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