keras v2.2.4.1

Monthly downloads

by Daniel Falbel View Source

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
dataset_boston_housing	Boston housing price regression dataset
callback_csv_logger	Callback that streams epoch results to a csv file
backend	Keras backend tensor engine
callback_reduce_lr_on_plateau	Reduce learning rate when a metric has stopped improving.
flow_images_from_dataframe	Takes the dataframe and the path to a directory and generates batches of augmented/normalized data.
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.
KerasConstraint	Base R6 class for Keras constraints
bidirectional	Bidirectional wrapper for RNNs.
KerasCallback	Base R6 class for Keras callbacks
application_vgg	VGG16 and VGG19 models for Keras.
dataset_cifar10	CIFAR10 small image classification
get_file	Downloads a file from a URL if it not already in the cache.
dataset_fashion_mnist	Fashion-MNIST database of fashion articles
application_xception	Xception V1 model for Keras.
callback_progbar_logger	Callback that prints metrics to stdout.
dataset_cifar100	CIFAR100 small image classification
callback_model_checkpoint	Save the model after every epoch.
flow_images_from_directory	Generates batches of data from images in a directory (with optional augmented/normalized data)
callback_early_stopping	Stop training when a monitored quantity has stopped improving.
freeze_weights	Freeze and unfreeze weights
application_inception_resnet_v2	Inception-ResNet v2 model, with weights trained on ImageNet
fit_image_data_generator	Fit image data generator internal statistics to some sample data.
fit_text_tokenizer	Update tokenizer internal vocabulary based on a list of texts or list of sequences.
callback_terminate_on_naan	Callback that terminates training when a NaN loss is encountered.
application_resnet50	ResNet50 model for Keras.
callback_tensorboard	TensorBoard basic visualizations
constraints	Weight constraints
hdf5_matrix	Representation of HDF5 dataset to be used instead of an R array
image_data_generator	Generate batches of image data with real-time data augmentation. The data will be looped over (in batches).
generator_next	Retrieve the next item from a generator
count_params	Count the total number of scalars composing the weights.
dataset_reuters	Reuters newswire topics classification
get_input_at	Retrieve tensors for layers with multiple nodes
initializer_he_normal	He normal initializer.
initializer_he_uniform	He uniform variance scaling initializer.
initializer_random_uniform	Initializer that generates tensors with a uniform distribution.
create_wrapper	Create a Keras Wrapper
create_layer	Create a Keras Layer
application_inception_v3	Inception V3 model, with weights pre-trained on ImageNet.
initializer_truncated_normal	Initializer that generates a truncated normal distribution.
k_batch_flatten	Turn a nD tensor into a 2D tensor with same 1st dimension.
get_config	Layer/Model configuration
k_batch_get_value	Returns the value of more than one tensor variable.
callback_lambda	Create a custom callback
k_abs	Element-wise absolute value.
callback_learning_rate_scheduler	Learning rate scheduler.
k_all	Bitwise reduction (logical AND).
k_categorical_crossentropy	Categorical crossentropy between an output tensor and a target tensor.
k_clear_session	Destroys the current TF graph and creates a new one.
implementation	Keras implementation
initializer_constant	Initializer that generates tensors initialized to a constant value.
k_ctc_batch_cost	Runs CTC loss algorithm on each batch element.
dataset_imdb	IMDB Movie reviews sentiment classification
evaluate.keras.engine.training.Model	Evaluate a Keras model
k_ctc_decode	Decodes the output of a softmax.
k_dtype	Returns the dtype of a Keras tensor or variable, as a string.
k_elu	Exponential linear unit.
k_batch_normalization	Applies batch normalization on x given mean, var, beta and gamma.
k_batch_set_value	Sets the values of many tensor variables at once.
dataset_mnist	MNIST database of handwritten digits
k_foldl	Reduce elems using fn to combine them from left to right.
k_foldr	Reduce elems using fn to combine them from right to left.
fit_generator	Fits the model on data yielded batch-by-batch by a generator.
fit.keras.engine.training.Model	Train a Keras model
evaluate_generator	Evaluates the model on a data generator.
k_greater_equal	Element-wise truth value of (x >= y).
install_keras	Install Keras and the TensorFlow backend
export_savedmodel.keras.engine.training.Model	Export a Saved Model
get_layer	Retrieves a layer based on either its name (unique) or index.
get_weights	Layer/Model weights as R arrays
initializer_glorot_normal	Glorot normal initializer, also called Xavier normal initializer.
initializer_glorot_uniform	Glorot uniform initializer, also called Xavier uniform initializer.
imagenet_decode_predictions	Decodes the prediction of an ImageNet model.
imagenet_preprocess_input	Preprocesses a tensor or array encoding a batch of images.
initializer_lecun_uniform	LeCun uniform initializer.
initializer_ones	Initializer that generates tensors initialized to 1.
k_hard_sigmoid	Segment-wise linear approximation of sigmoid.
k_argmax	Returns the index of the maximum value along an axis.
image_load	Loads an image into PIL format.
image_to_array	3D array representation of images
is_keras_available	Check if Keras is Available
k_conv2d	2D convolution.
initializer_identity	Initializer that generates the identity matrix.
k_conv2d_transpose	2D deconvolution (i.e. transposed convolution).
k_cast	Casts a tensor to a different dtype and returns it.
k_log	Element-wise log.
initializer_orthogonal	Initializer that generates a random orthogonal matrix.
initializer_random_normal	Initializer that generates tensors with a normal distribution.
k_any	Bitwise reduction (logical OR).
initializer_lecun_normal	LeCun normal initializer.
k_logsumexp	Computes log(sum(exp(elements across dimensions of a tensor))).
k_ctc_label_dense_to_sparse	Converts CTC labels from dense to sparse.
k_mean	Mean of a tensor, alongside the specified axis.
k_arange	Creates a 1D tensor containing a sequence of integers.
k_cos	Computes cos of x element-wise.
k_cast_to_floatx	Cast an array to the default Keras float type.
k_min	Minimum value in a tensor.
k_argmin	Returns the index of the minimum value along an axis.
k_constant	Creates a constant tensor.
k_permute_dimensions	Permutes axes in a tensor.
k_cumprod	Cumulative product of the values in a tensor, alongside the specified axis.
k_eval	Evaluates the value of a variable.
k_exp	Element-wise exponential.
k_get_value	Returns the value of a variable.
k_get_variable_shape	Returns the shape of a variable.
initializer_zeros	Initializer that generates tensors initialized to 0.
initializer_variance_scaling	Initializer capable of adapting its scale to the shape of weights.
k_batch_dot	Batchwise dot product.
k_backend	Active Keras backend
k_count_params	Returns the static number of elements in a Keras variable or tensor.
k_conv1d	1D convolution.
k_cumsum	Cumulative sum of the values in a tensor, alongside the specified axis.
k_bias_add	Adds a bias vector to a tensor.
k_placeholder	Instantiates a placeholder tensor and returns it.
k_depthwise_conv2d	Depthwise 2D convolution with separable filters.
k_function	Instantiates a Keras function
k_gather	Retrieves the elements of indices indices in the tensor reference.
k_binary_crossentropy	Binary crossentropy between an output tensor and a target tensor.
k_clip	Element-wise value clipping.
k_concatenate	Concatenates a list of tensors alongside the specified axis.
k_expand_dims	Adds a 1-sized dimension at index axis.
k_eye	Instantiate an identity matrix and returns it.
k_l2_normalize	Normalizes a tensor wrt the L2 norm alongside the specified axis.
k_learning_phase	Returns the learning phase flag.
k_less	Element-wise truth value of (x < y).
k_less_equal	Element-wise truth value of (x <= y).
k_gradients	Returns the gradients of variables w.r.t. loss.
k_relu	Rectified linear unit.
k_dot	Multiplies 2 tensors (and/or variables) and returns a tensor.
k_greater	Element-wise truth value of (x > y).
k_conv3d	3D convolution.
k_minimum	Element-wise minimum of two tensors.
k_repeat	Repeats a 2D tensor.
k_in_test_phase	Selects x in test phase, and alt otherwise.
k_conv3d_transpose	3D deconvolution (i.e. transposed convolution).
k_moving_average_update	Compute the moving average of a variable.
k_in_train_phase	Selects x in train phase, and alt otherwise.
k_int_shape	Returns the shape of tensor or variable as a list of int or NULL entries.
k_dropout	Sets entries in x to zero at random, while scaling the entire tensor.
k_max	Maximum value in a tensor.
k_maximum	Element-wise maximum of two tensors.
k_random_normal	Returns a tensor with normal distribution of values.
k_prod	Multiplies the values in a tensor, alongside the specified axis.
k_random_binomial	Returns a tensor with random binomial distribution of values.
k_in_top_k	Returns whether the targets are in the top k predictions.
k_epsilon	Fuzz factor used in numeric expressions.
k_flatten	Flatten a tensor.
k_reshape	Reshapes a tensor to the specified shape.
k_equal	Element-wise equality between two tensors.
k_resize_images	Resizes the images contained in a 4D tensor.
k_floatx	Default float type
k_sin	Computes sin of x element-wise.
k_random_normal_variable	Instantiates a variable with values drawn from a normal distribution.
k_get_session	TF session to be used by the backend.
k_manual_variable_initialization	Sets the manual variable initialization flag.
k_softmax	Softmax of a tensor.
k_identity	Returns a tensor with the same content as the input tensor.
k_map_fn	Map the function fn over the elements elems and return the outputs.
k_ndim	Returns the number of axes in a tensor, as an integer.
k_normalize_batch_in_training	Computes mean and std for batch then apply batch_normalization on batch.
k_pool2d	2D Pooling.
k_softplus	Softplus of a tensor.
k_image_data_format	Default image data format convention ('channels_first' or 'channels_last').
k_get_uid	Get the uid for the default graph.
k_random_uniform	Returns a tensor with uniform distribution of values.
k_softsign	Softsign of a tensor.
k_random_uniform_variable	Instantiates a variable with values drawn from a uniform distribution.
k_separable_conv2d	2D convolution with separable filters.
k_is_sparse	Returns whether a tensor is a sparse tensor.
k_is_tensor	Returns whether x is a symbolic tensor.
k_temporal_padding	Pads the middle dimension of a 3D tensor.
k_tile	Creates a tensor by tiling x by n.
k_ones	Instantiates an all-ones tensor variable and returns it.
k_ones_like	Instantiates an all-ones variable of the same shape as another tensor.
keras_model	Keras Model
k_set_learning_phase	Sets the learning phase to a fixed value.
keras_model_custom	Create a Keras custom model
k_pow	Element-wise exponentiation.
k_pool3d	3D Pooling.
k_is_keras_tensor	Returns whether x is a Keras tensor.
k_stack	Stacks a list of rank R tensors into a rank R+1 tensor.
k_print_tensor	Prints message and the tensor value when evaluated.
k_repeat_elements	Repeats the elements of a tensor along an axis.
k_std	Standard deviation of a tensor, alongside the specified axis.
k_reset_uids	Reset graph identifiers.
k_to_dense	Converts a sparse tensor into a dense tensor and returns it.
k_transpose	Transposes a tensor and returns it.
keras-package	R interface to Keras
k_is_placeholder	Returns whether x is a placeholder.
keras_array	Keras array object
k_set_value	Sets the value of a variable, from an R array.
k_shape	Returns the symbolic shape of a tensor or variable.
keras_model_sequential	Keras Model composed of a linear stack of layers
layer_cudnn_lstm	Fast LSTM implementation backed by CuDNN.
k_rnn	Iterates over the time dimension of a tensor
k_round	Element-wise rounding to the closest integer.
layer_activation	Apply an activation function to an output.
k_spatial_3d_padding	Pads 5D tensor with zeros along the depth, height, width dimensions.
k_local_conv1d	Apply 1D conv with un-shared weights.
layer_add	Layer that adds a list of inputs.
k_sqrt	Element-wise square root.
layer_alpha_dropout	Applies Alpha Dropout to the input.
k_local_conv2d	Apply 2D conv with un-shared weights.
k_sparse_categorical_crossentropy	Categorical crossentropy with integer targets.
k_not_equal	Element-wise inequality between two tensors.
k_one_hot	Computes the one-hot representation of an integer tensor.
k_spatial_2d_padding	Pads the 2nd and 3rd dimensions of a 4D tensor.
k_square	Element-wise square.
k_stop_gradient	Returns variables but with zero gradient w.r.t. every other variable.
k_switch	Switches between two operations depending on a scalar value.
k_tanh	Element-wise tanh.
layer_dense	Add a densely-connected NN layer to an output
layer_conv_2d_transpose	Transposed 2D convolution layer (sometimes called Deconvolution).
k_update_add	Update the value of x by adding increment.
k_resize_volumes	Resizes the volume contained in a 5D tensor.
k_sum	Sum of the values in a tensor, alongside the specified axis.
k_var	Variance of a tensor, alongside the specified axis.
k_squeeze	Removes a 1-dimension from the tensor at index axis.
k_variable	Instantiates a variable and returns it.
layer_conv_3d	3D convolution layer (e.g. spatial convolution over volumes).
layer_activation_selu	Scaled Exponential Linear Unit.
layer_activation_softmax	Softmax activation function.
layer_depthwise_conv_2d	Depthwise separable 2D convolution.
k_reverse	Reverse a tensor along the specified axes.
layer_average_pooling_2d	Average pooling operation for spatial data.
layer_average_pooling_3d	Average pooling operation for 3D data (spatial or spatio-temporal).
k_update_sub	Update the value of x by subtracting decrement.
layer_dot	Layer that computes a dot product between samples in two tensors.
layer_activation_elu	Exponential Linear Unit.
k_zeros	Instantiates an all-zeros variable and returns it.
k_zeros_like	Instantiates an all-zeros variable of the same shape as another tensor.
layer_activation_leaky_relu	Leaky version of a Rectified Linear Unit.
layer_conv_1d	1D convolution layer (e.g. temporal convolution).
layer_conv_2d	2D convolution layer (e.g. spatial convolution over images).
layer_locally_connected_1d	Locally-connected layer for 1D inputs.
layer_global_max_pooling_1d	Global max pooling operation for temporal data.
layer_locally_connected_2d	Locally-connected layer for 2D inputs.
layer_global_max_pooling_2d	Global max pooling operation for spatial data.
layer_gaussian_noise	Apply additive zero-centered Gaussian noise.
layer_upsampling_1d	Upsampling layer for 1D inputs.
layer_global_average_pooling_1d	Global average pooling operation for temporal data.
layer_reshape	Reshapes an output to a certain shape.
layer_lstm	Long Short-Term Memory unit - Hochreiter 1997.
layer_masking	Masks a sequence by using a mask value to skip timesteps.
layer_upsampling_2d	Upsampling layer for 2D inputs.
model_to_yaml	Model configuration as YAML
k_sigmoid	Element-wise sigmoid.
k_sign	Element-wise sign.
layer_minimum	Layer that computes the minimum (element-wise) a list of inputs.
%<-%	Assign values to names
layer_separable_conv_1d	Depthwise separable 1D convolution.
layer_multiply	Layer that multiplies (element-wise) a list of inputs.
layer_spatial_dropout_3d	Spatial 3D version of Dropout.
optimizer_nadam	Nesterov Adam optimizer
layer_separable_conv_2d	Separable 2D convolution.
layer_activation_parametric_relu	Parametric Rectified Linear Unit.
layer_subtract	Layer that subtracts two inputs.
loss_mean_squared_error	Model loss functions
layer_simple_rnn	Fully-connected RNN where the output is to be fed back to input.
make_sampling_table	Generates a word rank-based probabilistic sampling table.
layer_zero_padding_2d	Zero-padding layer for 2D input (e.g. picture).
plot.keras_training_history	Plot training history
%>%	Pipe operator
layer_cropping_3d	Cropping layer for 3D data (e.g. spatial or spatio-temporal).
layer_zero_padding_3d	Zero-padding layer for 3D data (spatial or spatio-temporal).
layer_cudnn_gru	Fast GRU implementation backed by CuDNN.
regularizer_l1	L1 and L2 regularization
reset_states	Reset the states for a layer
layer_activation_relu	Rectified Linear Unit activation function
layer_dropout	Applies Dropout to the input.
optimizer_rmsprop	RMSProp optimizer
layer_batch_normalization	Batch normalization layer (Ioffe and Szegedy, 2014).
predict_generator	Generates predictions for the input samples from a data generator.
predict_on_batch	Returns predictions for a single batch of samples.
serialize_model	Serialize a model to an R object
layer_embedding	Turns positive integers (indexes) into dense vectors of fixed size.
skipgrams	Generates skipgram word pairs.
layer_max_pooling_1d	Max pooling operation for temporal data.
text_one_hot	One-hot encode a text into a list of word indexes in a vocabulary of size n.
text_to_word_sequence	Convert text to a sequence of words (or tokens).
to_categorical	Converts a class vector (integers) to binary class matrix.
k_truncated_normal	Returns a tensor with truncated random normal distribution of values.
train_on_batch	Single gradient update or model evaluation over one batch of samples.
layer_concatenate	Layer that concatenates a list of inputs.
k_update	Update the value of x to new_x.
use_implementation	Select a Keras implementation and backend
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_spatial_dropout_1d	Spatial 1D version of Dropout.
layer_spatial_dropout_2d	Spatial 2D version of Dropout.
metric_binary_accuracy	Model performance metrics
model_to_json	Model configuration as JSON
layer_activation_thresholded_relu	Thresholded Rectified Linear Unit.
layer_cropping_1d	Cropping layer for 1D input (e.g. temporal sequence).
optimizer_adadelta	Adadelta optimizer.
layer_activity_regularization	Layer that applies an update to the cost function based input activity.
layer_average	Layer that averages a list of inputs.
layer_average_pooling_1d	Average pooling for temporal data.
optimizer_adagrad	Adagrad optimizer.
layer_cropping_2d	Cropping layer for 2D input (e.g. picture).
pop_layer	Remove the last layer in a model
predict.keras.engine.training.Model	Generate predictions from a Keras model
layer_conv_3d_transpose	Transposed 3D convolution layer (sometimes called Deconvolution).
layer_conv_lstm_2d	Convolutional LSTM.
layer_flatten	Flattens an input
save_text_tokenizer	Save a text tokenizer to an external file
sequences_to_matrix	Convert a list of sequences into a matrix.
layer_gaussian_dropout	Apply multiplicative 1-centered Gaussian noise.
layer_global_average_pooling_2d	Global average pooling operation for spatial data.
layer_global_max_pooling_3d	Global Max pooling operation for 3D data.
layer_gru	Gated Recurrent Unit - Cho et al.
layer_global_average_pooling_3d	Global Average pooling operation for 3D data.
layer_input	Input layer
layer_lambda	Wraps arbitrary expression as a layer
layer_max_pooling_3d	Max pooling operation for 3D data (spatial or spatio-temporal).
layer_permute	Permute the dimensions of an input according to a given pattern
layer_maximum	Layer that computes the maximum (element-wise) a list of inputs.
layer_repeat_vector	Repeats the input n times.
layer_upsampling_3d	Upsampling layer for 3D inputs.
layer_zero_padding_1d	Zero-padding layer for 1D input (e.g. temporal sequence).
multi_gpu_model	Replicates a model on different GPUs.
optimizer_sgd	Stochastic gradient descent optimizer
normalize	Normalize a matrix or nd-array
pad_sequences	Pads sequences to the same length
save_model_hdf5	Save/Load models using HDF5 files
save_model_weights_hdf5	Save/Load model weights using HDF5 files
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.
optimizer_adam	Adam optimizer
time_distributed	Apply a layer to every temporal slice of an input.
optimizer_adamax	Adamax optimizer
predict_proba	Generates probability or class probability predictions for the input samples.
timeseries_generator	Utility function for generating batches of temporal data.
reexports	Objects exported from other packages
text_tokenizer	Text tokenization utility
texts_to_matrix	Convert a list of texts to a matrix.
texts_to_sequences	Transform each text in texts in a sequence of integers.
texts_to_sequences_generator	Transforms each text in texts in a sequence of integers.
application_nasnet	Instantiates a NASNet model.
KerasLayer	Base R6 class for Keras layers
KerasWrapper	Base R6 class for Keras wrappers
application_mobilenet	MobileNet model architecture.
application_mobilenet_v2	MobileNetV2 model architecture
activation_relu	Activation functions
application_densenet	Instantiates the DenseNet architecture.
clone_model	Clone a model instance.
compile.keras.engine.training.Model	Configure a Keras model for training
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
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	6.1.1
VignetteBuilder	knitr
NeedsCompilation	no
Packaged	2019-04-05 14:46:57 UTC; dfalbel
Repository	CRAN
Date/Publication	2019-04-05 21:30:08 UTC

imports	generics (>= 0.0.1) , magrittr , methods , R6 , reticulate (>= 1.10) , tensorflow (>= 1.13.1) , tfruns (>= 1.0) , zeallot
suggests	ggplot2 , knitr , rmarkdown , testthat
depends	R (>= 3.2)
Contributors	Yuan Tang, JJ Allaire, RStudio, Fran<c3><a7>ois Chollet, Google, Wouter Van Der Bijl, Martin Studer, Sigrid Keydana