【tensorflow】 tf.argmax() 用法例子

版权声明：本文为博主原创文章，引用时请附上链接。 https://blog.csdn.net/abc13526222160/article/details/86288830

argmax()官方文档如下：

tf.argmax(input, dimension, name=None) 
Returns the index with the largest value across dimensions of a tensor. 
Args: 
input: A Tensor. Must be one of the following types: float32, float64, int64, int32, uint8, int16, int8, complex64, qint8, quint8, qint32. 
dimension: A Tensor of type int32. int32, 0 <= dimension < rank(input). Describes which dimension of the input Tensor to reduce across. For vectors, use dimension = 0. 
name: A name for the operation (optional). 
Returns: 
A Tensor of type int64.

dimension=0 按列找 
dimension=1 按行找 
tf.argmax()返回最大数值的下标 
通常和tf.equal()一起使用，计算模型准确度 

correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

 例如：

>>> import tensorflow as tf
>>> a = tf.constant([1.,2.,3.,0.,9.,])
>>> b = tf.constant([[1,2,3],[3,2,1],[4,5,6],[6,5,4]])
>>> with tf.Session() as sess:
...     sess.run(tf.argmax(a, 0))
... 
4
>>> with tf.Session() as sess:
...     sess.run(tf.argmax(b, 0))
... 
array([3, 2, 2])
>>>