Skip to contents

Formula:

loss <- maximum(neg - pos + 1, 0)

where neg=maximum((1-y_true)*y_pred) and pos=sum(y_true*y_pred)

Usage

metric_categorical_hinge(
  y_true,
  y_pred,
  ...,
  name = "categorical_hinge",
  dtype = NULL
)

Arguments

y_true

The ground truth values. y_true values are expected to be either {-1, +1} or {0, 1} (i.e. a one-hot-encoded tensor) with shape = [batch_size, d0, .. dN].

y_pred

The predicted values with shape = [batch_size, d0, .. dN].

...

For forward/backward compatability.

name

(Optional) string name of the metric instance.

dtype

(Optional) data type of the metric result.

Value

Categorical hinge loss values with shape = [batch_size, d0, .. dN-1].

Usage

Standalone usage:

m <- metric_categorical_hinge()
m$update_state(rbind(c(0, 1), c(0, 0)), rbind(c(0.6, 0.4), c(0.4, 0.6)))
m$result()

## tf.Tensor(1.4000001, shape=(), dtype=float32)

m$reset_state()
m$update_state(rbind(c(0, 1), c(0, 0)), rbind(c(0.6, 0.4), c(0.4, 0.6)),
               sample_weight = c(1, 0))
m$result()

## tf.Tensor(1.2, shape=(), dtype=float32)

See also

Other losses:
Loss()
loss_binary_crossentropy()
loss_binary_focal_crossentropy()
loss_categorical_crossentropy()
loss_categorical_focal_crossentropy()
loss_categorical_hinge()
loss_cosine_similarity()
loss_hinge()
loss_huber()
loss_kl_divergence()
loss_log_cosh()
loss_mean_absolute_error()
loss_mean_absolute_percentage_error()
loss_mean_squared_error()
loss_mean_squared_logarithmic_error()
loss_poisson()
loss_sparse_categorical_crossentropy()
loss_squared_hinge()
metric_binary_crossentropy()
metric_binary_focal_crossentropy()
metric_categorical_crossentropy()
metric_categorical_focal_crossentropy()
metric_hinge()
metric_huber()
metric_kl_divergence()
metric_log_cosh()
metric_mean_absolute_error()
metric_mean_absolute_percentage_error()
metric_mean_squared_error()
metric_mean_squared_logarithmic_error()
metric_poisson()
metric_sparse_categorical_crossentropy()
metric_squared_hinge()

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_cosine_similarity()
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_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()

Other hinge metrics:
metric_hinge()
metric_squared_hinge()