tf.keras.metrics.BinaryCrossentropy

View source

Class BinaryCrossentropy

免费成长做爱直播有哪些Computes the crossentropy metric between the labels and predictions.

Aliases:

  • Class tf.compat.v1.keras.metrics.BinaryCrossentropy
  • Class tf.compat.v2.keras.metrics.BinaryCrossentropy
  • Class tf.compat.v2.metrics.BinaryCrossentropy
  • Class tf.metrics.BinaryCrossentropy

免费成长做爱直播有哪些This is the crossentropy metric class to be used when there are only two label classes (0 and 1).

Usage:

m = tf.keras.metrics.BinaryCrossentropy()
m.update_state([1., 0., 1., 0.], [1., 1., 1., 0.])

# EPSILON = 1e-7, y = y_true, y` = y_pred, Y_MAX = 0.9999999
# y` = clip_ops.clip_by_value(output, EPSILON, 1. - EPSILON)
# y` = [Y_MAX, Y_MAX, Y_MAX, EPSILON]

# Metric = -(y log(y` + EPSILON) + (1 - y) log(1 - y` + EPSILON))
#        = [-log(Y_MAX + EPSILON), -log(1 - Y_MAX + EPSILON),
#           -log(Y_MAX + EPSILON), -log(1)]
#        = [(0 + 15.33) / 2, (0 + 0) / 2]
# Reduced metric = 7.665 / 2

print('Final result: ', m.result().numpy())  # Final result: 3.833

免费成长做爱直播有哪些Usage with tf.keras API:

model = tf.keras.Model(inputs, outputs)
model.compile(
    'sgd',
    loss='mse',
    metrics=[tf.keras.metrics.BinaryCrossentropy()])

__init__

View source

__init__(
    name='binary_crossentropy',
    dtype=None,
    from_logits=False,
    label_smoothing=0
)

Creates a BinaryCrossentropy instance.

Args:

  • name: (Optional) string name of the metric instance.
  • dtype: (Optional) data type of the metric result.
  • from_logits: (Optional )Whether output is expected to be a logits tensor. By default, we consider that output encodes a probability distribution.
  • label_smoothing: (Optional) Float in [0, 1]. When > 0, label values are smoothed, meaning the confidence on label values are relaxed. e.g. label_smoothing=0.2 means that we will use a value of 0.1 for label 0 and 0.9 for label 1"

Methods

reset_states

View source

reset_states()

Resets all of the metric state variables.

This function is called between epochs/steps, when a metric is evaluated during training.

result

View source

result()

免费成长做爱直播有哪些Computes and returns the metric value tensor.

免费成长做爱直播有哪些Result computation is an idempotent operation that simply calculates the metric value using the state variables.

update_state

View source

update_state(
    y_true,
    y_pred,
    sample_weight=None
)

Accumulates metric statistics.

y_true and y_pred免费成长做爱直播有哪些 should have the same shape.

Args:

  • y_true: The ground truth values.
  • y_pred: The predicted values.
  • sample_weight: Optional weighting of each example. Defaults to 1. Can be a Tensor whose rank is either 0, or the same rank as y_true, and must be broadcastable to y_true.

Returns:

Update op.

results matching ""

    No results matching ""