用於一個回歸任務或者正則問題

1 # l2損失，output= sum(x ** 2)/2
2 inputdata = tf.Variable(np.random.rand(2,3), dtype=np.float32)
3 loss = tf.nn.l2_loss(inputdata)    # 標量
4 with tf.Session() as sess:
5     sess.run(tf.global_variables_initializer())
6     print (sess.run(inputdata))
7     print (sess.run(loss))

輸出：

[[ 0.99520844 0.57105571 0.4224354 ]
[ 0.77398151 0.40279421 0.6592328 ]]
1.34544

TensorFlow 度量張量和張量或者和零之間的誤差值