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.
