Skip to contents

Computes the cosine similarity between the labels and predictions.

Source: R/metrics.R
metric_cosine_similarity.Rd

Formula:

loss <- sum(l2_norm(y_true) * l2_norm(y_pred))

See: Cosine Similarity. This metric keeps the average cosine similarity between predictions and labels over a stream of data.

Usage

metric_cosine_similarity(
  ...,
  name = "cosine_similarity",
  dtype = NULL,
  axis = -1L
)

Arguments

...

For forward/backward compatability.

name

(Optional) string name of the metric instance.

dtype

(Optional) data type of the metric result.

axis

(Optional) Defaults to -1. The dimension along which the cosine similarity is computed.

Value

a Metric instance is returned. The Metric instance can be passed directly to compile(metrics = ), or used as a standalone object. See ?Metric for example usage.

Examples

Standalone usage:

m <- metric_cosine_similarity(axis=2)
m$update_state(rbind(c(0., 1.), c(1., 1.)), rbind(c(1., 0.), c(1., 1.)))
m$result()

## tf.Tensor(0.5, shape=(), dtype=float32)


m$reset_state()
m$update_state(rbind(c(0., 1.), c(1., 1.)), rbind(c(1., 0.), c(1., 1.)),
               sample_weight = c(0.3, 0.7))
m$result()

## tf.Tensor(0.7, shape=(), dtype=float32)

Usage with compile() API:

model %>% compile(
  optimizer = 'sgd',
  loss = 'mse',
  metrics = list(metric_cosine_similarity(axis=2)))

See also

Other regression metrics:
metric_concordance_correlation()
metric_log_cosh_error()
metric_mean_absolute_error()
metric_mean_absolute_percentage_error()
metric_mean_squared_error()
metric_mean_squared_logarithmic_error()
metric_pearson_correlation()
metric_r2_score()
metric_root_mean_squared_error()

Other metrics:
Metric()
custom_metric()
metric_auc()
metric_binary_accuracy()
metric_binary_crossentropy()
metric_binary_focal_crossentropy()
metric_binary_iou()
metric_categorical_accuracy()
metric_categorical_crossentropy()
metric_categorical_focal_crossentropy()
metric_categorical_hinge()
metric_concordance_correlation()
metric_f1_score()
metric_false_negatives()
metric_false_positives()
metric_fbeta_score()
metric_hinge()
metric_huber()
metric_iou()
metric_kl_divergence()
metric_log_cosh()
metric_log_cosh_error()
metric_mean()
metric_mean_absolute_error()
metric_mean_absolute_percentage_error()
metric_mean_iou()
metric_mean_squared_error()
metric_mean_squared_logarithmic_error()
metric_mean_wrapper()
metric_one_hot_iou()
metric_one_hot_mean_iou()
metric_pearson_correlation()
metric_poisson()
metric_precision()
metric_precision_at_recall()
metric_r2_score()
metric_recall()
metric_recall_at_precision()
metric_root_mean_squared_error()
metric_sensitivity_at_specificity()
metric_sparse_categorical_accuracy()
metric_sparse_categorical_crossentropy()
metric_sparse_top_k_categorical_accuracy()
metric_specificity_at_sensitivity()
metric_squared_hinge()
metric_sum()
metric_top_k_categorical_accuracy()
metric_true_negatives()
metric_true_positives()