tf.math.argmax

TensorFlow 1 version View source on GitHub

Returns the index with the largest value across axes of a tensor.

tf.math.argmax(
    input, axis=None, output_type=tf.dtypes.int64, name=None
)

In case of identity returns the smallest index.

For example:

A = tf.constant([2, 20, 30, 3, 6])
tf.math.argmax(A)  # A[2] is maximum in tensor A
<tf.Tensor: shape=(), dtype=int64, numpy=2>
B = tf.constant([[2, 20, 30, 3, 6], [3, 11, 16, 1, 8],
                 [14, 45, 23, 5, 27]])
tf.math.argmax(B, 0)
<tf.Tensor: shape=(5,), dtype=int64, numpy=array([2, 2, 0, 2, 2])>
tf.math.argmax(B, 1)
<tf.Tensor: shape=(3,), dtype=int64, numpy=array([2, 2, 1])>
C = tf.constant([0, 0, 0, 0])
tf.math.argmax(C) # Returns smallest index in case of ties
<tf.Tensor: shape=(), dtype=int64, numpy=0>

input A Tensor.
axis An integer, the axis to reduce across. Default to 0.
output_type An optional output dtype (tf.int32 or tf.int64). Defaults to tf.int64.
name An optional name for the operation.

A Tensor of type output_type.