Learn R Programming

keras3 (version 1.5.0)

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

11,255

Version

1.5.0

License

MIT + file LICENSE

Issues

120

Pull Requests

0

Stars

854

Forks

282

Maintainer

Tomasz Kalinowski

Last Published

December 22nd, 2025

Functions in keras3 (1.5.0)

Callback

Define a custom Callback class
Metric

Subclass the base Metric class
activation_celu

Continuously Differentiable Exponential Linear Unit.
Constraint

Define a custom Constraint class
activation_elu

Exponential Linear Unit.
LearningRateSchedule

Define a custom LearningRateSchedule class
Loss

Subclass the base Loss class
Model

Subclass the base Keras Model Class
activation_exponential

Exponential activation function.
Layer

Define a custom Layer class.
activation_hard_silu

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

Logarithm of the sigmoid activation function.
activation_linear

Linear activation function (pass-through).
activation_gelu

Gaussian error linear unit (GELU) activation function.
activation_hard_tanh

HardTanh activation function.
activation_hard_shrink

Hard Shrink activation function.
activation_glu

Gated Linear Unit (GLU) activation function.
activation_hard_sigmoid

Hard sigmoid activation function.
activation_leaky_relu

Leaky relu activation function.
activation_log_softmax

Log-Softmax activation function.
activation_silu

Swish (or Silu) activation function.
activation_relu

Applies the rectified linear unit activation function.
activation_relu6

Relu6 activation function.
activation_softplus

Softplus activation function.
activation_selu

Scaled Exponential Linear Unit (SELU).
activation_mish

Mish activation function.
activation_sigmoid

Sigmoid activation function.
activation_softsign

Softsign activation function.
activation_soft_shrink

Soft Shrink activation function.
activation_softmax

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

Squareplus activation function.
activation_sparse_plus

SparsePlus activation function.
activation_sparsemax

Sparsemax activation function.
activation_tanh

Hyperbolic tangent activation function.
adapt

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

Instantiates the ConvNeXtBase architecture.
activation_tanh_shrink

Tanh shrink activation function.
activation_sparse_sigmoid

Sparse sigmoid activation function.
active_property

Create an active property class method
activation_threshold

Threshold activation function.
application_convnext_large

Instantiates the ConvNeXtLarge architecture.
application_efficientnet_b2

Instantiates the EfficientNetB2 architecture.
application_convnext_small

Instantiates the ConvNeXtSmall architecture.
application_densenet201

Instantiates the Densenet201 architecture.
application_densenet169

Instantiates the Densenet169 architecture.
application_convnext_xlarge

Instantiates the ConvNeXtXLarge architecture.
application_efficientnet_b1

Instantiates the EfficientNetB1 architecture.
application_convnext_tiny

Instantiates the ConvNeXtTiny architecture.
application_densenet121

Instantiates the Densenet121 architecture.
application_efficientnet_b0

Instantiates the EfficientNetB0 architecture.
application_efficientnet_b4

Instantiates the EfficientNetB4 architecture.
application_efficientnet_v2b0

Instantiates the EfficientNetV2B0 architecture.
application_efficientnet_v2b3

Instantiates the EfficientNetV2B3 architecture.
application_efficientnet_b3

Instantiates the EfficientNetB3 architecture.
application_efficientnet_v2l

Instantiates the EfficientNetV2L architecture.
application_efficientnet_v2b2

Instantiates the EfficientNetV2B2 architecture.
application_efficientnet_b5

Instantiates the EfficientNetB5 architecture.
application_efficientnet_b7

Instantiates the EfficientNetB7 architecture.
application_efficientnet_b6

Instantiates the EfficientNetB6 architecture.
application_efficientnet_v2b1

Instantiates the EfficientNetV2B1 architecture.
application_mobilenet_v3_small

Instantiates the MobileNetV3Small architecture.
application_inception_resnet_v2

Instantiates the Inception-ResNet v2 architecture.
application_mobilenet

Instantiates the MobileNet architecture.
application_mobilenet_v2

Instantiates the MobileNetV2 architecture.
application_nasnet_mobile

Instantiates a Mobile NASNet model in ImageNet mode.
application_efficientnet_v2m

Instantiates the EfficientNetV2M architecture.
application_efficientnet_v2s

Instantiates the EfficientNetV2S architecture.
application_nasnet_large

Instantiates a NASNet model in ImageNet mode.
application_mobilenet_v3_large

Instantiates the MobileNetV3Large architecture.
application_inception_v3

Instantiates the Inception v3 architecture.
application_resnet101

Instantiates the ResNet101 architecture.
audio_dataset_from_directory

Generates a tf.data.Dataset from audio files in a directory.
application_vgg16

Instantiates the VGG16 model.
application_vgg19

Instantiates the VGG19 model.
application_resnet101_v2

Instantiates the ResNet101V2 architecture.
application_resnet152_v2

Instantiates the ResNet152V2 architecture.
application_xception

Instantiates the Xception architecture.
application_resnet152

Instantiates the ResNet152 architecture.
application_resnet50

Instantiates the ResNet50 architecture.
application_resnet50_v2

Instantiates the ResNet50V2 architecture.
callback_early_stopping

Stop training when a monitored metric has stopped improving.
callback_remote_monitor

Callback used to stream events to a server.
callback_backup_and_restore

Callback to back up and restore the training state.
callback_model_checkpoint

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

Reduce learning rate when a metric has stopped improving.
callback_learning_rate_scheduler

Learning rate scheduler.
callback_csv_logger

Callback that streams epoch results to a CSV file.
callback_lambda

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

Backward compatibility
bidirectional

layer_bidirectional
compile.keras.src.models.model.Model

Configure a model for training.
callback_terminate_on_nan

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

Clone a Functional or Sequential Model instance.
config_disable_interactive_logging

Turn off interactive logging.
clear_session

Resets all state generated by Keras.
callback_tensorboard

Enable visualizations for TensorBoard.
callback_swap_ema_weights

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

Publicly accessible method for determining the current backend.
config_disable_traceback_filtering

Turn off traceback filtering.
config_disable_flash_attention

Disable flash attention.
config_is_interactive_logging_enabled

Check if interactive logging is enabled.
config_is_flash_attention_enabled

Checks whether flash attention is globally enabled in Keras.
config_image_data_format

Return the default image data format convention.
config_epsilon

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

Turn on interactive logging.
config_floatx

Return the default float type, as a string.
config_enable_unsafe_deserialization

Disables safe mode globally, allowing deserialization of lambdas.
config_enable_flash_attention

Enable flash attention.
config_enable_traceback_filtering

Turn on traceback filtering.
config_dtype_policy

Returns the current default dtype policy object.
config_max_epochs

Configure the default training loop limits.
config_set_image_data_format

Set the value of the image data format convention.
config_is_traceback_filtering_enabled

Check if traceback filtering is enabled.
constraint_maxnorm

MaxNorm weight constraint.
config_is_nnx_enabled

Check whether NNX-specific features are enabled on the JAX backend.
constraint_minmaxnorm

MinMaxNorm weight constraint.
config_set_floatx

Set the default float dtype.
config_set_backend

Reload the backend (and the Keras package).
config_set_dtype_policy

Sets the default dtype policy globally.
config_set_epsilon

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

Boston housing price regression dataset
count_params

Count the total number of scalars composing the weights.
dataset_cifar100

CIFAR100 small image classification
custom_metric

Custom metric function
dataset_imdb

IMDB Movie reviews sentiment classification
constraint_unitnorm

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

Constrains the weights to be non-negative.
dataset_cifar10

CIFAR10 small image classification
dataset_california_housing

Loads the California Housing dataset.
dataset_fashion_mnist

Fashion-MNIST database of fashion articles
dataset_mnist

MNIST database of handwritten digits
get_config

Layer/Model configuration
fit.keras.src.models.model.Model

Train a model for a fixed number of epochs (dataset iterations).
get_file

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

Reuters newswire topics classification
evaluate.keras.src.models.model.Model

Evaluate a Keras Model
export_savedmodel.keras.src.models.model.Model

Export the model as an artifact for inference.
deserialize_keras_object

Retrieve the object by deserializing the config dict.
get_custom_objects

Get/set the currently registered custom objects.
freeze_weights

Freeze and unfreeze weights
get_source_inputs

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

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

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

Returns the name registered to an object within the Keras framework.
%<-active%

Make an Active Binding
get_registered_object

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

Layer/Model weights as R arrays
image_dataset_from_directory

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

Retrieves tree-like structure of model variables.
%py_class%

Make a python class constructor
initializer_glorot_uniform

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

He normal initializer.
imagenet_preprocess_input

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

Resize images to a target size without aspect ratio distortion.
image_to_array

Converts a PIL Image instance to a matrix.
imagenet_decode_predictions

Decodes the prediction of an ImageNet model.
initializer_constant

Initializer that generates tensors with constant values.
image_from_array

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

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

Loads an image into PIL format.
initializer_truncated_normal

Initializer that generates a truncated normal distribution.
initializer_random_normal

Random normal initializer.
initializer_lecun_uniform

Lecun uniform initializer.
initializer_stft

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

Random uniform initializer.
initializer_orthogonal

Initializer that generates an orthogonal matrix.
initializer_ones

Initializer that generates tensors initialized to 1.
initializer_he_uniform

He uniform variance scaling initializer.
initializer_lecun_normal

Lecun normal initializer.
initializer_identity

Initializer that generates the identity matrix.
keras3-package

keras3: R Interface to 'Keras'
initializer_zeros

Initializer that generates tensors initialized to 0.
keras_model

Keras Model (Functional API)
keras_model_sequential

Keras Model composed of a linear stack of layers
install_keras

Install Keras
initializer_variance_scaling

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

Applies an activation function to an output.
keras_variable

Represents a backend-agnostic variable in Keras.
keras_input

Create a Keras tensor (Functional API input).
keras

Main Keras module
layer_activation_parametric_relu

Parametric Rectified Linear Unit activation layer.
layer_additive_attention

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

Softmax activation layer.
layer_alpha_dropout

Applies Alpha Dropout to the input.
layer_activation_elu

Applies an Exponential Linear Unit function to an output.
layer_activity_regularization

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

Leaky version of a Rectified Linear Unit activation layer.
layer_activation_relu

Rectified Linear Unit activation function layer.
layer_add

Performs elementwise addition operation.
layer_attention

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

Layer that normalizes its inputs.
layer_auto_contrast

Performs the auto-contrast operation on an image.
layer_category_encoding

A preprocessing layer which encodes integer features.
layer_average_pooling_2d

Average pooling operation for 2D spatial data.
layer_average

Averages a list of inputs element-wise..
layer_bidirectional

Bidirectional wrapper for RNNs.
layer_aug_mix

Performs the AugMix data augmentation technique.
layer_average_pooling_3d

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

A preprocessing layer which crops images.
layer_average_pooling_1d

Average pooling for temporal data.
layer_conv_3d_transpose

3D transposed convolution layer.
layer_concatenate

Concatenates a list of inputs.
layer_conv_lstm_1d

1D Convolutional LSTM.
layer_conv_1d

1D convolution layer (e.g. temporal convolution).
layer_conv_lstm_2d

2D Convolutional LSTM.
layer_conv_2d_transpose

2D transposed convolution layer.
layer_conv_1d_transpose

1D transposed convolution layer.
layer_conv_2d

2D convolution layer.
layer_conv_lstm_3d

3D Convolutional LSTM.
layer_conv_3d

3D convolution layer.
layer_cropping_2d

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

Applies dropout to the input.
layer_cropping_1d

Cropping layer for 1D input (e.g. temporal sequence).
layer_depthwise_conv_1d

1D depthwise convolution layer.
layer_cut_mix

CutMix data augmentation technique.
layer_dense

Just your regular densely-connected NN layer.
layer_depthwise_conv_2d

2D depthwise convolution layer.
layer_discretization

A preprocessing layer which buckets continuous features by ranges.
layer_dot

Computes element-wise dot product of two tensors.
layer_cropping_3d

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

Apply additive zero-centered Gaussian noise.
layer_feature_space

One-stop utility for preprocessing and encoding structured data.
layer_global_average_pooling_1d

Global average pooling operation for temporal data.
layer_equalization

Preprocessing layer for histogram equalization on image channels.
layer_flax_module_wrapper

Keras Layer that wraps a Flax module.
layer_flatten

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

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

A layer that uses einsum as the backing computation.
layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.
layer_global_average_pooling_2d

Global average pooling operation for 2D data.
layer_identity

Identity layer.
layer_group_normalization

Group normalization layer.
layer_hashing

A preprocessing layer which hashes and bins categorical features.
layer_gru

Gated Recurrent Unit - Cho et al. 2014.
layer_hashed_crossing

A preprocessing layer which crosses features using the "hashing trick".
layer_global_max_pooling_3d

Global max pooling operation for 3D data.
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_global_max_pooling_2d

Global max pooling operation for 2D data.
layer_group_query_attention

Grouped Query Attention layer.
layer_lambda

Wraps arbitrary expressions as a Layer object.
layer_max_pooling_1d

Max pooling operation for 1D temporal data.
layer_jax_model_wrapper

Keras Layer that wraps a JAX model.
layer_masking

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

Layer normalization layer (Ba et al., 2016).
layer_max_pooling_2d

Max pooling operation for 2D spatial data.
layer_max_num_bounding_boxes

Ensure the maximum number of bounding boxes.
layer_lstm

Long Short-Term Memory layer - Hochreiter 1997.
layer_integer_lookup

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

keras_input
layer_multiply

Performs elementwise multiplication.
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_pipeline

Applies a series of layers to an input.
layer_minimum

Computes elementwise minimum on a list of inputs.
layer_normalization

A preprocessing layer that normalizes continuous features.
layer_mel_spectrogram

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

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

Multi Head Attention layer.
layer_random_elastic_transform

A preprocessing layer that applies random elastic transformations.
layer_random_brightness

A preprocessing layer which randomly adjusts brightness during training.
layer_rand_augment

RandAugment performs the Rand Augment operation on input images.
layer_random_contrast

A preprocessing layer which randomly adjusts contrast during training.
layer_random_flip

A preprocessing layer which randomly flips images during training.
layer_random_color_jitter

Randomly apply brightness, contrast, saturation
layer_random_erasing

Random Erasing data augmentation technique.
layer_random_gaussian_blur

Applies random Gaussian blur to images for data augmentation.
layer_random_crop

A preprocessing layer which randomly crops images during training.
layer_random_color_degeneration

Randomly performs the color degeneration operation on given images.
layer_random_invert

Preprocessing layer for random inversion of image colors.
layer_random_saturation

Randomly adjusts the saturation on given images.
layer_random_grayscale

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

Randomly performs the sharpness operation on given images.
layer_random_hue

Randomly adjusts the hue on given images.
layer_random_translation

A preprocessing layer which randomly translates images during training.
layer_random_perspective

A preprocessing layer that applies random perspective transformations.
layer_random_shear

A preprocessing layer that randomly applies shear transformations
layer_random_posterization

Reduces the number of bits for each color channel.
layer_random_rotation

A preprocessing layer which randomly rotates images during training.
layer_separable_conv_2d

2D separable convolution layer.
layer_resizing

A preprocessing layer which resizes images.
layer_repeat_vector

Repeats the input n times.
layer_separable_conv_1d

1D separable convolution layer.
layer_random_zoom

A preprocessing layer which randomly zooms images during training.
layer_rms_normalization

Root Mean Square (RMS) Normalization layer.
layer_reshape

Layer that reshapes inputs into the given shape.
layer_rnn

Base class for recurrent layers
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_subtract

Performs elementwise subtraction.
layer_string_lookup

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

Reload a Keras model/layer that was saved via export_savedmodel().
layer_spatial_dropout_3d

Spatial 3D version of Dropout.
layer_spatial_dropout_2d

Spatial 2D version of Dropout.
layer_solarization

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

Performs spectral normalization on the weights of a target layer.
layer_spatial_dropout_1d

Spatial 1D version of Dropout.
layer_text_vectorization

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

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

A LearningRateSchedule that uses a cosine decay with optional warmup.
layer_zero_padding_3d

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

Upsampling layer for 3D inputs.
layer_unit_normalization

Unit normalization layer.
layer_zero_padding_2d

Zero-padding layer for 2D input (e.g. picture).
layer_zero_padding_1d

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

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

Torch module wrapper layer.
layer_upsampling_1d

Upsampling layer for 1D inputs.
layer_upsampling_2d

Upsampling layer for 2D inputs.
learning_rate_schedule_exponential_decay

A LearningRateSchedule that uses an exponential decay schedule.
learning_rate_schedule_piecewise_constant_decay

A LearningRateSchedule that uses a piecewise constant decay schedule.
learning_rate_schedule_inverse_time_decay

A LearningRateSchedule that uses an inverse time decay schedule.
load_model_weights

Load the weights from a single file or sharded files.
learning_rate_schedule_polynomial_decay

A LearningRateSchedule that uses a polynomial decay schedule.
loss_categorical_crossentropy

Computes the crossentropy loss between the labels and predictions.
loss_binary_focal_crossentropy

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

Loads a model saved via save_model().
loss_binary_crossentropy

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

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

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

Computes the cosine similarity between y_true & y_pred.
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_circle

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

Computes the Huber loss between y_true & y_pred.
loss_categorical_hinge

Computes the categorical hinge loss between y_true & y_pred.
loss_ctc

CTC (Connectionist Temporal Classification) loss.
loss_categorical_focal_crossentropy

Computes the alpha balanced focal crossentropy loss.
loss_categorical_generalized_cross_entropy

Computes the generalized cross entropy loss.
loss_poisson

Computes the Poisson loss between y_true & y_pred.
mark_active

active_property
loss_mean_absolute_error

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

Computes the Tversky loss value between y_true and y_pred.
loss_log_cosh

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

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

Computes the squared hinge loss between y_true & y_pred.
loss_mean_squared_error

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

Computes the crossentropy loss between the labels and predictions.
loss_mean_squared_logarithmic_error

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

Computes the crossentropy metric between the labels and predictions.
metric_binary_iou

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

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

Calculates how often predictions match binary labels.
metric_categorical_hinge

Computes the categorical hinge metric between y_true and y_pred.
metric_categorical_focal_crossentropy

Computes the categorical focal crossentropy loss.
metric_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions.
metric_concordance_correlation

Calculates the Concordance Correlation Coefficient (CCC).
metric_binary_focal_crossentropy

Computes the binary focal crossentropy loss.
metric_categorical_accuracy

Calculates how often predictions match one-hot labels.
metric_kl_divergence

Computes Kullback-Leibler divergence metric between y_true and
metric_hinge

Computes the hinge metric between y_true and y_pred.
metric_cosine_similarity

Computes the cosine similarity between the labels and predictions.
metric_iou

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

Computes Huber loss value.
metric_false_negatives

Calculates the number of false negatives.
metric_fbeta_score

Computes F-Beta score.
metric_log_cosh

Logarithm of the hyperbolic cosine of the prediction error.
metric_f1_score

Computes F-1 Score.
metric_false_positives

Calculates the number of false positives.
metric_mean_absolute_error

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

Computes the mean Intersection-Over-Union metric.
metric_mean_absolute_percentage_error

Computes mean absolute percentage error between y_true and y_pred.
metric_one_hot_mean_iou

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

Computes the mean squared error between y_true and y_pred.
metric_one_hot_iou

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

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

Wrap a stateless metric function with the Mean metric.
metric_mean_squared_logarithmic_error

Computes mean squared logarithmic error between y_true and y_pred.
metric_mean

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

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

Calculates the Pearson Correlation Coefficient (PCC).
metric_recall_at_precision

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

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

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

Computes the Poisson metric between y_true and y_pred.
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_recall

Computes the recall of the predictions with respect to the labels.
metric_r2_score

Computes R2 score.
metric_true_negatives

Calculates the number of true negatives.
metric_specificity_at_sensitivity

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

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

Computes the hinge metric between y_true and y_pred.
%<-%

Assign values to names
metric_top_k_categorical_accuracy

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

Create a named list from arguments
metric_true_positives

Calculates the number of true positives.
metric_sum

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

Computes the crossentropy metric between the labels and predictions.
op_abs

Compute the absolute value element-wise.
normalize

Normalizes an array.
newaxis

New axis
op_add

Add arguments element-wise.
new_loss_class

Loss
new_layer_class

Layer
new_learning_rate_schedule_class

LearningRateSchedule
new_metric_class

Metric
new_model_class

Model
new_callback_class

Callback