sparse_softmax_cross_entropy_with_logits(_sentinel=None, # pylint: disable=invalid-name,labels=None, logits=None,name=None):
_sentinel:本质上是不用的参数,不用填
logits:shape为[batch_size,num_classes],type为float32或float64
name:操作的名字,可填可不填
import tensorflow as tf
input_data = tf.Variable([[0.2, 0.1, 0.9], [0.3, 0.4, 0.6]], dtype=tf.float32)
output = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=input_data, labels=[0, 2])
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
print(sess.run(output))
# [ 1.36573195 0.93983102]