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

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

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.

Returns:

Accuracy Tensor.

Raises:

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

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