Learn R Programming

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

keras (version 2.0.9)

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

25,525

Version

2.0.9

License

MIT + file LICENSE

Maintainer

JJ Allaire

Last Published

November 17th, 2017

Functions in keras (2.0.9)

application_inception_v3

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

application_vgg

VGG16 and VGG19 models for Keras.

callback_progbar_logger

Callback that prints metrics to stdout.

application_mobilenet

MobileNet model architecture.

callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.

Base R6 class for Keras callbacks

callback_learning_rate_scheduler

Learning rate scheduler.

callback_model_checkpoint

Save the model after every epoch.

Base R6 class for Keras layers

callback_early_stopping

Stop training when a monitored quantity has stopped improving.

application_xception

Xception V1 model for Keras.

callback_lambda

Create a custom callback

Keras backend tensor engine

Bidirectional wrapper for RNNs.

callback_csv_logger

Callback that streams epoch results to a csv file

activation_relu

Activation functions

Configure a Keras model for training

application_inception_resnet_v2

Inception-ResNet v2 model, with weights trained on ImageNet

constraint_maxnorm

MaxNorm weight constraint

callback_terminate_on_naan

Callback that terminates training when a NaN loss is encountered.

MNIST database of handwritten digits

Clone a model instance.

dataset_reuters

Reuters newswire topics classification

Retreive the next item from a generator

callback_remote_monitor

Callback used to stream events to a server.

Layer/Model configuration

callback_tensorboard

TensorBoard basic visualizations

constraint_minmaxnorm

MinMaxNorm weight constraint

Create a Keras Layer

constraint_nonneg

NonNeg weight constraint

constraint_unitnorm

UnitNorm weight constraint

dataset_fashion_mnist

Fashion-MNIST database of fashion articles

Count the total number of scalars composing the weights.

IMDB Movie reviews sentiment classification

evaluate.keras.engine.training.Model

Evaluate a Keras model

dataset_boston_housing

Boston housing price regression dataset

dataset_cifar10

CIFAR10 small image classification

evaluate_generator

Evaluates the model on a data generator.

dataset_cifar100

CIFAR100 small image classification

flow_images_from_directory

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

export_savedmodel.keras.engine.training.Model

Export a Saved Model

Train a Keras model

Freeze and unfreeze weights

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

Loads an image into PIL format.

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

Retrieve tensors for layers with multiple nodes

fit_image_data_generator

Fit image data generator internal statistics to some sample data.

imagenet_decode_predictions

Decodes the prediction of an ImageNet model.

Keras implementation

imagenet_preprocess_input

Preprocesses a tensor encoding a batch of images.

initializer_lecun_uniform

LeCun uniform initializer.

initializer_constant

Initializer that generates tensors initialized to a constant value.

fit_text_tokenizer

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

initializer_identity

Initializer that generates the identity matrix.

flow_images_from_data

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

initializer_lecun_normal

LeCun normal initializer.

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

3D array representation of images

initializer_ones

Initializer that generates tensors initialized to 1.

initializer_he_normal

He normal initializer.

initializer_variance_scaling

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

initializer_he_uniform

He uniform variance scaling initializer.

R interface to Keras

initializer_zeros

Initializer that generates tensors initialized to 0.

layer_activity_regularization

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

layer_batch_normalization

Batch normalization layer (Ioffe and Szegedy, 2014).

layer_activation_thresholded_relu

Thresholded Rectified Linear Unit.

layer_concatenate

Layer that concatenates a list of inputs.

layer_conv_lstm_2d

Convolutional LSTM.

initializer_random_uniform

Initializer that generates tensors with a uniform distribution.

layer_cropping_3d

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

initializer_truncated_normal

Initializer that generates a truncated normal distribution.

layer_cudnn_gru

Fast GRU implementation backed by CuDNN.

layer_activation

Apply an activation function to an output.

layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.

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

layer_activation_elu

Exponential Linear Unit.

image_data_generator

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

layer_conv_3d_transpose

Transposed 3D convolution layer (sometimes called Deconvolution).

initializer_orthogonal

Initializer that generates a random orthogonal matrix.

layer_cropping_1d

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

Layer/Model weights as R arrays

layer_cropping_2d

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

initializer_glorot_normal

Glorot normal initializer, also called Xavier normal initializer.

layer_global_max_pooling_2d

Global max pooling operation for spatial data.

layer_gaussian_noise

Apply additive zero-centered Gaussian noise.

initializer_glorot_uniform

Glorot uniform initializer, also called Xavier uniform initializer.

layer_max_pooling_2d

Max pooling operation for spatial data.

Install Keras and the TensorFlow backend

layer_max_pooling_3d

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

application_resnet50

ResNet50 model for Keras.

Keras array object

layer_global_max_pooling_3d

Global Max pooling operation for 3D data.

layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit.

Wraps arbitrary expression as a layer

layer_activation_parametric_relu

Parametric Rectified Linear Unit.

layer_locally_connected_1d

Locally-connected layer for 1D inputs.

is_keras_available

Check if Keras is Available

layer_average_pooling_2d

Average pooling operation for spatial data.

Layer that averages a list of inputs.

layer_average_pooling_3d

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

layer_average_pooling_1d

Average pooling for temporal data.

layer_conv_2d_transpose

Transposed 2D convolution layer (sometimes called Deconvolution).

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

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

Permute the dimensions of an input according to a given pattern

layer_cudnn_lstm

Fast LSTM implementation backed by CuDNN.

loss_mean_squared_error

Model loss functions

optimizer_adadelta

Adadelta optimizer.

optimizer_adagrad

Adagrad optimizer.

make_sampling_table

Generates a word rank-based probabilistic sampling table.

Generates probability or class probability predictions for the input samples.

Add a densely-connected NN layer to an output

Objects exported from other packages

layer_global_average_pooling_3d

Global Average pooling operation for 3D data.

summary.keras.engine.training.Model

Print a summary of a Keras model

text_hashing_trick

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

layer_global_max_pooling_1d

Global max pooling operation for temporal data.

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

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

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

layer_max_pooling_1d

Max pooling operation for temporal data.

Applies Dropout to the input.

layer_spatial_dropout_3d

Spatial 3D version of Dropout.

layer_global_average_pooling_1d

Global average pooling operation for temporal data.

initializer_random_normal

Initializer that generates tensors with a normal distribution.

Layer that subtracts two inputs.

metric_binary_accuracy

Model performance metrics

keras_model_sequential

Keras Model composed of a linear stack of layers

Layer that adds a list of inputs.

Model configuration as JSON

optimizer_nadam

Nesterov Adam optimizer

layer_global_average_pooling_2d

Global average pooling operation for spatial data.

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

optimizer_rmsprop

RMSProp optimizer

Remove the last layer in a model

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

layer_alpha_dropout

Applies Alpha Dropout to the input.

layer_repeat_vector

Repeats the input n times.

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

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

Reshapes an output to a certain shape.

optimizer_adamax

Adamax optimizer

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).

plot.keras_training_history

Plot training history

layer_embedding

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

Flattens an input

text_to_word_sequence

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

Gated Recurrent Unit - Cho et al.

Long-Short Term Memory unit - Hochreiter 1997.

layer_locally_connected_2d

Locally-connected layer for 2D inputs.

layer_separable_conv_2d

Depthwise separable 2D convolution.

predict.keras.engine.training.Model

Generate predictions from a Keras model

save_model_hdf5

Save/Load models using HDF5 files

layer_simple_rnn

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

save_model_weights_hdf5

Save/Load model weights using HDF5 files

layer_upsampling_3d

Upsampling layer for 3D inputs.

layer_spatial_dropout_1d

Spatial 1D version of Dropout.

layer_spatial_dropout_2d

Spatial 2D version of Dropout.

layer_zero_padding_1d

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

layer_upsampling_1d

Upsampling layer for 1D inputs.

Text tokenization utility

save_text_tokenizer

Save a text tokenizer to an external file

texts_to_matrix

Convert a list of texts to a matrix.

sequences_to_matrix

Convert a list of sequences into a matrix.

serialize_model

Serialize a model to an R object

Generates skipgram word pairs.

time_distributed

Apply a layer to every temporal slice of an input.

texts_to_sequences

Transform each text in texts in a sequence of integers.

layer_upsampling_2d

Upsampling layer for 2D inputs.

texts_to_sequences_generator

Transforms each text in texts in a sequence of integers.

multi_gpu_model

Replicates a model on different GPUs.

Model configuration as YAML

Normalize a matrix or nd-array

Assign values to names

predict_generator

Generates predictions for the input samples from a data generator.

predict_on_batch

Returns predictions for a single batch of samples.

Stochastic gradient descent optimizer

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

L1 and L2 regularization

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

Reset the states for a layer

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