Learn R Programming

⚠️There's a newer version (2.13.0) of this package.Take me there.

keras (version 2.0.8)

R Interface to 'Keras'

Description

Interface to 'Keras' , a high-level neural networks API. 'Keras' was developed with a focus on enabling fast experimentation, supports both convolution based networks and recurrent networks (as well as combinations of the two), and runs seamlessly on both 'CPU' and 'GPU' devices.

Copy Link

Version

Install

install.packages('keras')

Monthly Downloads

30,713

Version

2.0.8

License

MIT + file LICENSE

Maintainer

JJ Allaire

Last Published

September 30th, 2017

Functions in keras (2.0.8)

callback_remote_monitor

Callback used to stream events to a server.

constraint_maxnorm

MaxNorm weight constraint

constraint_minmaxnorm

MinMaxNorm weight constraint

Train a Keras model

Fits the model on data yielded batch-by-batch by a generator.

flow_images_from_data

Generates batches of augmented/normalized data from image data and labels

flow_images_from_directory

Generates batches of data from images in a directory (with optional augmented/normalized data)

initializer_he_uniform

He uniform variance scaling initializer.

initializer_identity

Initializer that generates the identity matrix.

initializer_ones

Initializer that generates tensors initialized to 1.

initializer_orthogonal

Initializer that generates a random orthogonal matrix.

is_keras_available

Check if Keras is Available

R interface to Keras

layer_alpha_dropout

Applies Alpha Dropout to the input.

application_xception

Xception V1 model for Keras.

callback_model_checkpoint

Save the model after every epoch.

callback_progbar_logger

Callback that prints metrics to stdout.

application_vgg

VGG16 and VGG19 models for Keras.

Count the total number of scalars composing the weights.

Create a Keras Layer

MNIST database of handwritten digits

dataset_reuters

Reuters newswire topics classification

Layer/Model weights as R arrays

Representation of HDF5 dataset to be used instead of an R array

imagenet_preprocess_input

Preprocesses a tensor encoding a batch of images.

Keras implementation

initializer_truncated_normal

Initializer that generates a truncated normal distribution.

initializer_variance_scaling

Initializer capable of adapting its scale to the shape of weights.

layer_activation_elu

Exponential Linear Unit.

layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit.

layer_concatenate

Layer that concatenates a list of inputs.

1D convolution layer (e.g. temporal convolution).

Add a densely-connected NN layer to an output

Layer that computes a dot product between samples in two tensors.

Layer that averages a list of inputs.

3D convolution layer (e.g. spatial convolution over volumes).

layer_conv_3d_transpose

Transposed 3D convolution layer (sometimes called Deconvolution).

layer_global_max_pooling_1d

Global max pooling operation for temporal data.

layer_global_max_pooling_2d

Global max pooling operation for spatial data.

Wraps arbitrary expression as a layer

Layer that multiplies (element-wise) a list of inputs.

Permute the dimensions of an input according to a given pattern

loss_mean_squared_error

Model loss functions

make_sampling_table

Generates a word rank-based probabilistic sampling table.

Flattens an input

layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.

Long-Short Term Memory unit - Hochreiter 1997.

metric_binary_accuracy

Model performance metrics

Model configuration as JSON

predict_generator

Generates predictions for the input samples from a data generator.

predict_on_batch

Returns predictions for a single batch of samples.

Generates skipgram word pairs.

summary.keras.engine.training.Model

Print a summary of a Keras model

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

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

layer_repeat_vector

Repeats the input n times.

Reshapes an output to a certain shape.

layer_zero_padding_2d

Zero-padding layer for 2D input (e.g. picture).

layer_zero_padding_3d

Zero-padding layer for 3D data (spatial or spatio-temporal).

Single gradient update or model evaluation over one batch of samples.

optimizer_adadelta

Adadelta optimizer.

optimizer_adagrad

Adagrad optimizer.

Remove the last layer in a model

predict.keras.engine.training.Model

Generate predictions from a Keras model

sequences_to_matrix

Convert a list of sequences into a matrix.

serialize_model

Serialize a model to an R object

text_to_word_sequence

Convert text to a sequence of words (or tokens).

Text tokenization utility

activation_relu

Activation functions

application_inception_v3

Inception V3 model, with weights pre-trained on ImageNet.

callback_lambda

Create a custom callback

callback_learning_rate_scheduler

Learning rate scheduler.

constraint_nonneg

NonNeg weight constraint

constraint_unitnorm

UnitNorm weight constraint

fit_image_data_generator

Fit image data generator internal statistics to some sample data.

fit_text_tokenizer

Update tokenizer internal vocabulary based on a list of texts or list of sequences.

initializer_glorot_uniform

Glorot uniform initializer, also called Xavier uniform initializer.

initializer_he_normal

He normal initializer.

initializer_lecun_normal

LeCun normal initializer.

initializer_lecun_uniform

LeCun uniform initializer.

Keras array object

layer_cropping_2d

Cropping layer for 2D input (e.g. picture).

layer_cropping_3d

Cropping layer for 3D data (e.g. spatial or spatio-temporal).

initializer_zeros

Initializer that generates tensors initialized to 0.

layer_separable_conv_2d

Depthwise separable 2D convolution.

layer_simple_rnn

Fully-connected RNN where the output is to be fed back to input.

optimizer_adamax

Adamax optimizer

Generates probability or class probability predictions for the input samples.

Objects exported from other packages

Install Keras and the TensorFlow backend

layer_average_pooling_1d

Average pooling for temporal data.

layer_average_pooling_2d

Average pooling operation for spatial data.

layer_conv_lstm_2d

Convolutional LSTM.

layer_cropping_1d

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

Applies Dropout to the input.

layer_embedding

Turns positive integers (indexes) into dense vectors of fixed size.

application_mobilenet

MobileNet model architecture.

application_resnet50

ResNet50 model for Keras.

layer_spatial_dropout_1d

Spatial 1D version of Dropout.

layer_spatial_dropout_2d

Spatial 2D version of Dropout.

layer_spatial_dropout_3d

Spatial 3D version of Dropout.

image_data_generator

Generate minibatches of image data with real-time data augmentation.

Loads an image into PIL format.

layer_upsampling_3d

Upsampling layer for 3D inputs.

Layer that subtracts two inputs.

Stochastic gradient descent optimizer

Pads each sequence to the same length (length of the longest sequence).

layer_zero_padding_1d

Zero-padding layer for 1D input (e.g. temporal sequence).

texts_to_matrix

Convert a list of texts to a matrix.

texts_to_sequences

Transform each text in texts in a sequence of integers.

text_hashing_trick

Converts a text to a sequence of indexes in a fixed-size hashing space.

One-hot encode a text into a list of word indexes in a vocabulary of size n.

Base R6 class for Keras callbacks

Base R6 class for Keras layers

callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.

2D convolution layer (e.g. spatial convolution over images).

layer_conv_2d_transpose

Transposed 2D convolution layer (sometimes called Deconvolution).

layer_gaussian_noise

Apply additive zero-centered Gaussian noise.

layer_global_average_pooling_1d

Global average pooling operation for temporal data.

layer_locally_connected_1d

Locally-connected layer for 1D inputs.

layer_locally_connected_2d

Locally-connected layer for 2D inputs.

save_model_hdf5

Save/Load models using HDF5 files

save_model_weights_hdf5

Save/Load model weights using HDF5 files

callback_csv_logger

Callback that streams epoch results to a csv file

callback_early_stopping

Stop training when a monitored quantity has stopped improving.

Clone a model instance.

Configure a Keras model for training

initializer_constant

Initializer that generates tensors initialized to a constant value.

initializer_glorot_normal

Glorot normal initializer, also called Xavier normal initializer.

layer_average_pooling_3d

Average pooling operation for 3D data (spatial or spatio-temporal).

layer_batch_normalization

Batch normalization layer (Ioffe and Szegedy, 2014).

Keras backend tensor engine

Bidirectional wrapper for RNNs.

callback_tensorboard

TensorBoard basic visualizations

callback_terminate_on_naan

Callback that terminates training when a NaN loss is encountered.

dataset_boston_housing

Boston housing price regression dataset

dataset_cifar10

CIFAR10 small image classification

dataset_cifar100

CIFAR100 small image classification

IMDB Movie reviews sentiment classification

Layer/Model configuration

Downloads a file from a URL if it not already in the cache.

Converts a PIL Image instance to a 3d-array.

imagenet_decode_predictions

Decodes the prediction of an ImageNet model.

layer_activation_parametric_relu

Parametric Rectified Linear Unit.

Evaluate a Keras model

evaluate_generator

Evaluates the model on a data generator.

layer_activation_thresholded_relu

Thresholded Rectified Linear Unit.

layer_global_average_pooling_2d

Global average pooling operation for spatial data.

layer_global_average_pooling_3d

Global Average pooling operation for 3D data.

layer_global_max_pooling_3d

Global Max pooling operation for 3D data.

Retrieve tensors for layers with multiple nodes

Retrieves a layer based on either its name (unique) or index.

Gated Recurrent Unit - Cho et al.

initializer_random_normal

Initializer that generates tensors with a normal distribution.

initializer_random_uniform

Initializer that generates tensors with a uniform distribution.

keras_model_sequential

Keras Model composed of a linear stack of layers

layer_activation

Apply an activation function to an output.

layer_activity_regularization

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

Layer that adds a list of inputs.

optimizer_nadam

Nesterov Adam optimizer

optimizer_rmsprop

RMSProp optimizer

layer_max_pooling_1d

Max pooling operation for temporal data.

layer_max_pooling_2d

Max pooling operation for spatial data.

layer_max_pooling_3d

Max pooling operation for 3D data (spatial or spatio-temporal).

Layer that computes the maximum (element-wise) a list of inputs.

layer_upsampling_1d

Upsampling layer for 1D inputs.

layer_upsampling_2d

Upsampling layer for 2D inputs.

Model configuration as YAML

Normalize a matrix or nd-array

plot.keras_training_history

Plot training history

L1 and L2 regularization

Reset the states for a layer

texts_to_sequences_generator

Transforms each text in texts in a sequence of integers.

time_distributed

Apply a layer to every temporal slice of an input.