Learn R Programming

keras3 (version 1.3.0)

R Interface to 'Keras'

Description

Interface to 'Keras' , 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.

Copy Link

Version

Install

install.packages('keras3')

Monthly Downloads

4,899

Version

1.3.0

License

MIT + file LICENSE

Issues

114

Pull Requests

0

Stars

846

Forks

283

Maintainer

Tomasz Kalinowski

Last Published

March 3rd, 2025

Functions in keras3 (1.3.0)

activation_elu

Exponential Linear Unit.
Model

Subclass the base Keras Model Class
Constraint

Define a custom Constraint class
activation_celu

Continuously Differentiable Exponential Linear Unit.
activation_exponential

Exponential activation function.
LearningRateSchedule

Define a custom LearningRateSchedule class
Metric

Subclass the base Metric class
Callback

Define a custom Callback class
Loss

Subclass the base Loss class
Layer

Define a custom Layer class.
activation_hard_silu

Hard SiLU activation function, also known as Hard Swish.
activation_hard_shrink

Hard Shrink activation function.
activation_linear

Linear activation function (pass-through).
activation_log_sigmoid

Logarithm of the sigmoid activation function.
activation_glu

Gated Linear Unit (GLU) activation function.
activation_leaky_relu

Leaky relu activation function.
activation_log_softmax

Log-Softmax activation function.
activation_gelu

Gaussian error linear unit (GELU) activation function.
activation_hard_sigmoid

Hard sigmoid activation function.
activation_hard_tanh

HardTanh activation function.
activation_sigmoid

Sigmoid activation function.
activation_softplus

Softplus activation function.
activation_silu

Swish (or Silu) activation function.
activation_soft_shrink

Soft Shrink activation function.
activation_softmax

Softmax converts a vector of values to a probability distribution.
activation_softsign

Softsign activation function.
activation_relu6

Relu6 activation function.
activation_selu

Scaled Exponential Linear Unit (SELU).
activation_tanh_shrink

Tanh shrink activation function.
adapt

Fits the state of the preprocessing layer to the data being passed
activation_sparse_plus

SparsePlus activation function.
activation_squareplus

Squareplus activation function.
activation_tanh

Hyperbolic tangent activation function.
activation_sparsemax

Sparsemax activation function.
active_property

Create an active property class method
activation_mish

Mish activation function.
activation_threshold

Threshold activation function.
application_convnext_large

Instantiates the ConvNeXtLarge architecture.
application_convnext_base

Instantiates the ConvNeXtBase architecture.
activation_relu

Applies the rectified linear unit activation function.
application_convnext_tiny

Instantiates the ConvNeXtTiny architecture.
application_convnext_small

Instantiates the ConvNeXtSmall architecture.
application_densenet169

Instantiates the Densenet169 architecture.
application_convnext_xlarge

Instantiates the ConvNeXtXLarge architecture.
application_densenet121

Instantiates the Densenet121 architecture.
application_densenet201

Instantiates the Densenet201 architecture.
application_efficientnet_v2b3

Instantiates the EfficientNetV2B3 architecture.
application_efficientnet_b0

Instantiates the EfficientNetB0 architecture.
application_efficientnet_v2b2

Instantiates the EfficientNetV2B2 architecture.
application_efficientnet_b1

Instantiates the EfficientNetB1 architecture.
application_efficientnet_b5

Instantiates the EfficientNetB5 architecture.
application_efficientnet_b4

Instantiates the EfficientNetB4 architecture.
application_efficientnet_b6

Instantiates the EfficientNetB6 architecture.
application_efficientnet_b7

Instantiates the EfficientNetB7 architecture.
application_efficientnet_b3

Instantiates the EfficientNetB3 architecture.
application_efficientnet_b2

Instantiates the EfficientNetB2 architecture.
application_efficientnet_v2b0

Instantiates the EfficientNetV2B0 architecture.
application_efficientnet_v2b1

Instantiates the EfficientNetV2B1 architecture.
application_efficientnet_v2m

Instantiates the EfficientNetV2M architecture.
application_efficientnet_v2l

Instantiates the EfficientNetV2L architecture.
application_mobilenet_v3_small

Instantiates the MobileNetV3Small architecture.
application_inception_v3

Instantiates the Inception v3 architecture.
application_nasnet_large

Instantiates a NASNet model in ImageNet mode.
application_mobilenet

Instantiates the MobileNet architecture.
application_nasnet_mobile

Instantiates a Mobile NASNet model in ImageNet mode.
application_resnet101

Instantiates the ResNet101 architecture.
application_efficientnet_v2s

Instantiates the EfficientNetV2S architecture.
application_inception_resnet_v2

Instantiates the Inception-ResNet v2 architecture.
application_mobilenet_v2

Instantiates the MobileNetV2 architecture.
application_resnet50_v2

Instantiates the ResNet50V2 architecture.
application_mobilenet_v3_large

Instantiates the MobileNetV3Large architecture.
application_resnet50

Instantiates the ResNet50 architecture.
application_resnet152_v2

Instantiates the ResNet152V2 architecture.
application_vgg16

Instantiates the VGG16 model.
application_nasnetlarge

Backward compatibility
audio_dataset_from_directory

Generates a tf.data.Dataset from audio files in a directory.
application_xception

Instantiates the Xception architecture.
application_vgg19

Instantiates the VGG19 model.
callback_learning_rate_scheduler

Learning rate scheduler.
callback_lambda

Callback for creating simple, custom callbacks on-the-fly.
callback_remote_monitor

Callback used to stream events to a server.
callback_swap_ema_weights

Swaps model weights and EMA weights before and after evaluation.
callback_backup_and_restore

Callback to back up and restore the training state.
bidirectional

layer_bidirectional
application_resnet101_v2

Instantiates the ResNet101V2 architecture.
application_resnet152

Instantiates the ResNet152 architecture.
callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.
callback_model_checkpoint

Callback to save the Keras model or model weights at some frequency.
callback_csv_logger

Callback that streams epoch results to a CSV file.
callback_early_stopping

Stop training when a monitored metric has stopped improving.
compile.keras.src.models.model.Model

Configure a model for training.
config_backend

Publicly accessible method for determining the current backend.
config_dtype_policy

Returns the current default dtype policy object.
config_disable_traceback_filtering

Turn off traceback filtering.
callback_terminate_on_nan

Callback that terminates training when a NaN loss is encountered.
config_epsilon

Return the value of the fuzz factor used in numeric expressions.
clear_session

Resets all state generated by Keras.
clone_model

Clone a Functional or Sequential Model instance.
callback_tensorboard

Enable visualizations for TensorBoard.
config_enable_traceback_filtering

Turn on traceback filtering.
config_is_interactive_logging_enabled

Check if interactive logging is enabled.
config_is_traceback_filtering_enabled

Check if traceback filtering is enabled.
config_enable_unsafe_deserialization

Disables safe mode globally, allowing deserialization of lambdas.
config_enable_flash_attention

Enable flash attention.
config_enable_interactive_logging

Turn on interactive logging.
config_floatx

Return the default float type, as a string.
constraint_minmaxnorm

MinMaxNorm weight constraint.
constraint_unitnorm

Constrains the weights incident to each hidden unit to have unit norm.
config_set_epsilon

Set the value of the fuzz factor used in numeric expressions.
count_params

Count the total number of scalars composing the weights.
constraint_nonneg

Constrains the weights to be non-negative.
config_set_backend

Reload the backend (and the Keras package).
config_disable_interactive_logging

Turn off interactive logging.
config_image_data_format

Return the default image data format convention.
config_disable_flash_attention

Disable flash attention.
config_is_flash_attention_enabled

Checks whether flash attention is globally enabled in Keras.
config_set_floatx

Set the default float dtype.
dataset_cifar10

CIFAR10 small image classification
config_set_dtype_policy

Sets the default dtype policy globally.
dataset_cifar100

CIFAR100 small image classification
dataset_mnist

MNIST database of handwritten digits
dataset_reuters

Reuters newswire topics classification
dataset_boston_housing

Boston housing price regression dataset
custom_metric

Custom metric function
constraint_maxnorm

MaxNorm weight constraint.
config_set_image_data_format

Set the value of the image data format convention.
freeze_weights

Freeze and unfreeze weights
deserialize_keras_object

Retrieve the object by deserializing the config dict.
fit.keras.src.models.model.Model

Train a model for a fixed number of epochs (dataset iterations).
export_savedmodel.keras.src.models.model.Model

Export the model as an artifact for inference.
dataset_fashion_mnist

Fashion-MNIST database of fashion articles
get_config

Layer/Model configuration
dataset_imdb

IMDB Movie reviews sentiment classification
evaluate.keras.src.models.model.Model

Evaluate a Keras Model
get_custom_objects

Get/set the currently registered custom objects.
get_file

Downloads a file from a URL if it not already in the cache.
get_registered_object

Returns the class associated with name if it is registered with Keras.
get_source_inputs

Returns the list of input tensors necessary to compute tensor.
image_array_save

Saves an image stored as an array to a path or file object.
image_smart_resize

Resize images to a target size without aspect ratio distortion.
%<-active%

Make an Active Binding
image_to_array

Converts a PIL Image instance to a matrix.
%py_class%

Make a python class constructor
get_weights

Layer/Model weights as R arrays
get_state_tree

Retrieves tree-like structure of model variables.
get_layer

Retrieves a layer based on either its name (unique) or index.
initializer_glorot_normal

The Glorot normal initializer, also called Xavier normal initializer.
initializer_constant

Initializer that generates tensors with constant values.
initializer_lecun_uniform

Lecun uniform initializer.
image_from_array

Converts a 3D array to a PIL Image instance.
initializer_lecun_normal

Lecun normal initializer.
imagenet_preprocess_input

Preprocesses a tensor or array encoding a batch of images.
imagenet_decode_predictions

Decodes the prediction of an ImageNet model.
get_registered_name

Returns the name registered to an object within the Keras framework.
image_load

Loads an image into PIL format.
initializer_glorot_uniform

The Glorot uniform initializer, also called Xavier uniform initializer.
initializer_he_normal

He normal initializer.
keras

Main Keras module
install_keras

Install Keras
initializer_stft

Initializer of Conv kernels for Short-term Fourier Transformation (STFT).
image_dataset_from_directory

Generates a tf.data.Dataset from image files in a directory.
initializer_he_uniform

He uniform variance scaling initializer.
initializer_zeros

Initializer that generates tensors initialized to 0.
initializer_truncated_normal

Initializer that generates a truncated normal distribution.
initializer_variance_scaling

Initializer that adapts its scale to the shape of its input tensors.
initializer_random_normal

Random normal initializer.
initializer_random_uniform

Random uniform initializer.
initializer_orthogonal

Initializer that generates an orthogonal matrix.
initializer_identity

Initializer that generates the identity matrix.
initializer_ones

Initializer that generates tensors initialized to 1.
layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit activation layer.
layer_activation_elu

Applies an Exponential Linear Unit function to an output.
layer_activation

Applies an activation function to an output.
layer_activation_parametric_relu

Parametric Rectified Linear Unit activation layer.
layer_activation_relu

Rectified Linear Unit activation function layer.
keras_input

Create a Keras tensor (Functional API input).
keras_model_sequential

Keras Model composed of a linear stack of layers
keras_model

Keras Model (Functional API)
keras3-package

keras3: R Interface to 'Keras'
layer_activation_softmax

Softmax activation layer.
layer_alpha_dropout

Applies Alpha Dropout to the input.
layer_average_pooling_2d

Average pooling operation for 2D spatial data.
layer_additive_attention

Additive attention layer, a.k.a. Bahdanau-style attention.
layer_average

Averages a list of inputs element-wise..
layer_auto_contrast

Performs the auto-contrast operation on an image.
layer_attention

Dot-product attention layer, a.k.a. Luong-style attention.
layer_activity_regularization

Layer that applies an update to the cost function based input activity.
layer_average_pooling_3d

Average pooling operation for 3D data (spatial or spatio-temporal).
layer_average_pooling_1d

Average pooling for temporal data.
layer_add

Performs elementwise addition operation.
layer_conv_1d_transpose

1D transposed convolution layer.
layer_center_crop

A preprocessing layer which crops images.
layer_conv_3d

3D convolution layer.
layer_category_encoding

A preprocessing layer which encodes integer features.
layer_conv_1d

1D convolution layer (e.g. temporal convolution).
layer_batch_normalization

Layer that normalizes its inputs.
layer_conv_2d_transpose

2D transposed convolution layer.
layer_conv_2d

2D convolution layer.
layer_concatenate

Concatenates a list of inputs.
layer_bidirectional

Bidirectional wrapper for RNNs.
layer_conv_lstm_2d

2D Convolutional LSTM.
layer_conv_3d_transpose

3D transposed convolution layer.
layer_cropping_3d

Cropping layer for 3D data (e.g. spatial or spatio-temporal).
layer_depthwise_conv_1d

1D depthwise convolution layer.
layer_cropping_2d

Cropping layer for 2D input (e.g. picture).
layer_dense

Just your regular densely-connected NN layer.
layer_depthwise_conv_2d

2D depthwise convolution layer.
layer_cropping_1d

Cropping layer for 1D input (e.g. temporal sequence).
layer_conv_lstm_1d

1D Convolutional LSTM.
layer_conv_lstm_3d

3D Convolutional LSTM.
layer_dropout

Applies dropout to the input.
layer_einsum_dense

A layer that uses einsum as the backing computation.
layer_embedding

Turns nonnegative integers (indexes) into dense vectors of fixed size.
layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.
layer_equalization

Preprocessing layer for histogram equalization on image channels.
layer_discretization

A preprocessing layer which buckets continuous features by ranges.
layer_dot

Computes element-wise dot product of two tensors.
layer_flax_module_wrapper

Keras Layer that wraps a Flax module.
layer_feature_space

One-stop utility for preprocessing and encoding structured data.
layer_flatten

Flattens the input. Does not affect the batch size.
layer_gaussian_noise

Apply additive zero-centered Gaussian noise.
layer_group_query_attention

Grouped Query Attention layer.
layer_global_average_pooling_1d

Global average pooling operation for temporal data.
layer_global_average_pooling_2d

Global average pooling operation for 2D data.
layer_group_normalization

Group normalization layer.
layer_global_max_pooling_1d

Global max pooling operation for temporal data.
layer_global_max_pooling_3d

Global max pooling operation for 3D data.
layer_global_max_pooling_2d

Global max pooling operation for 2D data.
layer_gru

Gated Recurrent Unit - Cho et al. 2014.
layer_global_average_pooling_3d

Global average pooling operation for 3D data.
layer_hashed_crossing

A preprocessing layer which crosses features using the "hashing trick".
layer_jax_model_wrapper

Keras Layer that wraps a JAX model.
layer_identity

Identity layer.
layer_hashing

A preprocessing layer which hashes and bins categorical features.
layer_layer_normalization

Layer normalization layer (Ba et al., 2016).
layer_lambda

Wraps arbitrary expressions as a Layer object.
layer_lstm

Long Short-Term Memory layer - Hochreiter 1997.
layer_input

keras_input
layer_masking

Masks a sequence by using a mask value to skip timesteps.
layer_integer_lookup

A preprocessing layer that maps integers to (possibly encoded) indices.
layer_max_num_bounding_boxes

Ensure the maximum number of bounding boxes.
layer_mix_up

MixUp implements the MixUp data augmentation technique.
layer_max_pooling_3d

Max pooling operation for 3D data (spatial or spatio-temporal).
layer_maximum

Computes element-wise maximum on a list of inputs.
layer_multiply

Performs elementwise multiplication.
layer_multi_head_attention

Multi Head Attention layer.
layer_max_pooling_1d

Max pooling operation for 1D temporal data.
layer_mel_spectrogram

A preprocessing layer to convert raw audio signals to Mel spectrograms.
layer_max_pooling_2d

Max pooling operation for 2D spatial data.
layer_minimum

Computes elementwise minimum on a list of inputs.
layer_pipeline

Applies a series of layers to an input.
layer_random_contrast

A preprocessing layer which randomly adjusts contrast during training.
layer_random_color_jitter

Randomly apply brightness, contrast, saturation
layer_random_flip

A preprocessing layer which randomly flips images during training.
layer_rand_augment

RandAugment performs the Rand Augment operation on input images.
layer_random_color_degeneration

Randomly performs the color degeneration operation on given images.
layer_random_brightness

A preprocessing layer which randomly adjusts brightness during training.
layer_permute

Permutes the dimensions of the input according to a given pattern.
layer_random_crop

A preprocessing layer which randomly crops images during training.
layer_normalization

A preprocessing layer that normalizes continuous features.
layer_random_translation

A preprocessing layer which randomly translates images during training.
layer_random_posterization

Reduces the number of bits for each color channel.
layer_random_grayscale

Preprocessing layer for random conversion of RGB images to grayscale.
layer_random_saturation

Randomly adjusts the saturation on given images.
layer_random_hue

Randomly adjusts the hue on given images.
layer_random_rotation

A preprocessing layer which randomly rotates images during training.
layer_random_shear

A preprocessing layer that randomly applies shear transformations
layer_repeat_vector

Repeats the input n times.
layer_random_zoom

A preprocessing layer which randomly zooms images during training.
layer_random_sharpness

Randomly performs the sharpness operation on given images.
layer_reshape

Layer that reshapes inputs into the given shape.
layer_spatial_dropout_2d

Spatial 2D version of Dropout.
layer_rnn

Base class for recurrent layers
layer_spatial_dropout_1d

Spatial 1D version of Dropout.
layer_simple_rnn

Fully-connected RNN where the output is to be fed back as the new input.
layer_rescaling

A preprocessing layer which rescales input values to a new range.
layer_separable_conv_2d

2D separable convolution layer.
layer_separable_conv_1d

1D separable convolution layer.
layer_resizing

A preprocessing layer which resizes images.
layer_solarization

Applies (max_value - pixel + min_value) for each pixel in the image.
layer_tfsm

Reload a Keras model/layer that was saved via export_savedmodel().
layer_string_lookup

A preprocessing layer that maps strings to (possibly encoded) indices.
layer_spectral_normalization

Performs spectral normalization on the weights of a target layer.
layer_subtract

Performs elementwise subtraction.
layer_time_distributed

This wrapper allows to apply a layer to every temporal slice of an input.
layer_text_vectorization

A preprocessing layer which maps text features to integer sequences.
layer_torch_module_wrapper

Torch module wrapper layer.
layer_spatial_dropout_3d

Spatial 3D version of Dropout.
layer_unit_normalization

Unit normalization layer.
layer_stft_spectrogram

Layer to compute the Short-Time Fourier Transform (STFT) on a 1D signal.
learning_rate_schedule_inverse_time_decay

A LearningRateSchedule that uses an inverse time decay schedule.
learning_rate_schedule_cosine_decay_restarts

A LearningRateSchedule that uses a cosine decay schedule with restarts.
layer_zero_padding_1d

Zero-padding layer for 1D input (e.g. temporal sequence).
learning_rate_schedule_exponential_decay

A LearningRateSchedule that uses an exponential decay schedule.
layer_zero_padding_2d

Zero-padding layer for 2D input (e.g. picture).
layer_upsampling_1d

Upsampling layer for 1D inputs.
learning_rate_schedule_cosine_decay

A LearningRateSchedule that uses a cosine decay with optional warmup.
layer_upsampling_2d

Upsampling layer for 2D inputs.
layer_zero_padding_3d

Zero-padding layer for 3D data (spatial or spatio-temporal).
layer_upsampling_3d

Upsampling layer for 3D inputs.
load_model

Loads a model saved via save_model().
loss_categorical_hinge

Computes the categorical hinge loss between y_true & y_pred.
load_model_weights

Load weights from a file saved via save_model_weights().
loss_circle

Computes Circle Loss between integer labels and L2-normalized embeddings.
loss_categorical_crossentropy

Computes the crossentropy loss between the labels and predictions.
learning_rate_schedule_piecewise_constant_decay

A LearningRateSchedule that uses a piecewise constant decay schedule.
loss_binary_crossentropy

Computes the cross-entropy loss between true labels and predicted labels.
learning_rate_schedule_polynomial_decay

A LearningRateSchedule that uses a polynomial decay schedule.
loss_categorical_focal_crossentropy

Computes the alpha balanced focal crossentropy loss.
loss_binary_focal_crossentropy

Computes focal cross-entropy loss between true labels and predictions.
loss_mean_absolute_percentage_error

Computes the mean absolute percentage error between y_true and y_pred.
loss_mean_absolute_error

Computes the mean of absolute difference between labels and predictions.
loss_cosine_similarity

Computes the cosine similarity between y_true & y_pred.
loss_kl_divergence

Computes Kullback-Leibler divergence loss between y_true & y_pred.
loss_ctc

CTC (Connectionist Temporal Classification) loss.
loss_dice

Computes the Dice loss value between y_true and y_pred.
loss_hinge

Computes the hinge loss between y_true & y_pred.
loss_log_cosh

Computes the logarithm of the hyperbolic cosine of the prediction error.
loss_huber

Computes the Huber loss between y_true & y_pred.
loss_mean_squared_error

Computes the mean of squares of errors between labels and predictions.
metric_auc

Approximates the AUC (Area under the curve) of the ROC or PR curves.
loss_mean_squared_logarithmic_error

Computes the mean squared logarithmic error between y_true and y_pred.
mark_active

active_property
loss_tversky

Computes the Tversky loss value between y_true and y_pred.
loss_squared_hinge

Computes the squared hinge loss between y_true & y_pred.
loss_poisson

Computes the Poisson loss between y_true & y_pred.
metric_binary_focal_crossentropy

Computes the binary focal crossentropy loss.
metric_binary_crossentropy

Computes the crossentropy metric between the labels and predictions.
metric_binary_accuracy

Calculates how often predictions match binary labels.
loss_sparse_categorical_crossentropy

Computes the crossentropy loss between the labels and predictions.
metric_categorical_hinge

Computes the categorical hinge metric between y_true and y_pred.
metric_cosine_similarity

Computes the cosine similarity between the labels and predictions.
metric_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions.
metric_categorical_focal_crossentropy

Computes the categorical focal crossentropy loss.
metric_concordance_correlation

Calculates the Concordance Correlation Coefficient (CCC).
metric_binary_iou

Computes the Intersection-Over-Union metric for class 0 and/or 1.
metric_false_positives

Calculates the number of false positives.
metric_false_negatives

Calculates the number of false negatives.
metric_f1_score

Computes F-1 Score.
metric_categorical_accuracy

Calculates how often predictions match one-hot labels.
metric_huber

Computes Huber loss value.
metric_mean_absolute_percentage_error

Computes mean absolute percentage error between y_true and y_pred.
metric_hinge

Computes the hinge metric between y_true and y_pred.
metric_log_cosh

Logarithm of the hyperbolic cosine of the prediction error.
metric_kl_divergence

Computes Kullback-Leibler divergence metric between y_true and
metric_mean_absolute_error

Computes the mean absolute error between the labels and predictions.
metric_mean

Compute the (weighted) mean of the given values.
metric_log_cosh_error

Computes the logarithm of the hyperbolic cosine of the prediction error.
metric_fbeta_score

Computes F-Beta score.
metric_iou

Computes the Intersection-Over-Union metric for specific target classes.
metric_mean_wrapper

Wrap a stateless metric function with the Mean metric.
metric_one_hot_iou

Computes the Intersection-Over-Union metric for one-hot encoded labels.
metric_one_hot_mean_iou

Computes mean Intersection-Over-Union metric for one-hot encoded labels.
metric_precision_at_recall

Computes best precision where recall is >= specified value.
metric_poisson

Computes the Poisson metric between y_true and y_pred.
metric_precision

Computes the precision of the predictions with respect to the labels.
metric_mean_squared_error

Computes the mean squared error between y_true and y_pred.
metric_pearson_correlation

Calculates the Pearson Correlation Coefficient (PCC).
metric_mean_iou

Computes the mean Intersection-Over-Union metric.
metric_mean_squared_logarithmic_error

Computes mean squared logarithmic error between y_true and y_pred.
metric_sparse_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions.
metric_sensitivity_at_specificity

Computes best sensitivity where specificity is >= specified value.
metric_specificity_at_sensitivity

Computes best specificity where sensitivity is >= specified value.
metric_root_mean_squared_error

Computes root mean squared error metric between y_true and y_pred.
metric_sparse_categorical_accuracy

Calculates how often predictions match integer labels.
metric_sparse_top_k_categorical_accuracy

Computes how often integer targets are in the top K predictions.
metric_recall

Computes the recall of the predictions with respect to the labels.
metric_squared_hinge

Computes the hinge metric between y_true and y_pred.
metric_recall_at_precision

Computes best recall where precision is >= specified value.
metric_r2_score

Computes R2 score.
new_learning_rate_schedule_class

LearningRateSchedule
metric_top_k_categorical_accuracy

Computes how often targets are in the top K predictions.
new_loss_class

Loss
metric_true_positives

Calculates the number of true positives.
metric_sum

Compute the (weighted) sum of the given values.
metric_true_negatives

Calculates the number of true negatives.
new_layer_class

Layer
new_callback_class

Callback
new_metric_class

Metric
%<-%

Assign values to names
normalize

Normalizes an array.
op_all

Test whether all array elements along a given axis evaluate to TRUE.
new_model_class

Model
op_abs

Compute the absolute value element-wise.
op_append

Append tensor x2 to the end of tensor x1.
op_arange

Return evenly spaced values within a given interval.
op_any

Test whether any array element along a given axis evaluates to TRUE.
op_add

Add arguments element-wise.
op_arccosh

Inverse hyperbolic cosine, element-wise.
op_arccos

Trigonometric inverse cosine, element-wise.