f.argmax(data, axis=None)
一维数组
data = tf.constant([1,2,3])
with tf.Session() as sess:
print(sess.run(tf.argmax(data, 0)))
#轴默认为0
print(sess.run(tf.argmax(data)))
>>> 2
>>> 2
二维数组
data = tf.constant([[1,2,3], [4,5,6]])
with tf.Session() as sess:
print(sess.run(tf.argmax(data, 0)))
print(sess.run(tf.argmax(data, 1)))
>>> [1, 1, 1]
>>> [2, 2]
三维数组
data = tf.constant([[[1,2,3]],
[[7, 1,9]]])
with tf.Session() as sess:
print(sess.run(tf.argmax(data, 0)))
print(sess.run(tf.argmax(data, 1)))
print(sess.run(tf.argmax(data, 2)))
>>> [[1 0 1]]
>>> [[0,0,0],[0,0,0]]
>>> [[2],[2]]
针对三维的情况,下面给出一张图,帮助立即0、1、2的维度情况。