loss_ops.py 文件源码

def log_loss(
    predictions, labels=None, weights=_WEIGHT_SENTINEL, epsilon=1e-7,
    scope=None, targets=None, weight=_WEIGHT_SENTINEL):
  """Adds a Log Loss term to the training procedure.

  `weight` acts as a coefficient for the loss. If a scalar is provided, then the
  loss is simply scaled by the given value. If `weight` is a tensor of size
  [batch_size], then the total loss for each sample of the batch is rescaled
  by the corresponding element in the `weight` vector. If the shape of
  `weight` matches the shape of `predictions`, then the loss of each
  measurable element of `predictions` is scaled by the corresponding value of
  `weight`.

  Args:
    predictions: The predicted outputs.
    labels: The ground truth output tensor, same dimensions as 'predictions'.
    weights: Coefficients for the loss a scalar, a tensor of shape
      [batch_size] or a tensor whose shape matches `predictions`.
    epsilon: A small increment to add to avoid taking a log of zero.
    scope: The scope for the operations performed in computing the loss.
    targets: Deprecated alias for `labels`.
    weight: Deprecated alias for `weights`.

  Returns:
    A scalar `Tensor` representing the loss value.

  Raises:
    ValueError: If the shape of `predictions` doesn't match that of `labels` or
      if the shape of `weight` is invalid.
  """
  labels = _labels(labels, targets)
  weights = _weights(weights, weight)
  with ops.name_scope(scope, "log_loss",
                      [predictions, labels, weights]) as scope:
    predictions.get_shape().assert_is_compatible_with(labels.get_shape())
    predictions = math_ops.to_float(predictions)
    labels = math_ops.to_float(labels)
    losses = -math_ops.mul(
        labels,
        math_ops.log(predictions + epsilon)) - math_ops.mul(
            (1 - labels), math_ops.log(1 - predictions + epsilon))
    return compute_weighted_loss(losses, weights)