Learn R Programming

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

keras (version 2.8.0)

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

83,543

Version

2.8.0

License

MIT + file LICENSE

Maintainer

Tomasz Kalinowski

Last Published

February 10th, 2022

Functions in keras (2.8.0)

activation_relu

Activation functions

(Deprecated) Base R6 class for Keras layers

Create a custom Layer

application_densenet

Instantiates the DenseNet architecture.

Fits the state of the preprocessing layer to the data being passed

(Deprecated) Base R6 class for Keras callbacks

(Deprecated) Base R6 class for Keras wrappers

KerasConstraint

(Deprecated) Base R6 class for Keras constraints

application_efficientnet

Instantiates the EfficientNetB0 architecture

application_mobilenet_v3

Instantiates the MobileNetV3Large architecture

application_nasnet

Instantiates a NASNet model.

Keras backend tensor engine

application_xception

Instantiates the Xception architecture

application_resnet

Instantiates the ResNet architecture

callback_remote_monitor

Callback used to stream events to a server.

application_vgg

VGG16 and VGG19 models for Keras.

callback_tensorboard

TensorBoard basic visualizations

application_mobilenet_v2

MobileNetV2 model architecture

application_mobilenet

MobileNet model architecture.

callback_lambda

Create a custom callback

callback_terminate_on_naan

Callback that terminates training when a NaN loss is encountered.

callback_early_stopping

Stop training when a monitored quantity has stopped improving.

create_layer_wrapper

Create a Keras Layer wrapper

Clone a model instance.

callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.

application_inception_v3

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

application_inception_resnet_v2

Inception-ResNet v2 model, with weights trained on ImageNet

callback_progbar_logger

Callback that prints metrics to stdout.

Count the total number of scalars composing the weights.

dataset_cifar10

CIFAR10 small image classification

callback_csv_logger

Callback that streams epoch results to a csv file

Bidirectional wrapper for RNNs

export_savedmodel.keras.engine.training.Model

Export a Saved Model

Create a Keras Layer

callback_learning_rate_scheduler

Learning rate scheduler.

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

(Deprecated) Create a Keras Wrapper

fit.keras.engine.training.Model

Train a Keras model

flow_images_from_dataframe

Takes the dataframe and the path to a directory and generates batches of augmented/normalized data.

flow_images_from_directory

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

Loads an image into PIL format.

initializer_identity

Initializer that generates the identity matrix.

initializer_lecun_normal

LeCun normal initializer.

fit_image_data_generator

Fit image data generator internal statistics to some sample data.

3D array representation of images

MNIST database of handwritten digits

Custom metric function

dataset_cifar100

CIFAR100 small image classification

fit_text_tokenizer

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

flow_images_from_data

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

Make an Active Binding

compile.keras.engine.training.Model

Configure a Keras model for training

callback_model_checkpoint

Save the model after every epoch.

Weight constraints

dataset_reuters

Reuters newswire topics classification

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

initializer_glorot_uniform

Glorot uniform initializer, also called Xavier uniform initializer.

initializer_random_normal

Initializer that generates tensors with a normal distribution.

k_batch_get_value

Returns the value of more than one tensor variable.

k_clear_session

Destroys the current TF graph and creates a new one.

initializer_glorot_normal

Glorot normal initializer, also called Xavier normal initializer.

initializer_orthogonal

Initializer that generates a random orthogonal matrix.

k_batch_flatten

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

k_categorical_crossentropy

Categorical crossentropy between an output tensor and a target tensor.

Layer/Model configuration

3D convolution.

k_conv3d_transpose

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

initializer_ones

Initializer that generates tensors initialized to 1.

Bitwise reduction (logical AND).

Creates a constant tensor.

initializer_lecun_uniform

LeCun uniform initializer.

Element-wise absolute value.

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

imagenet_preprocess_input

Preprocesses a tensor or array encoding a batch of images.

imagenet_decode_predictions

Decodes the prediction of an ImageNet model.

Active Keras backend

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

Retrieve tensors for layers with multiple nodes

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

Concatenates a list of tensors alongside the specified axis.

Element-wise value clipping.

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

Batchwise dot product.

k_conv2d_transpose

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

2D convolution.

Keras implementation

initializer_variance_scaling

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

initializer_constant

Initializer that generates tensors initialized to a constant value.

dataset_fashion_mnist

Fashion-MNIST database of fashion articles

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

Computes the one-hot representation of an integer tensor.

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

Retrieves the elements of indices indices in the tensor reference.

k_get_variable_shape

Returns the shape of a variable.

Instantiates a Keras function

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

Element-wise inequality between two tensors.

Returns the value of a variable.

initializer_zeros

Initializer that generates tensors initialized to 0.

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

k_in_train_phase

Selects x in train phase, and alt otherwise.

Maximum value in a tensor.

1D convolution.

k_depthwise_conv2d

Depthwise 2D convolution with separable filters.

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

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

Get the uid for the default graph.

TF session to be used by the backend.

IMDB Movie reviews sentiment classification

Bitwise reduction (logical OR).

Casts a tensor to a different dtype and returns it.

k_cast_to_floatx

Cast an array to the default Keras float type.

Creates a 1D tensor containing a sequence of integers.

Default float type

Element-wise equality between two tensors.

k_image_data_format

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

Fuzz factor used in numeric expressions.

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

Flatten a tensor.

Freeze and unfreeze weights

Element-wise maximum of two tensors.

k_in_test_phase

Selects x in test phase, and alt otherwise.

Returns whether the targets are in the top k predictions.

Mean of a tensor, alongside the specified axis.

image_data_generator

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

initializer_he_normal

He normal initializer.

Retrieve the next item from a generator

initializer_he_uniform

He uniform variance scaling initializer.

image_dataset_from_directory

Create a dataset from a directory

Minimum value in a tensor.

Reverse a tensor along the specified axes.

Prints message and the tensor value when evaluated.

Element-wise exponentiation.

k_resize_volumes

Resizes the volume contained in a 5D tensor.

dataset_boston_housing

Boston housing price regression dataset

evaluate.keras.engine.training.Model

Evaluate a Keras model

k_is_keras_tensor

Returns whether x is a Keras tensor.

Element-wise log.

k_is_placeholder

Returns whether x is a placeholder.

Element-wise sigmoid.

k_manual_variable_initialization

Sets the manual variable initialization flag.

Instantiates an all-ones tensor variable and returns it.

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

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

Install TensorFlow and Keras, including all Python dependencies

evaluate_generator

(Deprecated) Evaluates the model on a data generator.

Layer/Model weights as R arrays

Make a python class constructor

is_keras_available

Check if Keras is Available

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

Returns the index of the maximum value along an axis.

Repeats a 2D tensor.

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

Rectified linear unit.

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

Returns the index of the minimum value along an axis.

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

k_batch_set_value

Sets the values of many tensor variables at once.

k_batch_normalization

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

Computes cos of x element-wise.

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

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

k_normalize_batch_in_training

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

Exponential linear unit.

Element-wise exponential.

Evaluates the value of a variable.

k_random_normal

Returns a tensor with normal distribution of values.

Element-wise sign.

Returns whether x is a symbolic tensor.

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

Returns whether a tensor is a sparse tensor.

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

Apply 1D conv with un-shared weights.

Apply 2D conv with un-shared weights.

k_sparse_categorical_crossentropy

Categorical crossentropy with integer targets.

Returns the symbolic shape of a tensor or variable.

k_separable_conv2d

2D convolution with separable filters.

k_random_binomial

Returns a tensor with random binomial distribution of values.

k_set_learning_phase

Sets the learning phase to a fixed value.

Standard deviation of a tensor, alongside the specified axis.

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

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

Transposes a tensor and returns it.

layer_activation_relu

Rectified Linear Unit activation function

Instantiates an all-zeros variable and returns it.

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

k_random_uniform_variable

Instantiates a variable with values drawn from a uniform distribution.

k_random_uniform

Returns a tensor with uniform distribution of values.

k_random_normal_variable

Instantiates a variable with values drawn from a normal distribution.

k_spatial_2d_padding

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

k_spatial_3d_padding

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

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

initializer_truncated_normal

Initializer that generates a truncated normal distribution.

k_binary_crossentropy

Binary crossentropy between an output tensor and a target tensor.

Decodes the output of a softmax.

Adds a bias vector to a tensor.

initializer_random_uniform

Initializer that generates tensors with a uniform distribution.

Adds a 1-sized dimension at index axis.

k_ctc_batch_cost

Runs CTC loss algorithm on each batch element.

k_ctc_label_dense_to_sparse

Converts CTC labels from dense to sparse.

Element-wise minimum of two tensors.

k_moving_average_update

Compute the moving average of a variable.

Element-wise rounding to the closest integer.

Iterates over the time dimension of a tensor

Element-wise square.

Instantiates a variable and returns it.

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

Variance of a tensor, alongside the specified axis.

k_stop_gradient

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

keras_model_custom

(Deprecated) Create a Keras custom model

Element-wise square root.

keras_model_sequential

Keras Model composed of a linear stack of layers

Update the value of x by adding increment.

layer_activation_selu

Scaled Exponential Linear Unit.

Update the value of x by subtracting decrement.

k_resize_images

Resizes the images contained in a 4D tensor.

Reshapes a tensor to the specified shape.

Computes sin of x element-wise.

Softplus of a tensor.

Softmax of a tensor.

Instantiate an identity matrix and returns it.

layer_activation_softmax

Softmax activation function.

layer_activation_thresholded_relu

Thresholded Rectified Linear Unit.

layer_average_pooling_3d

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

layer_batch_normalization

Batch normalization layer (Ioffe and Szegedy, 2014).

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

k_temporal_padding

Pads the middle dimension of a 3D tensor.

layer_conv_3d_transpose

Transposed 3D convolution layer (sometimes called Deconvolution).

layer_conv_lstm_1d

1D Convolutional LSTM

layer_additive_attention

Additive attention layer, a.k.a. Bahdanau-style attention

Softsign of a tensor.

Keras array object

Update the value of x to new_x.

k_truncated_normal

Returns a tensor with truncated random normal distribution of values.

layer_alpha_dropout

Applies Alpha Dropout to the input.

layer_concatenate

Layer that concatenates a list of inputs.

Creates a tensor by tiling x by n.

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

layer_attention

Creates attention layer

layer_conv_1d_transpose

Transposed 1D convolution layer (sometimes called Deconvolution).

Layer that averages a list of inputs.

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

k_greater_equal

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

layer_cudnn_lstm

(Deprecated) Fast LSTM implementation backed by CuDNN.

layer_dense_features

Constructs a DenseFeatures.

layer_average_pooling_1d

Average pooling for temporal data.

Segment-wise linear approximation of sigmoid.

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

k_learning_phase

Returns the learning phase flag.

layer_cropping_1d

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

layer_activation_parametric_relu

Parametric Rectified Linear Unit.

layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit.

k_permute_dimensions

Permutes axes in a tensor.

Instantiates a placeholder tensor and returns it.

Layer that adds a list of inputs.

layer_activity_regularization

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

Switches between two operations depending on a scalar value.

k_repeat_elements

Repeats the elements of a tensor along an axis.

Reset graph identifiers.

Element-wise tanh.

Main Keras module

R interface to Keras

layer_depthwise_conv_1d

Depthwise 1D convolution

layer_average_pooling_2d

Average pooling operation for spatial data.

layer_activation_elu

Exponential Linear Unit.

layer_activation

Apply an activation function to an output.

Add a densely-connected NN layer to an output

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

layer_conv_2d_transpose

Transposed 2D convolution layer (sometimes called Deconvolution).

layer_embedding

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

layer_cropping_2d

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

layer_conv_lstm_3d

3D Convolutional LSTM

layer_conv_lstm_2d

Convolutional LSTM.

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

Applies Dropout to the input.

Flattens an input

layer_center_crop

Crop the central portion of the images to target height and width

layer_category_encoding

A preprocessing layer which encodes integer features.

A preprocessing layer which hashes and bins categorical features.

layer_locally_connected_2d

Locally-connected layer for 2D inputs.

Long Short-Term Memory unit - Hochreiter 1997.

Permute the dimensions of an input according to a given pattern

layer_random_contrast

Adjust the contrast of an image or images by a random factor

layer_cudnn_gru

(Deprecated) Fast GRU implementation backed by CuDNN.

layer_cropping_3d

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

layer_depthwise_conv_2d

Depthwise separable 2D convolution.

Gated Recurrent Unit - Cho et al.

layer_separable_conv_1d

Depthwise separable 1D convolution.

layer_global_average_pooling_1d

Global average pooling operation for temporal data.

layer_global_average_pooling_2d

Global average pooling operation for spatial data.

Cell class for the GRU layer

layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.

layer_gaussian_noise

Apply additive zero-centered Gaussian noise.

Wraps arbitrary expression as a layer

layer_integer_lookup

A preprocessing layer which maps integer features to contiguous ranges.

layer_multi_head_attention

MultiHeadAttention layer

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

layer_discretization

A preprocessing layer which buckets continuous features by ranges.

layer_global_max_pooling_2d

Global max pooling operation for spatial data.

layer_global_max_pooling_3d

Global Max pooling operation for 3D data.

layer_lstm_cell

Cell class for the LSTM layer

text_hashing_trick

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

layer_separable_conv_2d

Separable 2D convolution.

layer_spatial_dropout_3d

Spatial 3D version of Dropout.

metric_recall_at_precision

Computes best recall where precision is >= specified value

layer_random_rotation

Randomly rotate each image

layer_rescaling

Multiply inputs by scale and adds offset

layer_random_height

Randomly vary the height of a batch of images during training

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

layer_zero_padding_3d

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

layer_random_translation

Randomly translate each image during training

layer_spatial_dropout_2d

Spatial 2D version of Dropout.

metric_categorical_hinge

Computes the categorical hinge metric between y_true and y_pred

layer_stacked_rnn_cells

Wrapper allowing a stack of RNN cells to behave as a single cell

Model configuration as JSON

layer_upsampling_2d

Upsampling layer for 2D inputs.

layer_upsampling_3d

Upsampling layer for 3D inputs.

layer_max_pooling_1d

Max pooling operation for temporal data.

layer_text_vectorization

A preprocessing layer which maps text features to integer sequences.

metric-or-Metric

metric-or-Metric

Reshapes an output to a certain shape.

layer_upsampling_1d

Upsampling layer for 1D inputs.

Approximates the AUC (Area under the curve) of the ROC or PR curves

layer_random_crop

Randomly crop the images to target height and width

layer_simple_rnn

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

layer_simple_rnn_cell

Cell class for SimpleRNN

layer_random_flip

Randomly flip each image horizontally and vertically

layer_max_pooling_2d

Max pooling operation for spatial data.

layer_global_average_pooling_3d

Global Average pooling operation for 3D data.

layer_global_max_pooling_1d

Global max pooling operation for temporal data.

loss_cosine_proximity

(Deprecated) loss_cosine_proximity

layer_max_pooling_3d

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

metric_false_negatives

Calculates the number of false negatives

make_sampling_table

Generates a word rank-based probabilistic sampling table.

metric_kullback_leibler_divergence

Computes Kullback-Leibler divergence

metric_squared_hinge

Computes the squared hinge metric

metric_specificity_at_sensitivity

Computes best specificity where sensitivity is >= specified value

Computes the hinge metric between y_true and y_pred

plot.keras_training_history

Plot training history

metric_root_mean_squared_error

Computes root mean squared error metric between y_true and y_pred

metric_binary_accuracy

Calculates how often predictions match binary labels

layer_layer_normalization

Layer normalization layer (Ba et al., 2016).

metric_true_positives

Calculates the number of true positives

layer_random_width

Randomly vary the width of a batch of images during training

Layer that subtracts two inputs.

layer_repeat_vector

Repeats the input n times.

layer_locally_connected_1d

Locally-connected layer for 1D inputs.

layer_zero_padding_2d

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

layer_random_zoom

A preprocessing layer which randomly zooms images during training.

layer_string_lookup

A preprocessing layer which maps string features to integer indices.

layer_zero_padding_1d

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

metric_cosine_proximity

(Deprecated) metric_cosine_proximity

layer_spatial_dropout_1d

Spatial 1D version of Dropout.

metric_mean_iou

Computes the mean Intersection-Over-Union metric

metric_cosine_similarity

Computes the cosine similarity between the labels and predictions

metric_mean_squared_logarithmic_error

Computes the mean squared logarithmic error

metric_sparse_top_k_categorical_accuracy

Computes how often integer targets are in the top K predictions

metric_mean_wrapper

Wraps a stateless metric function with the Mean metric

optimizer_adagrad

Adagrad optimizer.

metric_mean_tensor

Computes the element-wise (weighted) mean of the given tensors

metric_sparse_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions

metric_mean_squared_error

Computes the mean squared error between labels and predictions

metric_mean_relative_error

Computes the mean relative error by normalizing with the given values

Assign values to names

Remove the last layer in a model

metric_accuracy

Calculates how often predictions equal labels

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

metric_precision_at_recall

Computes best precision where recall is >= specified value

metric_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions

predict.keras.engine.training.Model

Generate predictions from a Keras model

model_to_saved_model

(Deprecated) Export to Saved Model format

metric_true_negatives

Calculates the number of true negatives

Computes the recall of the predictions with respect to the labels

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

Image resizing layer

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

Base class for recurrent layers

layer_normalization

A preprocessing layer which normalizes continuous features.

Model configuration as YAML

model_from_saved_model

Load a Keras model from the Saved Model format

text_to_word_sequence

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

texts_to_sequences_generator

Transforms each text in texts in a sequence of integers.

time_distributed

This layer wrapper allows to apply a layer to every temporal slice of an input

Objects exported from other packages

timeseries_dataset_from_array

Creates a dataset of sliding windows over a timeseries provided as array

metric_sparse_categorical_accuracy

Calculates how often predictions match integer labels

metric_logcosh_error

Computes the logarithm of the hyperbolic cosine of the prediction error

metric_false_positives

Calculates the number of false positives

metric_binary_crossentropy

Computes the crossentropy metric between the labels and predictions

predict_on_batch

Returns predictions for a single batch of samples.

summary.keras.engine.training.Model

Print a summary of a Keras model

serialize_model

Serialize a model to an R object

save_model_weights_tf

Save model weights in the SavedModel format

save_text_tokenizer

Save a text tokenizer to an external file

predict_generator

(Deprecated) Generates predictions for the input samples from a data generator.

Computes the (weighted) mean of the given values

metric_sensitivity_at_specificity

Computes best sensitivity where specificity is >= specified value

multi_gpu_model

(Deprecated) Replicates a model on different GPUs.

Pads sequences to the same length

optimizer_adamax

Adamax optimizer

timeseries_generator

Utility function for generating batches of temporal data.

optimizer_nadam

Nesterov Adam optimizer

metric_categorical_accuracy

Calculates how often predictions match one-hot labels

metric_mean_absolute_error

Computes the mean absolute error between the labels and predictions

metric_mean_absolute_percentage_error

Computes the mean absolute percentage error between y_true and y_pred

(Deprecated) Generates probability or class probability predictions for the input samples.

text_dataset_from_directory

Generate a tf.data.Dataset from text files in a directory

Save/Load models using SavedModel format

save_model_weights_hdf5

Save/Load model weights using HDF5 files

Normalize a matrix or nd-array

Computes the Poisson metric between y_true and y_pred

optimizer_adadelta

Adadelta optimizer.

Computes the (weighted) sum of the given values

metric_top_k_categorical_accuracy

Computes how often targets are in the top K predictions

metric_precision

Computes the precision of the predictions with respect to the labels

Reset the states for a layer

save_model_hdf5

Save/Load models using HDF5 files

Text tokenization utility

with_custom_object_scope

Provide a scope with mappings of names to custom objects

Generates skipgram word pairs.

use_implementation

Select a Keras implementation and backend

optimizer_rmsprop

RMSProp optimizer

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

L1 and L2 regularization

sequences_to_matrix

Convert a list of sequences into a matrix.

sequential_model_input_layer

sequential_model_input_layer

Stochastic gradient descent optimizer

texts_to_matrix

Convert a list of texts to a matrix.

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

texts_to_sequences

Transform each text in texts in a sequence of integers.