View source on GitHub |

Calculates the number of true negatives.

tf.keras.metrics.TrueNegatives( thresholds=None, name=None, dtype=None )

For example, if `y_true`

is [0, 1, 0, 0] and `y_pred`

is [1, 1, 0, 0] then the true negatives value is 2. If the weights were specified as [0, 0, 1, 0] then the true negatives value would be 1.

If `sample_weight`

is given, calculates the sum of the weights of true negatives. This metric creates one local variable, `accumulator`

that is used to keep track of the number of true negatives.

If `sample_weight`

is `None`

, weights default to 1. Use `sample_weight`

of 0 to mask values.

m = tf.keras.metrics.TrueNegatives() m.update_state([0, 1, 0, 0], [1, 1, 0, 0]) print('Final result: ', m.result().numpy()) # Final result: 2

Usage with tf.keras API:

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

Args | |
---|---|

`thresholds` | (Optional) Defaults to 0.5. A float value or a python list/tuple of float threshold values in [0, 1]. A threshold is compared with prediction values to determine the truth value of predictions (i.e., above the threshold is `true` , below is `false` ). One metric value is generated for each threshold value. |

`name` | (Optional) string name of the metric instance. |

`dtype` | (Optional) data type of the metric result. |

`reset_states`

reset_states()

Resets all of the metric state variables.

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

`result`

result()

Computes and returns the metric value tensor.

Result computation is an idempotent operation that simply calculates the metric value using the state variables.

`update_state`

update_state( y_true, y_pred, sample_weight=None )

Accumulates the given confusion matrix condition statistics.

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. |

© 2020 The TensorFlow Authors. All rights reserved.

Licensed under the Creative Commons Attribution License 3.0.

Code samples licensed under the Apache 2.0 License.

https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/keras/metrics/TrueNegatives