tf.arg_max和tf.argmax

参考官方文档感觉这两个函数作用差不多但是我习惯用tf.argmax

format:argmax(input, axis=None, name=None, dimension=None)

Args:input: A `Tensor`. Must be one of the following types: `float32`, `float64`, `int64`, `int32`, `uint8`, `uint16`, `int16`, `int8`, `complex64`, `complex128`, `qint8`, `quint8`, `qint32`, `half`.
      axis: A `Tensor`. Must be one of the following types: `int32`, `int64`.(注意这里是整形就行了)
        int32, 0 <= axis < rank(input).  Describes which axis
        of the input Tensor to reduce across. For vectors, use axis = 0.
      name: A name for the operation (optional).

栗子

import tensorflow as tf  
x=tf.constant([[1.,2.,6],[6.,2.,6]])  

xShape=tf.shape(x)
z1=tf.arg_max(x,1)#沿axis=0操作


with tf.Session() as sess:
    xShapeValue,d1=sess.run([xShape,z1])
    print('shape= %s'%(xShapeValue))
    print(d1)

结果

一般用来求一个矩阵中，每行最大值的index，一般用在测试的时候。