tf.compat.v1.metrics.accuracy  |  TensorFlow v2.16.1 (original) (raw)

Calculates how often predictions matches labels.

tf.compat.v1.metrics.accuracy(
    labels,
    predictions,
    weights=None,
    metrics_collections=None,
    updates_collections=None,
    name=None
)

Migrate to TF2

tf.compat.v1.metrics.accuracy is not compatible with eager execution or tf.function. Please use tf.keras.metrics.Accuracy instead for TF2 migration. After instantiating a tf.keras.metrics.Accuracy object, you can first call theupdate_state() method to record the prediction/labels, and then call theresult() method to get the accuracy eagerly. You can also attach it to a Keras model when calling the compile method. Please refer to this guidefor more details.

Structural Mapping to Native TF2

Before:

accuracy, update_op = tf.compat.v1.metrics.accuracy(
  labels=labels,
  predictions=predictions,
  weights=weights,
  metrics_collections=metrics_collections,
  update_collections=update_collections,
  name=name)

After:

 m = tf.keras.metrics.Accuracy(
   name=name,
   dtype=None)

 m.update_state(
 y_true=labels,
 y_pred=predictions,
 sample_weight=weights)

 accuracy = m.result()

How to Map Arguments

Before & After Usage Example

Before:

g = tf.Graph() with g.as_default(): logits = [1, 2, 3] labels = [0, 2, 3] acc, acc_op = tf.compat.v1.metrics.accuracy(logits, labels) global_init = tf.compat.v1.global_variables_initializer() local_init = tf.compat.v1.local_variables_initializer() sess = tf.compat.v1.Session(graph=g) sess.run([global_init, local_init]) print(sess.run([acc, acc_op])) [0.0, 0.66667]

After:

m = tf.keras.metrics.Accuracy() m.update_state([1, 2, 3], [0, 2, 3]) m.result().numpy() 0.66667

# Used within Keras model
model.compile(optimizer='sgd',
              loss='mse',
              metrics=[tf.keras.metrics.Accuracy()])

Description

Used in the notebooks

The accuracy function creates two local variables, total andcount that are used to compute the frequency with which predictionsmatches labels. This frequency is ultimately returned as accuracy: an idempotent operation that simply divides total by count.

For estimation of the metric over a stream of data, the function creates anupdate_op operation that updates these variables and returns the accuracy. Internally, an is_correct operation computes a Tensor with elements 1.0 where the corresponding elements of predictions and labels match and 0.0 otherwise. Then update_op increments total with the reduced sum of the product of weights and is_correct, and it increments count with the reduced sum of weights.

If weights is None, weights default to 1. Use weights of 0 to mask values.