R Interface to the Keras Deep Learning Library


[Up] [Top]

Documentation for package ‘kerasR’ version 0.6.1

Help Pages

A B C D E F G H I K L M N O P R S T U V X Z

kerasR-package Keras Models in R

-- A --

Activation Applies an activation function to an output.
ActivityRegularization Layer that applies an update to the cost function based input activity.
Adadelta Optimizers
Adagrad Optimizers
Adam Optimizers
Adamax Optimizers
AdvancedActivation Advanced activation layers
Applications Load pre-trained models
AveragePooling Average pooling operation
AveragePooling1D Average pooling operation
AveragePooling2D Average pooling operation
AveragePooling3D Average pooling operation

-- B --

BatchNormalization Batch normalization layer
Bidirectional Layer wrappers

-- C --

Constant Define the way to set the initial random weights of Keras layers.
Constraints Apply penalties on layer parameters
Conv Convolution layers
Conv1D Convolution layers
Conv2D Convolution layers
Conv2DTranspose Convolution layers
Conv3D Convolution layers
Cropping Cropping layers for 1D input (e.g. temporal sequence).
Cropping1D Cropping layers for 1D input (e.g. temporal sequence).
Cropping2D Cropping layers for 1D input (e.g. temporal sequence).
Cropping3D Cropping layers for 1D input (e.g. temporal sequence).
CSVLogger Callback that streams epoch results to a csv file.

-- D --

Datasets Load datasets
decode_predictions Decode predictions from pre-defined imagenet networks
Dense Regular, densely-connected NN layer.
Dropout Applies Dropout to the input.

-- E --

EarlyStopping Stop training when a monitored quantity has stopped improving.
ELU Advanced activation layers
Embedding Embedding layer
expand_dims Expand dimensions of an array

-- F --

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

-- G --

GaussianDropout Apply Gaussian noise layer
GaussianNoise Apply Gaussian noise layer
GlobalAveragePooling1D Global pooling operations
GlobalAveragePooling2D Global pooling operations
GlobalMaxPooling1D Global pooling operations
GlobalMaxPooling2D Global pooling operations
GlobalPooling Global pooling operations
glorot_normal Define the way to set the initial random weights of Keras layers.
glorot_uniform Define the way to set the initial random weights of Keras layers.
GRU Recurrent neural network layers

-- H --

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

-- I --

Identity Define the way to set the initial random weights of Keras layers.
img_to_array Converts a PIL Image instance to a Numpy array.
InceptionV3 Load pre-trained models
Initalizers Define the way to set the initial random weights of Keras layers.

-- K --

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.
keras_load Load and save keras models
keras_load_weights Load and save keras models
keras_model_from_json Load and save keras models
keras_model_to_json Load and save keras models
keras_predict Predict values from a keras model
keras_predict_classes Predict values from a keras model
keras_predict_proba Predict values from a keras model
keras_save Load and save keras models
keras_save_weights Load and save keras models

-- L --

l1 Apply penalties on layer parameters
l1_l2 Apply penalties on layer parameters
l2 Apply penalties on layer parameters
LayerWrapper Layer wrappers
LeakyReLU Advanced activation layers
lecun_uniform Define the way to set the initial random weights of Keras layers.
LoadSave Load and save keras models
load_boston_housing Load datasets
load_cifar10 Load datasets
load_cifar100 Load datasets
load_imdb Load datasets
load_img Load image from a file as PIL object
load_mnist Load datasets
load_reuters Load datasets
LocallyConnected Locally-connected layer
LocallyConnected1D Locally-connected layer
LocallyConnected2D Locally-connected layer
LSTM Recurrent neural network layers

-- M --

Masking Masks a sequence by using a mask value to skip timesteps.
MaxPooling Max pooling operations
MaxPooling1D Max pooling operations
MaxPooling2D Max pooling operations
MaxPooling3D Max pooling operations
max_norm Apply penalties on layer parameters
ModelCheckpoint Save the model after every epoch.

-- N --

Nadam Optimizers
non_neg Apply penalties on layer parameters
normalize Normalize a Numpy array.

-- O --

Ones Define the way to set the initial random weights of Keras layers.
one_hot One-hot encode a text into a list of word indexes
Optimizers Optimizers
Orthogonal Define the way to set the initial random weights of Keras layers.

-- P --

pad_sequences Pad a linear sequence for an RNN input
Permute Permutes the dimensions of the input according to a given pattern.
plot_model Plot model architecture to a file
Predict Predict values from a keras model
PReLU Advanced activation layers
preprocess_input Preprocess input for pre-defined imagenet networks

-- R --

RandomNormal Define the way to set the initial random weights of Keras layers.
RandomUniform Define the way to set the initial random weights of Keras 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.
ResNet50 Load pre-trained models
RMSprop Optimizers
RNN Recurrent neural network layers
run_examples Should examples be run on this system

-- S --

SeparableConv2D Convolution layers
Sequential Initialize sequential model
SGD Optimizers
SimpleRNN Recurrent neural network layers

-- T --

TensorBoard Tensorboard basic visualizations.
text_to_word_sequence Split a sentence into a list of words.
ThresholdedReLU Advanced activation layers
TimeDistributed Layer wrappers
Tokenizer Tokenizer
to_categorical Converts a class vector (integers) to binary class matrix.
TruncatedNormal Define the way to set the initial random weights of Keras layers.

-- U --

unit_norm Apply penalties on layer parameters
UpSampling UpSampling layers.
UpSampling1D UpSampling layers.
UpSampling2D UpSampling layers.
UpSampling3D UpSampling layers.

-- V --

VarianceScaling Define the way to set the initial random weights of Keras layers.
VGG16 Load pre-trained models
VGG19 Load pre-trained models

-- X --

Xception Load pre-trained models

-- Z --

ZeroPadding Zero-padding layers
ZeroPadding1D Zero-padding layers
ZeroPadding2D Zero-padding layers
ZeroPadding3D Zero-padding layers
Zeros Define the way to set the initial random weights of Keras layers.