tf.contrib.metrics.accuracy

tf.contrib.metrics.accuracy(
    predictions,
    labels,
    weights=None,
    name=None
)

Defined in tensorflow/contrib/metrics/python/metrics/classification.py.

See the guide: Metrics (contrib) > Metric Ops

Computes the percentage of times that predictions matches labels.

Args:

  • predictions: the predicted values, a Tensor whose dtype and shape matches 'labels'.
  • labels: the ground truth values, a Tensor of any shape and bool, integer, or string dtype.
  • weights: None or Tensor of float values to reweight the accuracy.
  • name: A name for the operation (optional).

Returns:

Accuracy Tensor.

Raises:

  • ValueError: if dtypes don't match or if dtype is not bool, integer, or string.