LostTech.TensorFlow : API Documentation

Type Precision

Namespace tensorflow.keras.metrics

Parent Metric

Interfaces IPrecision

Computes the precision of the predictions with respect to the labels.

For example, if `y_true` is [0, 1, 1, 1] and `y_pred` is [1, 0, 1, 1] then the precision value is 2/(2+1) ie. 0.66. If the weights were specified as [0, 0, 1, 0] then the precision value would be 1.

The metric creates two local variables, `true_positives` and `false_positives` that are used to compute the precision. This value is ultimately returned as `precision`, an idempotent operation that simply divides `true_positives` by the sum of `true_positives` and `false_positives`.

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

If `top_k` is set, we'll calculate precision as how often on average a class among the top-k classes with the highest predicted values of a batch entry is correct and can be found in the label for that entry.

If `class_id` is specified, we calculate precision by considering only the entries in the batch for which `class_id` is above the threshold and/or in the top-k highest predictions, and computing the fraction of them for which `class_id` is indeed a correct label.

Usage: Usage with tf.keras API:

m = tf.keras.metrics.Precision()
            m.update_state([0, 1, 1, 1], [1, 0, 1, 1])
            print('Final result: ', m.result().numpy())  # Final result: 0.66

Methods

Properties

Public instance methods

object update_state(IEnumerable<IGraphNodeBase> y_true, IEnumerable<object> y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

IEnumerable<IGraphNodeBase> y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
IEnumerable<object> y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(IEnumerable<IGraphNodeBase> y_true, int y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

IEnumerable<IGraphNodeBase> y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
int y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(IEnumerable<IGraphNodeBase> y_true, IGraphNodeBase y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

IEnumerable<IGraphNodeBase> y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
IGraphNodeBase y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(IEnumerable<IGraphNodeBase> y_true, object y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

IEnumerable<IGraphNodeBase> y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
object y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(ValueTuple<PythonClassContainer, PythonClassContainer> y_true, IEnumerable<object> y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

ValueTuple<PythonClassContainer, PythonClassContainer> y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
IEnumerable<object> y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(ValueTuple<PythonClassContainer, PythonClassContainer> y_true, int y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

ValueTuple<PythonClassContainer, PythonClassContainer> y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
int y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(ValueTuple<PythonClassContainer, PythonClassContainer> y_true, IGraphNodeBase y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

ValueTuple<PythonClassContainer, PythonClassContainer> y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
IGraphNodeBase y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(ValueTuple<PythonClassContainer, PythonClassContainer> y_true, object y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

ValueTuple<PythonClassContainer, PythonClassContainer> y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
object y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(int y_true, IEnumerable<object> y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

int y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
IEnumerable<object> y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(int y_true, int y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

int y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
int y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(int y_true, IGraphNodeBase y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

int y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
IGraphNodeBase y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(int y_true, object y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

int y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
object y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(IGraphNodeBase y_true, IEnumerable<object> y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

IGraphNodeBase y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
IEnumerable<object> y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(IGraphNodeBase y_true, int y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

IGraphNodeBase y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
int y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(IGraphNodeBase y_true, IGraphNodeBase y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

IGraphNodeBase y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
IGraphNodeBase y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

object update_state(IGraphNodeBase y_true, object y_pred, IGraphNodeBase sample_weight)

Accumulates true positive and false positive statistics.

Parameters

IGraphNodeBase y_true: The ground truth values, with the same dimensions as `y_pred`. Will be cast to `bool`.
object y_pred: The predicted values. Each element must be in the range `[0, 1]`.
IGraphNodeBase 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

object: Update op.

Public properties

PythonFunctionContainer activity_regularizer get; set;

object activity_regularizer_dyn get; set;

bool built get; set;

Nullable<int> class_id get; set;

object dtype get;

object dtype_dyn get;

bool dynamic get;

object dynamic_dyn get;

object false_positives get; set;

IList<Node> inbound_nodes get;

object inbound_nodes_dyn get;

object init_thresholds get; set;

IList<object> input get;

object input_dyn get;

object input_mask get;

object input_mask_dyn get;

IList<object> input_shape get;

object input_shape_dyn get;

object input_spec get; set;

object input_spec_dyn get; set;

IList<object> losses get;

object losses_dyn get;

IList<object> metrics get;

object metrics_dyn get;

object name get;

object name_dyn get;

object name_scope get;

object name_scope_dyn get;

IList<object> non_trainable_variables get;

object non_trainable_variables_dyn get;

IList<object> non_trainable_weights get;

object non_trainable_weights_dyn get;

IList<object> outbound_nodes get;

object outbound_nodes_dyn get;

IList<object> output get;

object output_dyn get;

object output_mask get;

object output_mask_dyn get;

object output_shape get;

object output_shape_dyn get;

object PythonObject get;

bool stateful get; set;

ValueTuple<object> submodules get;

object submodules_dyn get;

bool supports_masking get; set;

object thresholds get; set;

Nullable<int> top_k get; set;

bool trainable get; set;

object trainable_dyn get; set;

object trainable_variables get;

object trainable_variables_dyn get;

IList<object> trainable_weights get;

object trainable_weights_dyn get;

object true_positives get; set;

IList<object> updates get;

object updates_dyn get;

object variables get;

object variables_dyn get;

IList<object> weights get;

object weights_dyn get;