Class CategoricalAccuracy
Inherits From: Mean
Defined in tensorflow/contrib/eager/python/metrics_impl.py
.
Calculates how often predictions
matches labels
.
This class is compatible with tf.keras.losses.categorical_crossentropy
,
tf.nn.softmax_cross_entropy_with_logits_v2
,
tf.losses.softmax_cross_entropy
.
Attributes:
name
: name of the accuracy object.dtype
: data type of tensor.
__init__
__init__(
name=None,
dtype=tf.dtypes.double
)
Inits CategoricalAccuracy with name and dtype.
Properties
name
variables
Methods
tf.contrib.eager.metrics.CategoricalAccuracy.__call__
__call__(
*args,
**kwargs
)
Returns op to execute to update this metric for these inputs.
Returns None if eager execution is enabled. Returns a graph-mode function if graph execution is enabled.
Args:
*args
: ***kwargs
: A mini-batch of inputs to the Metric, passed on tocall()
.
tf.contrib.eager.metrics.CategoricalAccuracy.add_variable
add_variable(
name,
shape=None,
dtype=None,
initializer=None
)
Only for use by descendants of Metric.
tf.contrib.eager.metrics.CategoricalAccuracy.aggregate
aggregate(metrics)
Adds in the state from a list of metrics.
Default implementation sums all the metric variables.
Args:
metrics
: A list of metrics with the same type asself
.
Raises:
ValueError
: If metrics contains invalid data.
tf.contrib.eager.metrics.CategoricalAccuracy.build
build(
*args,
**kwargs
)
Method to create variables.
Called by __call__()
before call()
for the first time.
Args:
*args
: ***kwargs
: The arguments to the first invocation of__call__()
.build()
may use the shape and/or dtype of these arguments when deciding how to create variables.
tf.contrib.eager.metrics.CategoricalAccuracy.call
call(
labels,
predictions,
weights=None
)
Accumulate accuracy statistics.
labels
and predictions
should have the same shape.
As argmax is being done here, labels and predictions type
can be different.
Args:
labels
: One-hot Tensor.predictions
: Tensor with the logits or probabilities for each example.weights
: Optional weighting of each example. Defaults to 1.
Returns:
The arguments, for easy chaining.
tf.contrib.eager.metrics.CategoricalAccuracy.init_variables
init_variables()
Initializes this Metric's variables.
Should be called after variables are created in the first execution
of __call__()
. If using graph execution, the return value should be
run()
in a session before running the op returned by __call__()
.
(See example above.)
Returns:
If using graph execution, this returns an op to perform the initialization. Under eager execution, the variables are reset to their initial values as a side effect and this function returns None.
tf.contrib.eager.metrics.CategoricalAccuracy.result
result(write_summary=True)
Returns the result of the Metric.
Args:
write_summary
: bool indicating whether to feed the result to the summary before returning.
Returns:
aggregated metric as float.
Raises:
ValueError
: if the optional argument is not bool
tf.contrib.eager.metrics.CategoricalAccuracy.value
value()
In graph mode returns the result Tensor while in eager the callable.