ArgMax

public final class ArgMax

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

Note that in case of ties the identity of the return value is not guaranteed.

Usage:

import tensorflow as tf
   a = [1, 10, 26.9, 2.8, 166.32, 62.3]
   b = tf.math.argmax(input = a)
   c = tf.keras.backend.eval(b)
   # c = 4
   # here a[4] = 166.32 which is the largest element of a across axis 0
   

Constants

String OP_NAME The name of this op, as known by TensorFlow core engine

Public Methods

Output<V>
asOutput()
Returns the symbolic handle of the tensor.
static <V extends TNumber> ArgMax<V>
create(Scope scope, Operand<? extends TType> input, Operand<? extends TNumber> dimension, Class<V> outputType)
Factory method to create a class wrapping a new ArgMax operation.
static ArgMax<TInt64>
create(Scope scope, Operand<? extends TType> input, Operand<? extends TNumber> dimension)
Factory method to create a class wrapping a new ArgMax operation using default output types.
Output<V>
output()

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "ArgMax"

Public Methods

public Output<V> asOutput ()

Returns the symbolic handle of the tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

public static ArgMax<V> create (Scope scope, Operand<? extends TType> input, Operand<? extends TNumber> dimension, Class<V> outputType)

Factory method to create a class wrapping a new ArgMax operation.

Parameters
scope current scope
dimension int32 or int64, must be in the range `[-rank(input), rank(input))`. Describes which dimension of the input Tensor to reduce across. For vectors, use dimension = 0.
Returns
  • a new instance of ArgMax

public static ArgMax<TInt64> create (Scope scope, Operand<? extends TType> input, Operand<? extends TNumber> dimension)

Factory method to create a class wrapping a new ArgMax operation using default output types.

Parameters
scope current scope
dimension int32 or int64, must be in the range `[-rank(input), rank(input))`. Describes which dimension of the input Tensor to reduce across. For vectors, use dimension = 0.
Returns
  • a new instance of ArgMax

public Output<V> output ()