![]() |
Returns the fraction of zeros in value
.
Aliases:
tf.compat.v1.math.zero_fraction
tf.compat.v1.nn.zero_fraction
tf.compat.v2.math.zero_fraction
tf.compat.v2.nn.zero_fraction
tf.nn.zero_fraction
tf.math.zero_fraction(
value,
name=None
)
If value
is empty, the result is nan
.
This is useful in summaries to measure and report sparsity. For example,
z = tf.nn.relu(...)
summ = tf.compat.v1.summary.scalar('sparsity', tf.nn.zero_fraction(z))
Args:
value
: A tensor of numeric type.name
: A name for the operation (optional).
Returns:
The fraction of zeros in value
, with type float32
.