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