![]() |
Class SparseTopKCategoricalAccuracy
Computes how often integer targets are in the top K
predictions.
Aliases:
- Class
tf.compat.v1.keras.metrics.SparseTopKCategoricalAccuracy
- Class
tf.compat.v2.keras.metrics.SparseTopKCategoricalAccuracy
- Class
tf.compat.v2.metrics.SparseTopKCategoricalAccuracy
Usage:
m = tf.keras.metrics.SparseTopKCategoricalAccuracy()
m.update_state([2, 1], [[0.1, 0.9, 0.8], [0.05, 0.95, 0]])
print('Final result: ', m.result().numpy()) # Final result: 1.0
Usage with tf.keras API:
model = tf.keras.Model(inputs, outputs)
model.compile(
'sgd',
metrics=[tf.keras.metrics.SparseTopKCategoricalAccuracy()])
__init__
__init__(
k=5,
name='sparse_top_k_categorical_accuracy',
dtype=None
)
Creates a SparseTopKCategoricalAccuracy
instance.
Args:
k
: (Optional) Number of top elements to look at for computing accuracy. Defaults to 5.name
: (Optional) string name of the metric instance.dtype
: (Optional) data type of the metric result.
__new__
__new__(
cls,
*args,
**kwargs
)
Create and return a new object. See help(type) for accurate signature.
Methods
tf.keras.metrics.SparseTopKCategoricalAccuracy.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.
tf.keras.metrics.SparseTopKCategoricalAccuracy.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.
tf.keras.metrics.SparseTopKCategoricalAccuracy.update_state
update_state(
y_true,
y_pred,
sample_weight=None
)
Accumulates metric statistics.
y_true
and y_pred
should have the same shape.
Args:
y_true
: The ground truth values.y_pred
: The predicted values.sample_weight
: Optional weighting of each example. Defaults to 1. Can be aTensor
whose rank is either 0, or the same rank asy_true
, and must be broadcastable toy_true
.
Returns:
Update op.