Learn R Programming

⚠️There's a newer version (2.16.0) of this package.Take me there.

keras (version 2.1.2)

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

17,691

Version

2.1.2

License

MIT + file LICENSE

Maintainer

JJ Allaire

Last Published

December 17th, 2017

Functions in keras (2.1.2)

application_mobilenet

MobileNet model architecture.

application_inception_v3

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

Keras backend tensor engine

application_xception

Xception V1 model for Keras.

Base R6 class for Keras callbacks

Base R6 class for Keras layers

activation_relu

Activation functions

callback_early_stopping

Stop training when a monitored quantity has stopped improving.

application_inception_resnet_v2

Inception-ResNet v2 model, with weights trained on ImageNet

callback_lambda

Create a custom callback

callback_learning_rate_scheduler

Learning rate scheduler.

callback_terminate_on_naan

Callback that terminates training when a NaN loss is encountered.

callback_model_checkpoint

Save the model after every epoch.

callback_remote_monitor

Callback used to stream events to a server.

Clone a model instance.

callback_tensorboard

TensorBoard basic visualizations

constraint_maxnorm

MaxNorm weight constraint

Create a Keras Layer

dataset_boston_housing

Boston housing price regression dataset

export_savedmodel.keras.engine.training.Model

Export a Saved Model

application_resnet50

ResNet50 model for Keras.

Train a Keras model

application_vgg

VGG16 and VGG19 models for Keras.

Bidirectional wrapper for RNNs.

dataset_fashion_mnist

Fashion-MNIST database of fashion articles

callback_csv_logger

Callback that streams epoch results to a csv file

IMDB Movie reviews sentiment classification

Configure a Keras model for training

Retreive the next item from a generator

constraint_minmaxnorm

MinMaxNorm weight constraint

constraint_nonneg

NonNeg weight constraint

Layer/Model configuration

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

callback_progbar_logger

Callback that prints metrics to stdout.

Retrieve tensors for layers with multiple nodes

Loads an image into PIL format.

callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.

3D array representation of images

constraint_unitnorm

UnitNorm weight constraint

flow_images_from_directory

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

Freeze and unfreeze weights

Count the total number of scalars composing the weights.

imagenet_decode_predictions

Decodes the prediction of an ImageNet model.

evaluate.keras.engine.training.Model

Evaluate a Keras model

imagenet_preprocess_input

Preprocesses a tensor encoding a batch of images.

initializer_orthogonal

Initializer that generates a random orthogonal matrix.

evaluate_generator

Evaluates the model on a data generator.

initializer_random_normal

Initializer that generates tensors with a normal distribution.

fit_text_tokenizer

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

Element-wise absolute value.

Keras implementation

flow_images_from_data

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

initializer_constant

Initializer that generates tensors initialized to a constant value.

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

initializer_he_normal

He normal initializer.

image_data_generator

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

initializer_he_uniform

He uniform variance scaling initializer.

initializer_random_uniform

Initializer that generates tensors with a uniform distribution.

initializer_truncated_normal

Initializer that generates a truncated normal distribution.

MNIST database of handwritten digits

Active Keras backend

dataset_reuters

Reuters newswire topics classification

Batchwise dot product.

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

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

fit_image_data_generator

Fit image data generator internal statistics to some sample data.

Layer/Model weights as R arrays

initializer_glorot_normal

Glorot normal initializer, also called Xavier normal initializer.

dataset_cifar10

CIFAR10 small image classification

initializer_ones

Initializer that generates tensors initialized to 1.

initializer_variance_scaling

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

dataset_cifar100

CIFAR100 small image classification

initializer_zeros

Initializer that generates tensors initialized to 0.

Bitwise reduction (logical OR).

k_batch_flatten

Turn a nD tensor into a 2D tensor with same 1st dimension.

k_batch_get_value

Returns the value of more than one tensor variable.

Creates a 1D tensor containing a sequence of integers.

Creates a constant tensor.

1D convolution.

k_categorical_crossentropy

Categorical crossentropy between an output tensor and a target tensor.

Computes cos of x element-wise.

k_clear_session

Destroys the current TF graph and creates a new one.

initializer_identity

Initializer that generates the identity matrix.

initializer_lecun_normal

LeCun normal initializer.

TF session to be used by the backend.

Adds a bias vector to a tensor.

Get the uid for the default graph.

k_binary_crossentropy

Binary crossentropy between an output tensor and a target tensor.

Returns the shape of tensor or variable as a list of int or NULL entries.

k_in_train_phase

Selects x in train phase, and alt otherwise.

Apply 2D conv with un-shared weights.

Element-wise log.

initializer_lecun_uniform

LeCun uniform initializer.

initializer_glorot_uniform

Glorot uniform initializer, also called Xavier uniform initializer.

Returns the static number of elements in a Keras variable or tensor.

Install Keras and the TensorFlow backend

is_keras_available

Check if Keras is Available

Adds a 1-sized dimension at index axis.

Returns the index of the maximum value along an axis.

Instantiate an identity matrix and returns it.

Returns the index of the minimum value along an axis.

2D convolution.

Returns the value of a variable.

k_conv2d_transpose

2D deconvolution (i.e. transposed convolution).

k_get_variable_shape

Returns the shape of a variable.

Minimum value in a tensor.

Element-wise minimum of two tensors.

Returns a tensor with the same content as the input tensor.

Instantiates a placeholder tensor and returns it.

k_image_data_format

Default image data format convention ('channels_first' or 'channels_last').

k_random_binomial

Returns a tensor with random binomial distribution of values.

Computes log(sum(exp(elements across dimensions of a tensor))).

k_random_normal

Returns a tensor with normal distribution of values.

k_ctc_batch_cost

Runs CTC loss algorithm on each batch element.

k_set_learning_phase

Sets the learning phase to a fixed value.

Decodes the output of a softmax.

Instantiates a Keras function

Retrieves the elements of indices indices in the tensor reference.

Evaluates the value of a variable.

k_in_test_phase

Selects x in test phase, and alt otherwise.

Element-wise exponential.

Element-wise value clipping.

Concatenates a list of tensors alongside the specified axis.

Sets the value of a variable, from an R array.

3D convolution.

Element-wise sign.

Bitwise reduction (logical AND).

k_batch_normalization

Applies batch normalization on x given mean, var, beta and gamma.

Computes sin of x element-wise.

k_batch_set_value

Sets the values of many tensor variables at once.

Removes a 1-dimension from the tensor at index axis.

Casts a tensor to a different dtype and returns it.

Stacks a list of rank R tensors into a rank R+1 tensor.

Cumulative sum of the values in a tensor, alongside the specified axis.

k_depthwise_conv2d

Depthwise 2D convolution with separable filters.

k_cast_to_floatx

Cast an array to the default Keras float type.

Returns the dtype of a Keras tensor or variable, as a string.

k_ctc_label_dense_to_sparse

Converts CTC labels from dense to sparse.

Exponential linear unit.

k_greater_equal

Element-wise truth value of (x >= y).

Cumulative product of the values in a tensor, alongside the specified axis.

Segment-wise linear approximation of sigmoid.

Fuzz factor used in numeric expressions.

Element-wise truth value of (x <= y).

Returns whether the targets are in the top k predictions.

k_conv3d_transpose

3D deconvolution (i.e. transposed convolution).

k_learning_phase

Returns the learning phase flag.

Multiplies 2 tensors (and/or variables) and returns a tensor.

Element-wise truth value of (x < y).

Sets entries in x to zero at random, while scaling the entire tensor.

Apply 1D conv with un-shared weights.

Map the function fn over the elements elems and return the outputs.

Element-wise equality between two tensors.

Maximum value in a tensor.

k_is_keras_tensor

Returns whether x is a Keras tensor.

Reduce elems using fn to combine them from left to right.

k_is_placeholder

Returns whether x is a placeholder.

Reduce elems using fn to combine them from right to left.

Element-wise maximum of two tensors.

Returns the gradients of variables w.r.t. loss.

Prints message and the tensor value when evaluated.

Multiplies the values in a tensor, alongside the specified axis.

Element-wise truth value of (x > y).

Reset graph identifiers.

Mean of a tensor, alongside the specified axis.

k_moving_average_update

Compute the moving average of a variable.

Instantiates an all-ones variable of the same shape as another tensor.

Returns the number of axes in a tensor, as an integer.

k_permute_dimensions

Permutes axes in a tensor.

Computes the one-hot representation of an integer tensor.

k_random_normal_variable

Instantiates a variable with values drawn from a normal distribution.

k_random_uniform_variable

Instantiates a variable with values drawn from a uniform distribution.

Reshapes a tensor to the specified shape.

k_manual_variable_initialization

Sets the manual variable initialization flag.

Softsign of a tensor.

k_sparse_categorical_crossentropy

Categorical crossentropy with integer targets.

k_normalize_batch_in_training

Computes mean and std for batch then apply batch_normalization on batch.

Standard deviation of a tensor, alongside the specified axis.

Element-wise inequality between two tensors.

Rectified linear unit.

Element-wise rounding to the closest integer.

Flatten a tensor.

k_separable_conv2d

2D convolution with separable filters.

Default float type

Instantiates an all-ones tensor variable and returns it.

Returns whether a tensor is a sparse tensor.

Update the value of x to new_x.

Update the value of x by adding increment.

Normalizes a tensor wrt the L2 norm alongside the specified axis.

layer_activity_regularization

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

Reverse a tensor along the specified axes.

Iterates over the time dimension of a tensor

Element-wise exponentiation.

keras_model_sequential

Keras Model composed of a linear stack of layers

layer_activation

Apply an activation function to an output.

Repeats a 2D tensor.

k_random_uniform

Returns a tensor with uniform distribution of values.

k_resize_images

Resizes the images contained in a 4D tensor.

k_stop_gradient

Returns variables but with zero gradient w.r.t. every other variable.

k_resize_volumes

Resizes the volume contained in a 5D tensor.

Update the value of x by subtracting decrement.

layer_locally_connected_2d

Locally-connected layer for 2D inputs.

layer_zero_padding_1d

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

Variance of a tensor, alongside the specified axis.

layer_zero_padding_2d

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

layer_cropping_2d

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

k_spatial_2d_padding

Pads the 2nd and 3rd dimensions of a 4D tensor.

layer_cropping_3d

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

k_spatial_3d_padding

Pads 5D tensor with zeros along the depth, height, width dimensions.

Element-wise square root.

layer_gaussian_noise

Apply additive zero-centered Gaussian noise.

Element-wise square.

layer_global_average_pooling_1d

Global average pooling operation for temporal data.

k_repeat_elements

Repeats the elements of a tensor along an axis.

layer_locally_connected_1d

Locally-connected layer for 1D inputs.

Returns the symbolic shape of a tensor or variable.

Element-wise sigmoid.

Layer that adds a list of inputs.

layer_activation_elu

Exponential Linear Unit.

Long-Short Term Memory unit - Hochreiter 1997.

layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit.

layer_average_pooling_1d

Average pooling for temporal data.

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

k_truncated_normal

Returns a tensor with truncated random normal distribution of values.

Sum of the values in a tensor, alongside the specified axis.

layer_activation_parametric_relu

Parametric Rectified Linear Unit.

layer_activation_thresholded_relu

Thresholded Rectified Linear Unit.

Switches between two operations depending on a scalar value.

layer_concatenate

Layer that concatenates a list of inputs.

Transposes a tensor and returns it.

layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.

layer_max_pooling_3d

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

layer_average_pooling_2d

Average pooling operation for spatial data.

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

layer_cudnn_gru

Fast GRU implementation backed by CuDNN.

layer_zero_padding_3d

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

layer_cudnn_lstm

Fast LSTM implementation backed by CuDNN.

loss_mean_squared_error

Model loss functions

predict_on_batch

Returns predictions for a single batch of samples.

Flattens an input

Creates a tensor by tiling x by n.

Generates probability or class probability predictions for the input samples.

Converts a sparse tensor into a dense tensor and returns it.

text_to_word_sequence

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

Keras array object

Text tokenization utility

layer_alpha_dropout

Applies Alpha Dropout to the input.

layer_simple_rnn

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

Layer that averages a list of inputs.

layer_conv_lstm_2d

Convolutional LSTM.

layer_spatial_dropout_1d

Spatial 1D version of Dropout.

Reshapes an output to a certain shape.

Model configuration as JSON

layer_separable_conv_2d

Depthwise separable 2D convolution.

Model configuration as YAML

Layer that subtracts two inputs.

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

optimizer_rmsprop

RMSProp optimizer

Stochastic gradient descent optimizer

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

layer_conv_3d_transpose

Transposed 3D convolution layer (sometimes called Deconvolution).

save_model_weights_hdf5

Save/Load model weights using HDF5 files

layer_cropping_1d

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

layer_upsampling_1d

Upsampling layer for 1D inputs.

Assign values to names

Add a densely-connected NN layer to an output

multi_gpu_model

Replicates a model on different GPUs.

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

layer_global_max_pooling_3d

Global Max pooling operation for 3D data.

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

Gated Recurrent Unit - Cho et al.

layer_max_pooling_1d

Max pooling operation for temporal data.

predict.keras.engine.training.Model

Generate predictions from a Keras model

layer_max_pooling_2d

Max pooling operation for spatial data.

save_text_tokenizer

Save a text tokenizer to an external file

predict_generator

Generates predictions for the input samples from a data generator.

sequences_to_matrix

Convert a list of sequences into a matrix.

texts_to_sequences_generator

Transforms each text in texts in a sequence of integers.

serialize_model

Serialize a model to an R object

time_distributed

Apply a layer to every temporal slice of an input.

Wraps arbitrary expression as a layer

Applies Dropout to the input.

Permute the dimensions of an input according to a given pattern

layer_repeat_vector

Repeats the input n times.

layer_embedding

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

layer_spatial_dropout_2d

Spatial 2D version of Dropout.

layer_spatial_dropout_3d

Spatial 3D version of Dropout.

Softmax of a tensor.

Normalize a matrix or nd-array

optimizer_adadelta

Adadelta optimizer.

Softplus of a tensor.

optimizer_adamax

Adamax optimizer

Element-wise tanh.

Instantiates an all-zeros variable and returns it.

Instantiates an all-zeros variable of the same shape as another tensor.

k_temporal_padding

Pads the middle dimension of a 3D tensor.

R interface to Keras

Instantiates a variable and returns it.

layer_batch_normalization

Batch normalization layer (Ioffe and Szegedy, 2014).

layer_average_pooling_3d

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

layer_conv_2d_transpose

Transposed 2D convolution layer (sometimes called Deconvolution).

layer_global_average_pooling_3d

Global Average pooling operation for 3D data.

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

use_implementation

Select a Keras implementation and backend

layer_global_average_pooling_2d

Global average pooling operation for spatial data.

with_custom_object_scope

Provide a scope with mappings of names to custom objects

layer_global_max_pooling_1d

Global max pooling operation for temporal data.

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

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

layer_upsampling_2d

Upsampling layer for 2D inputs.

make_sampling_table

Generates a word rank-based probabilistic sampling table.

layer_upsampling_3d

Upsampling layer for 3D inputs.

metric_binary_accuracy

Model performance metrics

plot.keras_training_history

Plot training history

optimizer_adagrad

Adagrad optimizer.

Remove the last layer in a model

Reset the states for a layer

save_model_hdf5

Save/Load models using HDF5 files

optimizer_nadam

Nesterov Adam optimizer

Objects exported from other packages

L1 and L2 regularization

texts_to_matrix

Convert a list of texts to a matrix.

Generates skipgram word pairs.

texts_to_sequences

Transform each text in texts in a sequence of integers.

summary.keras.engine.training.Model

Print a summary of a Keras model

layer_global_max_pooling_2d

Global max pooling operation for spatial data.

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.

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

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