tf.math.count_nonzero

TensorFlow 1 version View source on GitHub

Computes number of nonzero elements across dimensions of a tensor.

tf.math.count_nonzero(
    input, axis=None, keepdims=None, dtype=tf.dtypes.int64, name=None
)

Reduces input along the dimensions given in axis. Unless keepdims is true, the rank of the tensor is reduced by 1 for each entry in axis. If keepdims is true, the reduced dimensions are retained with length 1.

If axis has no entries, all dimensions are reduced, and a tensor with a single element is returned.

For example:

x = tf.constant([[0, 1, 0], [1, 1, 0]])
tf.math.count_nonzero(x)  # 3
tf.math.count_nonzero(x, 0)  # [1, 2, 0]
tf.math.count_nonzero(x, 1)  # [1, 2]
tf.math.count_nonzero(x, 1, keepdims=True)  # [[1], [2]]
tf.math.count_nonzero(x, [0, 1])  # 3

For example:

x = tf.constant(["", "a", "  ", "b", ""])
tf.math.count_nonzero(x) # 3, with "a", "  ", and "b" as nonzero strings.

input The tensor to reduce. Should be of numeric type, bool, or string.
axis The dimensions to reduce. If None (the default), reduces all dimensions. Must be in the range [-rank(input), rank(input)).
keepdims If true, retains reduced dimensions with length 1.
dtype The output dtype; defaults to tf.int64.
name A name for the operation (optional).

The reduced tensor (number of nonzero values).