Man pages for kerasR
R Interface to the Keras Deep Learning Library

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_available	Tests if keras is available on the system.
keras_check	Called to check if keras is installed and loaded
keras_compile	Compile a keras model
keras_fit	Fit a keras model
keras_init	Initialise connection to the keras python libraries.
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
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
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