keras v2.2.4

0

Monthly downloads

0th

Percentile

R Interface to 'Keras'

Interface to 'Keras' <https://keras.io>, 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.

Functions in keras

Name Description
KerasCallback Base R6 class for Keras callbacks
callback_learning_rate_scheduler Learning rate scheduler.
constraints Weight constraints
count_params Count the total number of scalars composing the weights.
dataset_reuters Reuters newswire topics classification
evaluate.keras.engine.training.Model Evaluate a Keras model
freeze_weights Freeze and unfreeze weights
generator_next Retrieve the next item from a generator
get_input_at Retrieve tensors for layers with multiple nodes
get_layer Retrieves a layer based on either its name (unique) or index.
initializer_glorot_uniform Glorot uniform initializer, also called Xavier uniform initializer.
initializer_he_normal He normal initializer.
initializer_ones Initializer that generates tensors initialized to 1.
application_mobilenet MobileNet model architecture.
initializer_orthogonal Initializer that generates a random orthogonal matrix.
k_argmin Returns the index of the minimum value along an axis.
k_backend Active Keras backend
k_cast_to_floatx Cast an array to the default Keras float type.
application_mobilenet_v2 MobileNetV2 model architecture
k_categorical_crossentropy Categorical crossentropy between an output tensor and a target tensor.
application_vgg VGG16 and VGG19 models for Keras.
k_conv1d 1D convolution.
k_conv2d 2D convolution.
application_xception Xception V1 model for Keras.
clone_model Clone a model instance.
compile.keras.engine.training.Model Configure a Keras model for training
dataset_boston_housing Boston housing price regression dataset
k_cumprod Cumulative product of the values in a tensor, alongside the specified axis.
k_cumsum Cumulative sum of the values in a tensor, alongside the specified axis.
k_exp Element-wise exponential.
k_expand_dims Adds a 1-sized dimension at index axis.
dataset_cifar10 CIFAR10 small image classification
activation_relu Activation functions
application_densenet Instantiates the DenseNet architecture.
backend Keras backend tensor engine
k_get_uid Get the uid for the default graph.
k_get_value Returns the value of a variable.
application_inception_resnet_v2 Inception-ResNet v2 model, with weights trained on ImageNet
bidirectional Bidirectional wrapper for RNNs.
callback_model_checkpoint Save the model after every epoch.
application_inception_v3 Inception V3 model, with weights pre-trained on ImageNet.
fit.keras.engine.training.Model Train a Keras model
fit_generator Fits the model on data yielded batch-by-batch by a generator.
application_resnet50 ResNet50 model for Keras.
application_nasnet Instantiates a NASNet model.
callback_reduce_lr_on_plateau Reduce learning rate when a metric has stopped improving.
callback_remote_monitor Callback used to stream events to a server.
k_int_shape 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.
callback_progbar_logger Callback that prints metrics to stdout.
dataset_imdb IMDB Movie reviews sentiment classification
KerasLayer Base R6 class for Keras layers
k_logsumexp Computes log(sum(exp(elements across dimensions of a tensor))).
create_layer Create a Keras Layer
fit_image_data_generator Fit image data generator internal statistics to some sample data.
create_wrapper Create a Keras Wrapper
KerasWrapper Base R6 class for Keras wrappers
fit_text_tokenizer Update tokenizer internal vocabulary based on a list of texts or list of sequences.
callback_csv_logger Callback that streams epoch results to a csv file
k_manual_variable_initialization Sets the manual variable initialization flag.
callback_early_stopping Stop training when a monitored quantity has stopped improving.
get_weights Layer/Model weights as R arrays
get_config Layer/Model configuration
hdf5_matrix Representation of HDF5 dataset to be used instead of an R array
initializer_glorot_normal Glorot normal initializer, also called Xavier normal initializer.
initializer_constant Initializer that generates tensors initialized to a constant value.
callback_tensorboard TensorBoard basic visualizations
dataset_mnist MNIST database of handwritten digits
get_file Downloads a file from a URL if it not already in the cache.
initializer_he_uniform He uniform variance scaling initializer.
initializer_truncated_normal Initializer that generates a truncated normal distribution.
initializer_identity Initializer that generates the identity matrix.
flow_images_from_data Generates batches of augmented/normalized data from image data and labels
image_load Loads an image into PIL format.
image_data_generator Generate batches of image data with real-time data augmentation. The data will be looped over (in batches).
flow_images_from_directory Generates batches of data from images in a directory (with optional augmented/normalized data)
callback_terminate_on_naan Callback that terminates training when a NaN loss is encountered.
imagenet_preprocess_input Preprocesses a tensor or array encoding a batch of images.
implementation Keras implementation
k_min Minimum value in a tensor.
is_keras_available Check if Keras is Available
initializer_random_normal Initializer that generates tensors with a normal distribution.
k_abs Element-wise absolute value.
initializer_random_uniform Initializer that generates tensors with a uniform distribution.
k_arange Creates a 1D tensor containing a sequence of integers.
dataset_cifar100 CIFAR100 small image classification
initializer_variance_scaling Initializer capable of adapting its scale to the shape of weights.
k_all Bitwise reduction (logical AND).
k_batch_get_value Returns the value of more than one tensor variable.
k_argmax Returns the index of the maximum value along an axis.
dataset_fashion_mnist Fashion-MNIST database of fashion articles
k_binary_crossentropy Binary crossentropy between an output tensor and a target 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.
k_any Bitwise reduction (logical OR).
k_minimum Element-wise minimum of two tensors.
k_reverse Reverse a tensor along the specified axes.
k_cast Casts a tensor to a different dtype and returns it.
evaluate_generator Evaluates the model on a data generator.
k_conv3d_transpose 3D deconvolution (i.e. transposed convolution).
k_random_binomial Returns a tensor with random binomial distribution of values.
k_cos Computes cos of x element-wise.
k_clear_session Destroys the current TF graph and creates a new one.
k_count_params Returns the static number of elements in a Keras variable or tensor.
k_clip Element-wise value clipping.
k_bias_add Adds a bias vector to a tensor.
k_ctc_batch_cost Runs CTC loss algorithm on each batch element.
export_savedmodel.keras.engine.training.Model Export a Saved Model
k_depthwise_conv2d Depthwise 2D convolution with separable filters.
image_to_array 3D array representation of images
k_sign Element-wise sign.
k_ctc_decode Decodes the output of a softmax.
k_random_normal Returns a tensor with normal distribution of values.
k_elu Exponential linear unit.
k_foldr Reduce elems using fn to combine them from right to left.
k_epsilon Fuzz factor used in numeric expressions.
k_function Instantiates a Keras function
imagenet_decode_predictions Decodes the prediction of an ImageNet model.
k_tile Creates a tensor by tiling x by n.
initializer_lecun_uniform LeCun uniform initializer.
initializer_zeros Initializer that generates tensors initialized to 0.
initializer_lecun_normal LeCun normal initializer.
k_dot Multiplies 2 tensors (and/or variables) and returns a tensor.
k_equal Element-wise equality between two tensors.
k_ctc_label_dense_to_sparse Converts CTC labels from dense to sparse.
install_keras Install Keras and the TensorFlow backend
k_batch_dot Batchwise dot product.
k_rnn Iterates over the time dimension of a tensor
k_batch_flatten Turn a nD tensor into a 2D tensor with same 1st dimension.
k_gather Retrieves the elements of indices indices in the tensor reference.
k_eval Evaluates the value of a variable.
k_eye Instantiate an identity matrix and returns it.
k_concatenate Concatenates a list of tensors alongside the specified axis.
k_flatten Flatten a tensor.
k_image_data_format Default image data format convention ('channels_first' or 'channels_last').
k_get_session TF session to be used by the backend.
k_in_test_phase Selects x in test phase, and alt otherwise.
k_constant Creates a constant tensor.
k_hard_sigmoid Segment-wise linear approximation of sigmoid.
k_gradients Returns the gradients of variables w.r.t. loss.
k_get_variable_shape Returns the shape of a variable.
k_learning_phase Returns the learning phase flag.
layer_activation_elu Exponential Linear Unit.
k_conv2d_transpose 2D deconvolution (i.e. transposed convolution).
k_identity Returns a tensor with the same content as the input tensor.
k_conv3d 3D convolution.
k_is_tensor Returns whether x is a symbolic tensor.
layer_max_pooling_2d Max pooling operation for spatial data.
k_sin Computes sin of x element-wise.
k_moving_average_update Compute the moving average of a variable.
k_less Element-wise truth value of (x < y).
k_squeeze Removes a 1-dimension from the tensor at index axis.
k_dropout Sets entries in x to zero at random, while scaling the entire tensor.
k_stack Stacks a list of rank R tensors into a rank R+1 tensor.
keras_model_custom Create a Keras custom model
k_less_equal Element-wise truth value of (x <= y).
k_to_dense Converts a sparse tensor into a dense tensor and returns it.
k_l2_normalize Normalizes a tensor wrt the L2 norm alongside the specified axis.
keras_model_sequential Keras Model composed of a linear stack of layers
k_dtype Returns the dtype of a Keras tensor or variable, as a string.
layer_activation Apply an activation function to an output.
layer_conv_2d 2D convolution layer (e.g. spatial convolution over images).
k_floatx Default float type
k_maximum Element-wise maximum of two tensors.
k_in_train_phase Selects x in train phase, and alt otherwise.
k_in_top_k Returns whether the targets are in the top k predictions.
k_local_conv2d Apply 2D conv with un-shared weights.
k_mean Mean of a tensor, alongside the specified axis.
k_foldl Reduce elems using fn to combine them from left to right.
k_local_conv1d Apply 1D conv with un-shared weights.
k_one_hot Computes the one-hot representation of an integer tensor.
k_ones Instantiates an all-ones tensor variable and returns it.
k_greater Element-wise truth value of (x > y).
k_greater_equal Element-wise truth value of (x >= y).
layer_average_pooling_2d Average pooling operation for spatial data.
layer_activation_leaky_relu Leaky version of a Rectified Linear Unit.
k_log Element-wise log.
k_is_placeholder Returns whether x is a placeholder.
layer_global_average_pooling_3d Global Average pooling operation for 3D data.
k_placeholder Instantiates a placeholder tensor and returns it.
k_random_uniform_variable Instantiates a variable with values drawn from a uniform distribution.
k_normalize_batch_in_training Computes mean and std for batch then apply batch_normalization on batch.
k_is_sparse Returns whether a tensor is a sparse tensor.
k_random_normal_variable Instantiates a variable with values drawn from a normal distribution.
k_ndim Returns the number of axes in a tensor, as an integer.
layer_average_pooling_1d Average pooling for temporal data.
layer_depthwise_conv_2d Depthwise separable 2D convolution.
k_reset_uids Reset graph identifiers.
k_random_uniform Returns a tensor with uniform distribution of values.
layer_dense Add a densely-connected NN layer to an output
k_not_equal Element-wise inequality between two tensors.
layer_embedding Turns positive integers (indexes) into dense vectors of fixed size.
k_softplus Softplus of a tensor.
k_print_tensor Prints message and the tensor value when evaluated.
k_pool2d 2D Pooling.
layer_subtract Layer that subtracts two inputs.
layer_lambda Wraps arbitrary expression as a layer
k_square Element-wise square.
k_reshape Reshapes a tensor to the specified shape.
k_map_fn Map the function fn over the elements elems and return the outputs.
k_std Standard deviation of a tensor, alongside the specified axis.
k_round Element-wise rounding to the closest integer.
k_prod Multiplies the values in a tensor, alongside the specified axis.
k_resize_images Resizes the images contained in a 4D tensor.
k_repeat_elements Repeats the elements of a tensor along an axis.
k_max Maximum value in a tensor.
layer_masking Masks a sequence by using a mask value to skip timesteps.
k_relu Rectified linear unit.
layer_activation_selu Scaled Exponential Linear Unit.
layer_global_max_pooling_1d Global max pooling operation for temporal data.
k_zeros Instantiates an all-zeros variable and returns it.
k_ones_like Instantiates an all-ones variable of the same shape as another tensor.
k_shape Returns the symbolic shape of a tensor or variable.
k_separable_conv2d 2D convolution with separable filters.
k_sum Sum of the values in a tensor, alongside the specified axis.
layer_locally_connected_1d Locally-connected layer for 1D inputs.
k_permute_dimensions Permutes axes in a tensor.
layer_max_pooling_3d Max pooling operation for 3D data (spatial or spatio-temporal).
k_stop_gradient Returns variables but with zero gradient w.r.t. every other variable.
k_sigmoid Element-wise sigmoid.
metric_binary_accuracy Model performance metrics
k_resize_volumes Resizes the volume contained in a 5D tensor.
k_update_sub Update the value of x by subtracting decrement.
k_softmax Softmax of a tensor.
layer_activation_thresholded_relu Thresholded Rectified Linear Unit.
k_update_add Update the value of x by adding increment.
k_sqrt Element-wise square root.
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.
layer_global_average_pooling_2d Global average pooling operation for spatial data.
keras_array Keras array object
k_softsign Softsign of a tensor.
k_pool3d 3D Pooling.
k_update Update the value of x to new_x.
k_tanh Element-wise tanh.
layer_upsampling_1d Upsampling layer for 1D inputs.
k_temporal_padding Pads the middle dimension of a 3D tensor.
keras-package R interface to Keras
k_zeros_like Instantiates an all-zeros variable of the same shape as another tensor.
optimizer_adagrad Adagrad optimizer.
k_switch Switches between two operations depending on a scalar value.
k_set_learning_phase Sets the learning phase to a fixed value.
layer_activation_softmax Softmax activation function.
k_pow Element-wise exponentiation.
layer_conv_2d_transpose Transposed 2D convolution layer (sometimes called Deconvolution).
layer_upsampling_2d Upsampling layer for 2D inputs.
layer_cudnn_gru Fast GRU implementation backed by CuDNN.
layer_conv_3d 3D convolution layer (e.g. spatial convolution over volumes).
keras_model Keras Model
layer_repeat_vector Repeats the input n times.
layer_gaussian_dropout Apply multiplicative 1-centered Gaussian noise.
layer_separable_conv_1d Depthwise separable 1D convolution.
k_var Variance of a tensor, alongside the specified axis.
optimizer_adam Adam optimizer
layer_cropping_2d Cropping layer for 2D input (e.g. picture).
layer_add Layer that adds a list of inputs.
layer_activation_parametric_relu Parametric Rectified Linear Unit.
k_repeat Repeats a 2D tensor.
layer_activation_relu Rectified Linear Unit activation function
make_sampling_table Generates a word rank-based probabilistic sampling table.
predict_on_batch Returns predictions for a single batch of samples.
layer_cudnn_lstm Fast LSTM implementation backed by CuDNN.
layer_conv_1d 1D convolution layer (e.g. temporal convolution).
k_sparse_categorical_crossentropy Categorical crossentropy with integer targets.
layer_global_max_pooling_2d Global max pooling operation for spatial data.
layer_concatenate Layer that concatenates a list of inputs.
layer_activity_regularization Layer that applies an update to the cost function based input activity.
k_set_value Sets the value of a variable, from an R array.
k_transpose Transposes a tensor and returns it.
k_variable Instantiates a variable and returns it.
layer_alpha_dropout Applies Alpha Dropout to the input.
layer_permute Permute the dimensions of an input according to a given pattern
layer_gru Gated Recurrent Unit - Cho et al.
layer_maximum Layer that computes the maximum (element-wise) a list of inputs.
layer_global_max_pooling_3d Global Max pooling operation for 3D data.
layer_conv_3d_transpose Transposed 3D convolution layer (sometimes called Deconvolution).
sequences_to_matrix Convert a list of sequences into a matrix.
optimizer_rmsprop RMSProp optimizer
layer_average Layer that averages a list of inputs.
layer_gaussian_noise Apply additive zero-centered Gaussian noise.
k_truncated_normal Returns a tensor with truncated random normal distribution of values.
layer_input Input layer
layer_average_pooling_3d Average pooling operation for 3D data (spatial or spatio-temporal).
texts_to_sequences_generator Transforms each text in texts in a sequence of integers.
predict_proba Generates probability or class probability predictions for the input samples.
layer_locally_connected_2d Locally-connected layer for 2D inputs.
layer_conv_lstm_2d Convolutional LSTM.
layer_max_pooling_1d Max pooling operation for temporal data.
layer_cropping_3d Cropping layer for 3D data (e.g. spatial or spatio-temporal).
layer_zero_padding_1d Zero-padding layer for 1D input (e.g. temporal sequence).
layer_flatten Flattens an input
layer_separable_conv_2d Separable 2D convolution.
layer_multiply Layer that multiplies (element-wise) a list of inputs.
layer_global_average_pooling_1d Global average pooling operation for temporal data.
layer_batch_normalization Batch normalization layer (Ioffe and Szegedy, 2014).
serialize_model Serialize a model to an R object
time_distributed Apply a layer to every temporal slice of an input.
layer_dot Layer that computes a dot product between samples in two tensors.
layer_reshape Reshapes an output to a certain shape.
model_to_json Model configuration as JSON
layer_zero_padding_3d Zero-padding layer for 3D data (spatial or spatio-temporal).
layer_spatial_dropout_2d Spatial 2D version of Dropout.
layer_cropping_1d Cropping layer for 1D input (e.g. temporal sequence).
train_on_batch Single gradient update or model evaluation over one batch of samples.
layer_minimum Layer that computes the minimum (element-wise) a list of inputs.
layer_dropout Applies Dropout to the input.
layer_upsampling_3d Upsampling layer for 3D inputs.
layer_lstm Long Short-Term Memory unit - Hochreiter 1997.
layer_simple_rnn Fully-connected RNN where the output is to be fed back to input.
save_model_hdf5 Save/Load models using HDF5 files
layer_spatial_dropout_3d Spatial 3D version of Dropout.
normalize Normalize a matrix or nd-array
texts_to_matrix Convert a list of texts to a matrix.
layer_spatial_dropout_1d Spatial 1D version of Dropout.
optimizer_sgd Stochastic gradient descent optimizer
model_to_yaml Model configuration as YAML
save_model_weights_hdf5 Save/Load model weights using HDF5 files
layer_zero_padding_2d Zero-padding layer for 2D input (e.g. picture).
optimizer_adadelta Adadelta optimizer.
%<-% Assign values to names
reset_states Reset the states for a layer
skipgrams Generates skipgram word pairs.
text_to_word_sequence Convert text to a sequence of words (or tokens).
plot.keras_training_history Plot training history
text_hashing_trick Converts a text to a sequence of indexes in a fixed-size hashing space.
predict_generator Generates predictions for the input samples from a data generator.
optimizer_adamax Adamax optimizer
timeseries_generator Utility function for generating batches of temporal data.
loss_mean_squared_error Model loss functions
save_text_tokenizer Save a text tokenizer to an external file
text_tokenizer Text tokenization utility
predict.keras.engine.training.Model Generate predictions from a Keras model
multi_gpu_model Replicates a model on different GPUs.
optimizer_nadam Nesterov Adam optimizer
pop_layer Remove the last layer in a model
reexports Objects exported from other packages
pad_sequences Pads sequences to the same length
%>% Pipe operator
with_custom_object_scope Provide a scope with mappings of names to custom objects
regularizer_l1 L1 and L2 regularization
texts_to_sequences Transform each text in texts in a sequence of integers.
use_implementation Select a Keras implementation and backend
summary.keras.engine.training.Model Print a summary of a Keras model
text_one_hot One-hot encode a text into a list of word indexes in a vocabulary of size n.
to_categorical Converts a class vector (integers) to binary class matrix.
KerasConstraint Base R6 class for Keras constraints
callback_lambda Create a custom callback
No Results!

Vignettes of keras

Name
images/MNIST.png
images/arxiv-mentions.png
images/aws-logo.png
images/baseline_model.png
images/boston_mae.png
images/boston_mae_earlystop.png
images/fashion_mnist.png
images/fashion_mnist_classes.png
images/fashion_mnist_heatmap.png
images/fashion_mnist_predictions.png
images/favicon.ico
images/google-logo.png
images/imdb_losscurve.png
images/losscurves_dropout.png
images/losscurves_l2.png
images/losscurves_overfitting.png
images/microsoft-logo.png
images/multi-hot.png
images/multi-input-multi-output-graph.png
images/nvidia-logo.png
images/regular_stacked_lstm.png
images/tensorboard.png
images/tensorboard_compare.png
images/training_history_ggplot2.png
about_keras_layers.Rmd
about_keras_models.Rmd
applications.Rmd
backend.Rmd
checkpoints.h5
custom_layers.Rmd
custom_models.Rmd
custom_wrappers.Rmd
eager_guide.Rmd
faq.Rmd
functional_api.Rmd
getting_started.Rmd
guide_keras.Rmd
sequential_model.Rmd
training_callbacks.Rmd
training_visualization.Rmd
tutorial_basic_classification.Rmd
tutorial_basic_regression.Rmd
tutorial_basic_text_classification.Rmd
tutorial_overfit_underfit.Rmd
tutorial_save_and_restore.Rmd
why_use_keras.Rmd
No Results!

Last month downloads

Details

Type Package
Encoding UTF-8
License MIT + file LICENSE
URL https://keras.rstudio.com
BugReports https://github.com/rstudio/keras/issues
SystemRequirements Keras >= 2.0 (https://keras.io)
RoxygenNote 6.1.0.9000
VignetteBuilder knitr
NeedsCompilation no
Packaged 2018-11-22 03:09:34 UTC; jjallaire
Repository CRAN
Date/Publication 2018-11-22 14:00:03 UTC

Include our badge in your README

[![Rdoc](http://www.rdocumentation.org/badges/version/keras)](http://www.rdocumentation.org/packages/keras)