Base R6 class for Keras constraints
MobileNetV2 model architecture
Base R6 class for Keras callbacks
Instantiates the DenseNet architecture.
application_inception_resnet_v2
Inception-ResNet v2 model, with weights trained on ImageNet
Activation functions
Base R6 class for Keras layers
Base R6 class for Keras wrappers
MobileNet model architecture.
Inception V3 model, with weights pre-trained on ImageNet.
Callback that streams epoch results to a csv file
Xception V1 model for Keras.
VGG16 and VGG19 models for Keras.
Stop training when a monitored quantity has stopped improving.
Weight constraints
Count the total number of scalars composing the weights.
Keras backend tensor engine
Callback used to stream events to a server.
callback_reduce_lr_on_plateau
Reduce learning rate when a metric has stopped improving.
Bidirectional wrapper for RNNs.
Callback that prints metrics to stdout.
callback_model_checkpoint
Save the model after every epoch.
Create a Keras Layer
Create a Keras Wrapper
evaluate.keras.engine.training.Model
Evaluate a Keras model
Reuters newswire topics classification
Fashion-MNIST database of fashion articles
Create a custom callback
CIFAR100 small image classification
callback_terminate_on_naan
Callback that terminates training when a NaN loss is encountered.
callback_learning_rate_scheduler
Learning rate scheduler.
TensorBoard basic visualizations
Instantiates a NASNet model.
Clone a model instance.
compile.keras.engine.training.Model
Configure a Keras model for training
MNIST database of handwritten digits
IMDB Movie reviews sentiment classification
CIFAR10 small image classification
Boston housing price regression dataset
ResNet50 model for Keras.
flow_images_from_directory
Generates batches of data from images in a directory (with optional
augmented/normalized data)
Generates batches of augmented/normalized data from image data and labels
Evaluates the model on a data generator.
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.
Fit image data generator internal statistics to some sample data.
Update tokenizer internal vocabulary based on a list of texts or list of
sequences.
export_savedmodel.keras.engine.training.Model
Export a Saved Model
Freeze and unfreeze weights
Generate batches of image data with real-time data augmentation. The data will be
looped over (in batches).
Loads an image into PIL format.
Fits the model on data yielded batch-by-batch by a generator.
Representation of HDF5 dataset to be used instead of an R array
Retrieve the next item from a generator
Layer/Model configuration
imagenet_decode_predictions
Decodes the prediction of an ImageNet model.
Initializer that generates the identity matrix.
Downloads a file from a URL if it not already in the cache.
Keras implementation
initializer_glorot_normal
Glorot normal initializer, also called Xavier normal initializer.
3D array representation of images
initializer_glorot_uniform
Glorot uniform initializer, also called Xavier uniform initializer.
Layer/Model weights as R arrays
Retrieves a layer based on either its name (unique) or index.
Install Keras and the TensorFlow backend
LeCun normal initializer.
Initializer that generates a random orthogonal matrix.
initializer_random_normal
Initializer that generates tensors with a normal distribution.
imagenet_preprocess_input
Preprocesses a tensor or array encoding a batch of images.
Turn a nD tensor into a 2D tensor with same 1st dimension.
Retrieve tensors for layers with multiple nodes
Active Keras backend
Applies batch normalization on x given mean, var, beta and gamma.
Returns the value of more than one tensor variable.
initializer_random_uniform
Initializer that generates tensors with a uniform distribution.
initializer_truncated_normal
Initializer that generates a truncated normal distribution.
Returns the index of the minimum value along an axis.
Returns the index of the maximum value along an axis.
He normal initializer.
He uniform variance scaling initializer.
Check if Keras is Available
Sets the values of many tensor variables at once.
Creates a constant tensor.
Bitwise reduction (logical OR).
Batchwise dot product.
Element-wise value clipping.
initializer_variance_scaling
Initializer capable of adapting its scale to the shape of weights.
Initializer that generates tensors initialized to 0.
Element-wise absolute value.
Bitwise reduction (logical AND).
k_categorical_crossentropy
Categorical crossentropy between an output tensor and a target tensor.
Cast an array to the default Keras float type.
Casts a tensor to a different dtype and returns it.
Initializer that generates tensors initialized to a constant value.
Concatenates a list of tensors alongside the specified axis.
1D convolution.
Destroys the current TF graph and creates a new one.
Decodes the output of a softmax.
Runs CTC loss algorithm on each batch element.
Fuzz factor used in numeric expressions.
Adds a 1-sized dimension at index axis
.
Element-wise equality between two tensors.
3D convolution.
3D deconvolution (i.e. transposed convolution).
k_ctc_label_dense_to_sparse
Converts CTC labels from dense to sparse.
Cumulative product of the values in a tensor, alongside the specified axis.
Evaluates the value of a variable.
Depthwise 2D convolution with separable filters.
Cumulative sum of the values in a tensor, alongside the specified axis.
Element-wise exponential.
initializer_lecun_uniform
LeCun uniform initializer.
Initializer that generates tensors initialized to 1.
2D convolution.
Returns the value of a variable.
Creates a 1D tensor containing a sequence of integers.
Element-wise log.
Selects x
in test phase, and alt
otherwise.
Returns whether the targets
are in the top k
predictions
.
Returns the shape of a variable.
Computes log(sum(exp(elements across dimensions of a tensor))).
Instantiate an identity matrix and returns it.
Returns a tensor with the same content as the input tensor.
Instantiates a Keras function
Binary crossentropy between an output tensor and a target tensor.
Adds a bias vector to a tensor.
Computes cos of x element-wise.
Returns the static number of elements in a Keras variable or tensor.
Selects x
in train phase, and alt
otherwise.
Exponential linear unit.
Returns the shape of tensor or variable as a list of int or NULL entries.
Returns the dtype of a Keras tensor or variable, as a string.
Retrieves the elements of indices indices
in the tensor reference
.
Element-wise truth value of (x >= y).
Multiplies 2 tensors (and/or variables) and returns a tensor .
2D deconvolution (i.e. transposed convolution).
Sets entries in x
to zero at random, while scaling the entire tensor.
Instantiates an all-ones tensor variable and returns it.
Flatten a tensor.
Default float type
Element-wise truth value of (x < y).
Get the uid for the default graph.
TF session to be used by the backend.
Segment-wise linear approximation of sigmoid.
Instantiates a variable with values drawn from a normal distribution.
Returns a tensor with normal distribution of values.
Reduce elems using fn to combine them from left to right.
Element-wise truth value of (x <= y).
Instantiates an all-ones variable of the same shape as another tensor.
Mean of a tensor, alongside the specified axis.
Permutes axes in a tensor.
Returns whether x
is a symbolic tensor.
Apply 2D conv with un-shared weights.
Computes the one-hot representation of an integer tensor.
Element-wise exponentiation.
Apply 1D conv with un-shared weights.
Default image data format convention ('channels_first' or 'channels_last').
Returns whether a tensor is a sparse tensor.
Element-wise inequality between two tensors.
Reduce elems using fn to combine them from right to left.
Instantiates a placeholder tensor and returns it.
Prints message
and the tensor value when evaluated.
Element-wise truth value of (x > y).
Element-wise maximum of two tensors.
Returns whether x
is a placeholder.
Returns the gradients of variables
w.r.t. loss
.
Maximum value in a tensor.
Returns whether x
is a Keras tensor.
Sets the learning phase to a fixed value.
2D convolution with separable filters.
Pads 5D tensor with zeros along the depth, height, width dimensions.
Element-wise square root.
Returns the number of axes in a tensor, as an integer.
Switches between two operations depending on a scalar value.
Element-wise rounding to the closest integer.
Resizes the images contained in a 4D tensor.
Reshapes a tensor to the specified shape.
Iterates over the time dimension of a tensor
Minimum value in a tensor.
Normalizes a tensor wrt the L2 norm alongside the specified axis.
Map the function fn over the elements elems and return the outputs.
k_manual_variable_initialization
Sets the manual variable initialization flag.
Returns the learning phase flag.
k_normalize_batch_in_training
Computes mean and std for batch then apply batch_normalization on batch.
Pads the middle dimension of a 3D tensor.
Element-wise minimum of two tensors.
Reverse a tensor along the specified axes.
3D Pooling.
2D Pooling.
Sets the value of a variable, from an R array.
Resizes the volume contained in a 5D tensor.
Returns the symbolic shape of a tensor or variable.
Repeats the elements of a tensor along an axis.
Element-wise square.
Removes a 1-dimension from the tensor at index axis
.
Rectified linear unit.
Reset graph identifiers.
Keras Model
Creates a tensor by tiling x
by n
.
layer_activity_regularization
Layer that applies an update to the cost function based input activity.
layer_activation_thresholded_relu
Thresholded Rectified Linear Unit.
Create a Keras custom model
Instantiates an all-zeros variable of the same shape as another tensor.
Repeats a 2D tensor.
Instantiates an all-zeros variable and returns it.
Keras Model composed of a linear stack of layers
Element-wise tanh.
Stacks a list of rank R
tensors into a rank R+1
tensor.
Transposes a tensor and returns it.
Keras array object
R interface to Keras
Converts a sparse tensor into a dense tensor and returns it.
Compute the moving average of a variable.
Scaled Exponential Linear Unit.
Max pooling operation for temporal data.
Masks a sequence by using a mask value to skip timesteps.
Upsampling layer for 3D inputs.
Upsampling layer for 2D inputs.
Variance of a tensor, alongside the specified axis.
Instantiates a variable and returns it.
Standard deviation of a tensor, alongside the specified axis.
layer_activation_parametric_relu
Parametric Rectified Linear Unit.
Rectified Linear Unit activation function
Multiplies the values in a tensor, alongside the specified axis.
Softmax activation function.
Average pooling operation for 3D data (spatial or spatio-temporal).
Average pooling operation for spatial data.
Cropping layer for 3D data (e.g. spatial or spatio-temporal).
Fast GRU implementation backed by CuDNN . Add a densely-connected NN layer to an output
2D convolution layer (e.g. spatial convolution over images).
Depthwise separable 2D convolution.
Constructs a DenseFeatures.
Fast LSTM implementation backed by CuDNN . 1D convolution layer (e.g. temporal convolution).
Returns a tensor with random binomial distribution of values.
Long Short-Term Memory unit - Hochreiter 1997.
layer_locally_connected_2d
Locally-connected layer for 2D inputs.
Max pooling operation for spatial data.
Apply an activation function to an output.
Average pooling for temporal data.
Cropping layer for 2D input (e.g. picture).
Turns positive integers (indexes) into dense vectors of fixed size.
Layer that averages a list of inputs.
Cropping layer for 1D input (e.g. temporal sequence).
Element-wise sigmoid.
Depthwise separable 1D convolution.
Separable 2D convolution.
Max pooling operation for 3D data (spatial or spatio-temporal).
Zero-padding layer for 1D input (e.g. temporal sequence).
Flattens an input
Element-wise sign.
Softplus of a tensor.
Softsign of a tensor.
Returns a tensor with truncated random normal distribution of values.
Wraps arbitrary expression as a layer
Export to Saved Model format
Model configuration as YAML
predict.keras.engine.training.Model
Generate predictions from a Keras model
Generates predictions for the input samples from a data generator.
Exponential Linear Unit.
Layer that adds a list of inputs.
Update the value of x
to new_x
.
layer_activation_leaky_relu
Leaky version of a Rectified Linear Unit.
Zero-padding layer for 2D input (e.g. picture).
Applies Alpha Dropout to the input.
Text tokenization utility
Save a text tokenizer to an external file
Convert text to a sequence of words (or tokens).
Save model weights in the SavedModel format
Layer that computes the maximum (element-wise) a list of inputs.
layer_locally_connected_1d
Locally-connected layer for 1D inputs.
Layer that computes the minimum (element-wise) a list of inputs.
Fully-connected RNN where the output is to be fed back to input.
Spatial 1D version of Dropout.
Single gradient update or model evaluation over one batch of samples.
Returns a tensor with uniform distribution of values.
Transposed 2D convolution layer (sometimes called Deconvolution).
layer_global_average_pooling_1d
Global average pooling operation for temporal data.
layer_global_average_pooling_2d
Global average pooling operation for spatial data.
layer_global_max_pooling_3d
Global Max pooling operation for 3D data.
Stochastic gradient descent optimizer
Generates probability or class probability predictions for the input samples.
Spatial 3D version of Dropout.
Reset the states for a layer
Spatial 2D version of Dropout.
layer_global_max_pooling_2d
Global max pooling operation for spatial data.
RMSProp optimizer
Returns predictions for a single batch of samples.
3D convolution layer (e.g. spatial convolution over volumes).
Adamax optimizer
Save/Load models using HDF5 files
Select a Keras implementation and backend
Returns variables
but with zero gradient w.r.t. every other variable.
Pads the 2nd and 3rd dimensions of a 4D tensor.
k_sparse_categorical_crossentropy
Categorical crossentropy with integer targets.
Computes sin of x element-wise.
Softmax of a tensor.
k_random_uniform_variable
Instantiates a variable with values drawn from a uniform distribution.
Sum of the values in a tensor, alongside the specified axis.
Apply multiplicative 1-centered Gaussian noise.
Update the value of x
by adding increment
.
Zero-padding layer for 3D data (spatial or spatio-temporal).
Update the value of x
by subtracting decrement
.
Apply additive zero-centered Gaussian noise.
Layer that multiplies (element-wise) a list of inputs.
layer_global_max_pooling_1d
Global max pooling operation for temporal data.
layer_global_average_pooling_3d
Global Average pooling operation for 3D data.
layer_batch_normalization
Batch normalization layer (Ioffe and Szegedy, 2014).
Layer that concatenates a list of inputs.
Transposed 3D convolution layer (sometimes called Deconvolution).
Convolutional LSTM.
Layer that computes a dot product between samples in two tensors.
Applies Dropout to the input.
plot.keras_training_history
Plot training history
Nesterov Adam optimizer
Generates skipgram word pairs.
Remove the last layer in a model
Gated Recurrent Unit - Cho et al.
Generates a word rank-based probabilistic sampling table.
Input layer
Reshapes an output to a certain shape.
Repeats the input n times.
Model performance metrics
Permute the dimensions of an input according to a given pattern
Upsampling layer for 1D inputs.
Load a Keras model from the Saved Model format
Layer that subtracts two inputs.
Model configuration as JSON
texts_to_sequences_generator
Transforms each text in texts in a sequence of integers.
Assign values to names
Replicates a model on different GPUs.
Model loss functions
Normalize a matrix or nd-array
Adagrad optimizer.
Adam optimizer
Objects exported from other packages
L1 and L2 regularization
Save/Load models using SavedModel format
Apply a layer to every temporal slice of an input.
Provide a scope with mappings of names to custom objects
Adadelta optimizer.
Save/Load model weights using HDF5 files
Converts a text to a sequence of indexes in a fixed-size hashing space.
One-hot encode a text into a list of word indexes in a vocabulary of size n.
Pads sequences to the same length
Transform each text in texts in a sequence of integers.
summary.keras.engine.training.Model
Print a summary of a Keras model
Convert a list of texts to a matrix.
Pipe operator
Convert a list of sequences into a matrix.
Serialize a model to an R object
Utility function for generating batches of temporal data.
Converts a class vector (integers) to binary class matrix.