Learn R Programming

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

keras (version 2.2.0)

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

2.2.0

License

MIT + file LICENSE

Maintainer

JJ Allaire

Last Published

August 24th, 2018

Functions in keras (2.2.0)

application_inception_resnet_v2

Inception-ResNet v2 model, with weights trained on ImageNet

Bidirectional wrapper for RNNs.

callback_csv_logger

Callback that streams epoch results to a csv file

Create a Keras Layer

Count the total number of scalars composing the weights.

activation_relu

Activation functions

fit_image_data_generator

Fit image data generator internal statistics to some sample data.

application_xception

Xception V1 model for Keras.

Keras backend tensor engine

Configure a Keras model for training

callback_learning_rate_scheduler

Learning rate scheduler.

callback_model_checkpoint

Save the model after every epoch.

Weight constraints

callback_early_stopping

Stop training when a monitored quantity has stopped improving.

callback_lambda

Create a custom callback

fit_text_tokenizer

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

dataset_cifar100

CIFAR100 small image classification

dataset_fashion_mnist

Fashion-MNIST database of fashion articles

Layer/Model weights as R arrays

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

dataset_boston_housing

Boston housing price regression dataset

dataset_cifar10

CIFAR10 small image classification

application_resnet50

ResNet50 model for Keras.

callback_progbar_logger

Callback that prints metrics to stdout.

callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.

dataset_reuters

Reuters newswire topics classification

Train a Keras model

evaluate.keras.engine.training.Model

Evaluate a Keras model

application_vgg

VGG16 and VGG19 models for Keras.

initializer_he_uniform

He uniform variance scaling initializer.

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

initializer_identity

Initializer that generates the identity matrix.

callback_terminate_on_naan

Callback that terminates training when a NaN loss is encountered.

Clone a model instance.

flow_images_from_data

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

callback_remote_monitor

Callback used to stream events to a server.

callback_tensorboard

TensorBoard basic visualizations

flow_images_from_directory

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

3D array representation of images

IMDB Movie reviews sentiment classification

Returns the index of the minimum value along an axis.

evaluate_generator

Evaluates the model on a data generator.

Retrieve tensors for layers with multiple nodes

imagenet_decode_predictions

Decodes the prediction of an ImageNet model.

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

Active Keras backend

MNIST database of handwritten digits

export_savedmodel.keras.engine.training.Model

Export a Saved Model

initializer_ones

Initializer that generates tensors initialized to 1.

initializer_glorot_uniform

Glorot uniform initializer, also called Xavier uniform initializer.

initializer_orthogonal

Initializer that generates a random orthogonal matrix.

Freeze and unfreeze weights

Concatenates a list of tensors alongside the specified axis.

Retrieve the next item from a generator

initializer_he_normal

He normal initializer.

Creates a constant tensor.

initializer_constant

Initializer that generates tensors initialized to a constant value.

Layer/Model configuration

initializer_zeros

Initializer that generates tensors initialized to 0.

k_conv2d_transpose

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

3D convolution.

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

Install Keras and the TensorFlow backend

initializer_truncated_normal

Initializer that generates a truncated normal distribution.

initializer_glorot_normal

Glorot normal initializer, also called Xavier normal initializer.

image_data_generator

Generate batches of image data with real-time data augmentation. The data will be looped over (in batches).

imagenet_preprocess_input

Preprocesses a tensor or array encoding a batch of images.

Keras implementation

initializer_random_normal

Initializer that generates tensors with a normal distribution.

Loads an image into PIL format.

Element-wise equality between two tensors.

initializer_lecun_normal

LeCun normal initializer.

initializer_lecun_uniform

LeCun uniform initializer.

initializer_variance_scaling

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

initializer_random_uniform

Initializer that generates tensors with a uniform distribution.

1D convolution.

Evaluates the value of a variable.

2D convolution.

Bitwise reduction (logical AND).

Bitwise reduction (logical OR).

Creates a 1D tensor containing a sequence of integers.

Batchwise dot product.

Returns the index of the maximum value along an axis.

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.

is_keras_available

Check if Keras is Available

Returns whether the targets are in the top k predictions.

k_batch_normalization

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

k_binary_crossentropy

Binary crossentropy between an output tensor and a target tensor.

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

k_cast_to_floatx

Cast an array to the default Keras float type.

Element-wise absolute value.

Casts a tensor to a different dtype and returns it.

k_ctc_batch_cost

Runs CTC loss algorithm on each batch element.

k_in_train_phase

Selects x in train phase, and alt otherwise.

k_categorical_crossentropy

Categorical crossentropy between an output tensor and a target tensor.

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

k_learning_phase

Returns the learning phase flag.

k_batch_set_value

Sets the values of many tensor variables at once.

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

Exponential linear unit.

Fuzz factor used in numeric expressions.

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

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

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

Adds a bias vector to a tensor.

Maximum value in a tensor.

Instantiates a Keras function

Element-wise exponential.

k_clear_session

Destroys the current TF graph and creates a new one.

k_moving_average_update

Compute the moving average of a variable.

Adds a 1-sized dimension at index axis.

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

k_get_variable_shape

Returns the shape of a variable.

Decodes the output of a softmax.

k_ctc_label_dense_to_sparse

Converts CTC labels from dense to sparse.

Retrieves the elements of indices indices in the tensor reference.

Default float type

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

Element-wise value clipping.

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

k_random_uniform_variable

Instantiates a variable with values drawn from a uniform distribution.

TF session to be used by the backend.

Rectified linear unit.

k_conv3d_transpose

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

Computes cos of x element-wise.

k_image_data_format

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

k_in_test_phase

Selects x in test phase, and alt otherwise.

k_depthwise_conv2d

Depthwise 2D convolution with separable filters.

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

k_resize_images

Resizes the images contained in a 4D tensor.

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

k_resize_volumes

Resizes the volume contained in a 5D tensor.

k_is_placeholder

Returns whether x is a placeholder.

Segment-wise linear approximation of sigmoid.

Element-wise square.

Element-wise square root.

Creates a tensor by tiling x by n.

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

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

Returns whether a tensor is a sparse tensor.

Returns whether x is a symbolic tensor.

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

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

Minimum value in a tensor.

Element-wise minimum of two tensors.

Apply 2D conv with un-shared weights.

layer_average_pooling_2d

Average pooling operation for spatial data.

Element-wise log.

Instantiate an identity matrix and returns it.

Get the uid for the default graph.

Keras array object

layer_locally_connected_2d

Locally-connected layer for 2D inputs.

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

k_permute_dimensions

Permutes axes in a tensor.

Flatten a tensor.

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

Returns the value of a variable.

Apply 1D conv with un-shared weights.

k_normalize_batch_in_training

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

Element-wise maximum of two tensors.

Computes the one-hot representation of an integer tensor.

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

Element-wise inequality between two tensors.

Reverse a tensor along the specified axes.

k_greater_equal

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

Instantiates an all-ones tensor variable and returns it.

Iterates over the time dimension of a tensor

layer_global_max_pooling_2d

Global max pooling operation for spatial data.

layer_global_max_pooling_1d

Global max pooling operation for temporal data.

Prints message and the tensor value when evaluated.

Mean of a tensor, alongside the specified axis.

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

make_sampling_table

Generates a word rank-based probabilistic sampling table.

k_random_binomial

Returns a tensor with random binomial distribution of values.

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

k_is_keras_tensor

Returns whether x is a Keras tensor.

layer_average_pooling_3d

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

Returns the symbolic shape of a tensor or variable.

layer_locally_connected_1d

Locally-connected layer for 1D inputs.

k_random_normal

Returns a tensor with normal distribution of values.

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

Element-wise sigmoid.

Element-wise rounding to the closest integer.

Instantiates a placeholder tensor and returns it.

k_manual_variable_initialization

Sets the manual variable initialization flag.

save_text_tokenizer

Save a text tokenizer to an external file

Assign values to names

Element-wise exponentiation.

k_set_learning_phase

Sets the learning phase to a fixed value.

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

k_separable_conv2d

2D convolution with separable filters.

loss_mean_squared_error

Model loss functions

Repeats a 2D tensor.

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

Layer that adds a list of inputs.

Model configuration as YAML

Switches between two operations depending on a scalar value.

k_repeat_elements

Repeats the elements of a tensor along an axis.

k_random_normal_variable

Instantiates a variable with values drawn from a normal distribution.

k_random_uniform

Returns a tensor with uniform distribution of values.

Softmax of a tensor.

Softplus of a tensor.

R interface to Keras

Update the value of x to new_x.

Instantiates a variable and returns it.

Update the value of x by adding increment.

Standard deviation of a tensor, alongside the specified axis.

Reset graph identifiers.

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

Instantiates an all-zeros variable and returns it.

predict_generator

Generates predictions for the input samples from a data generator.

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

Reshapes a tensor to the specified shape.

optimizer_adamax

Adamax optimizer

Softsign of a tensor.

Layer that averages a list of inputs.

plot.keras_training_history

Plot training history

Transposes a tensor and returns it.

Variance of a tensor, alongside the specified axis.

layer_activity_regularization

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

k_sparse_categorical_crossentropy

Categorical crossentropy with integer targets.

k_truncated_normal

Returns a tensor with truncated random normal distribution of values.

layer_average_pooling_1d

Average pooling for temporal data.

summary.keras.engine.training.Model

Print a summary of a Keras model

layer_activation

Apply an activation function to an output.

Element-wise sign.

k_spatial_2d_padding

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

keras_model_custom

Create a Keras custom model

sequences_to_matrix

Convert a list of sequences into a matrix.

Computes sin of x element-wise.

layer_activation_elu

Exponential Linear Unit.

k_spatial_3d_padding

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

Gated Recurrent Unit - Cho et al.

layer_alpha_dropout

Applies Alpha Dropout to the input.

time_distributed

Apply a layer to every temporal slice of an input.

timeseries_generator

Utility function for generating batches of temporal data.

keras_model_sequential

Keras Model composed of a linear stack of layers

Update the value of x by subtracting decrement.

layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit.

layer_conv_2d_transpose

Transposed 2D convolution layer (sometimes called Deconvolution).

Element-wise tanh.

layer_activation_parametric_relu

Parametric Rectified Linear Unit.

k_temporal_padding

Pads the middle dimension of a 3D tensor.

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

layer_upsampling_1d

Upsampling layer for 1D inputs.

layer_concatenate

Layer that concatenates a list of inputs.

layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.

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

k_stop_gradient

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

layer_activation_relu

Rectified Linear Unit activation function

predict.keras.engine.training.Model

Generate predictions from a Keras model

layer_activation_softmax

Softmax activation function.

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

layer_activation_thresholded_relu

Thresholded Rectified Linear Unit.

layer_batch_normalization

Batch normalization layer (Ioffe and Szegedy, 2014).

layer_conv_lstm_2d

Convolutional LSTM.

layer_depthwise_conv_2d

Depthwise separable 2D convolution.

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

Long Short-Term Memory unit - Hochreiter 1997.

layer_global_average_pooling_2d

Global average pooling operation for spatial data.

Applies Dropout to the input.

Wraps arbitrary expression as a layer

layer_embedding

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

Flattens an input

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

optimizer_adadelta

Adadelta optimizer.

layer_global_max_pooling_3d

Global Max pooling operation for 3D data.

layer_conv_3d_transpose

Transposed 3D convolution layer (sometimes called Deconvolution).

layer_cudnn_gru

Fast GRU implementation backed by CuDNN.

texts_to_matrix

Convert a list of texts to a matrix.

layer_gaussian_noise

Apply additive zero-centered Gaussian noise.

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

layer_simple_rnn

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

layer_cropping_1d

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

Reshapes an output to a certain shape.

layer_cropping_2d

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

layer_global_average_pooling_1d

Global average pooling operation for temporal data.

layer_cudnn_lstm

Fast LSTM implementation backed by CuDNN.

layer_max_pooling_1d

Max pooling operation for temporal data.

layer_spatial_dropout_2d

Spatial 2D version of Dropout.

optimizer_rmsprop

RMSProp optimizer

layer_cropping_3d

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

layer_separable_conv_1d

Depthwise separable 1D convolution.

Add a densely-connected NN layer to an output

layer_upsampling_3d

Upsampling layer for 3D inputs.

layer_separable_conv_2d

Separable 2D convolution.

predict_on_batch

Returns predictions for a single batch of samples.

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

layer_zero_padding_1d

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

layer_global_average_pooling_3d

Global Average pooling operation for 3D data.

layer_spatial_dropout_1d

Spatial 1D version of Dropout.

optimizer_nadam

Nesterov Adam optimizer

layer_spatial_dropout_3d

Spatial 3D version of Dropout.

layer_zero_padding_3d

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

metric_binary_accuracy

Model performance metrics

layer_max_pooling_2d

Max pooling operation for spatial data.

with_custom_object_scope

Provide a scope with mappings of names to custom objects

layer_repeat_vector

Repeats the input n times.

Model configuration as JSON

Text tokenization utility

use_implementation

Select a Keras implementation and backend

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

Permute the dimensions of an input according to a given pattern

L1 and L2 regularization

layer_max_pooling_3d

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

texts_to_sequences

Transform each text in texts in a sequence of integers.

Generates probability or class probability predictions for the input samples.

text_hashing_trick

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

Objects exported from other packages

layer_zero_padding_2d

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

optimizer_adagrad

Adagrad optimizer.

layer_upsampling_2d

Upsampling layer for 2D inputs.

save_model_weights_hdf5

Save/Load model weights using HDF5 files

Remove the last layer in a model

Pads sequences to the same length

Layer that subtracts two inputs.

Generates skipgram word pairs.

multi_gpu_model

Replicates a model on different GPUs.

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

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

save_model_hdf5

Save/Load models using HDF5 files

Normalize a matrix or nd-array

serialize_model

Serialize a model to an R object

texts_to_sequences_generator

Transforms each text in texts in a sequence of integers.

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

Stochastic gradient descent optimizer

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

Reset the states for a layer

text_to_word_sequence

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

application_mobilenet

MobileNet model architecture.

application_inception_v3

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

Base R6 class for Keras callbacks

application_densenet

Instantiates the DenseNet architecture.

KerasConstraint

Base R6 class for Keras constraints

Base R6 class for Keras layers

application_mobilenet_v2

MobileNetV2 model architecture

application_nasnet

Instantiates a NASNet model.