
kerasR-package Man page
keras_save Man page
keras_save_weights Man page
l1 Man page
l1_l2 Man page
l2 Man page
LayerWrapper Man page
LeakyReLU Man page
lecun_uniform Man page
load_boston_housing Man page
load_cifar10 Man page
load_cifar100 Man page
load_imdb Man page
load_img Man page
load_mnist Man page
load_reuters Man page
LoadSave Man page
LocallyConnected Man page
LocallyConnected1D Man page
LocallyConnected2D Man page
LSTM Man page
Masking Man page
max_norm Man page
MaxPooling Man page
MaxPooling1D Man page
MaxPooling2D Man page
MaxPooling3D Man page
ModelCheckpoint Man page
Nadam Man page
non_neg Man page
normalize Man page
one_hot Man page
Ones Man page
Optimizers Man page
Orthogonal Man page
pad_sequences Man page
Permute Man page
plot_model Man page
Predict Man page
PReLU Man page
preprocess_input Man page
RandomNormal Man page
RandomUniform Man page
ReduceLROnPlateau Man page
Regularizers Man page
RepeatVector Man page
Reshape Man page
ResNet50 Man page
RMSprop Man page
RNN Man page
run_examples Man page
SeparableConv2D Man page
Sequential Man page
SGD Man page
SimpleRNN Man page
TensorBoard Man page
text_to_word_sequence Man page
ThresholdedReLU Man page
TimeDistributed Man page
to_categorical Man page
Tokenizer Man page
TruncatedNormal Man page
unit_norm Man page
UpSampling Man page
UpSampling1D Man page
UpSampling2D Man page
UpSampling3D Man page
VarianceScaling Man page
VGG16 Man page
VGG19 Man page
Xception Man page
ZeroPadding Man page
ZeroPadding1D Man page
ZeroPadding2D Man page
ZeroPadding3D Man page
Zeros Man page

Files

inst
inst/doc
inst/doc/introduction.R
inst/doc/introduction.html
inst/doc/introduction.Rmd
NAMESPACE
R
R/preprocessing.R R/utils.R R/models.R R/applications.R R/onLoad.R R/initalizers.R R/layers.local.R R/layers.noise.R R/layers.core.R R/optimizers.R R/kerasR-package.R R/layers.embeddings.R R/layers.wrappers.R R/regularizers.R R/layers.advanced_activations.R R/layers.recurrent.R R/layers.normalization.R R/constraints.R R/callbacks.R R/layers.pooling.R R/datasets.R R/zzz.R R/layers.convolutional.R
vignettes
vignettes/elephant.jpg
vignettes/introduction.Rmd
README.md
MD5
build
build/vignette.rds
DESCRIPTION
man
man/img_to_array.Rd man/one_hot.Rd man/Predict.Rd man/Constraints.Rd man/CSVLogger.Rd man/UpSampling.Rd man/RepeatVector.Rd man/keras_compile.Rd man/Initalizers.Rd man/Permute.Rd man/ModelCheckpoint.Rd man/Applications.Rd man/Embedding.Rd man/keras_fit.Rd man/AdvancedActivation.Rd man/AveragePooling.Rd man/Dense.Rd man/EarlyStopping.Rd man/ActivityRegularization.Rd man/Optimizers.Rd man/ZeroPadding.Rd man/Cropping.Rd man/ReduceLROnPlateau.Rd man/Dropout.Rd man/decode_predictions.Rd man/Datasets.Rd man/pad_sequences.Rd man/Tokenizer.Rd man/expand_dims.Rd man/LoadSave.Rd man/Sequential.Rd man/run_examples.Rd man/kerasR.Rd man/Masking.Rd man/Regularizers.Rd man/LayerWrapper.Rd man/Conv.Rd man/load_img.Rd man/GlobalPooling.Rd man/text_to_word_sequence.Rd man/BatchNormalization.Rd man/normalize.Rd man/Activation.Rd man/TensorBoard.Rd man/Reshape.Rd man/MaxPooling.Rd man/LocallyConnected.Rd man/GaussianNoise.Rd man/RNN.Rd man/plot_model.Rd man/Flatten.Rd man/preprocess_input.Rd man/to_categorical.Rd

Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.