# tf.keras.metrics.FalsePositives

View source

## Class `FalsePositives`

### Aliases:

• Class `tf.compat.v1.keras.metrics.FalsePositives`
• Class `tf.compat.v2.keras.metrics.FalsePositives`
• Class `tf.compat.v2.metrics.FalsePositives`
• Class `tf.metrics.FalsePositives`

For example, if `y_true` is [0, 1, 0, 0] and `y_pred`大牛时代配资 is [0, 0, 1, 1] then the false positives value is 2. If the weights were specified as [0, 0, 1, 0] then the false positives value would be 1.

If `sample_weight` is given, calculates the sum of the weights of false positives. This metric creates one local variable, `accumulator` that is used to keep track of the number of false positives.

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

#### Usage:

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

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

## `__init__`

View source

``````__init__(
thresholds=None,
name=None,
dtype=None
)
``````

Creates a `FalsePositives` instance.

#### 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.

## Methods

### `reset_states`

View source

``````reset_states()
``````

### `result`

View source

``````result()
``````

### `update_state`

View source

``````update_state(
y_true,
y_pred,
sample_weight=None
)
``````

#### 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`.

Update op.