W3Cschool
恭喜您成為首批注冊(cè)用戶(hù)
獲得88經(jīng)驗(yàn)值獎(jiǎng)勵(lì)
tf.keras.backend.dot(
x,
y
)
定義在:tensorflow/python/keras/backend.py。
將2個(gè)張量(或變量)相乘并返回張量。
當(dāng)試圖將nD張量與nD張量相乘時(shí),它會(huì)再現(xiàn)Theano行為。(例如:(2, 3) * (4, 3, 5) -> (2, 4, 5))
參數(shù):
返回:
一個(gè)張量,x
和y
的點(diǎn)積。
例子:
# dot product between tensors
>>> x = K.placeholder(shape=(2, 3))
>>> y = K.placeholder(shape=(3, 4))
>>> xy = K.dot(x, y)
>>> xy
<tf.Tensor 'MatMul_9:0' shape=(2, 4) dtype=float32>
# dot product between tensors
>>> x = K.placeholder(shape=(32, 28, 3))
>>> y = K.placeholder(shape=(3, 4))
>>> xy = K.dot(x, y)
>>> xy
<tf.Tensor 'MatMul_9:0' shape=(32, 28, 4) dtype=float32>
# Theano-like behavior example
>>> x = K.random_uniform_variable(shape=(2, 3), low=0, high=1)
>>> y = K.ones((4, 3, 5))
>>> xy = K.dot(x, y)
>>> K.int_shape(xy)
(2, 4, 5)
Copyright©2021 w3cschool編程獅|閩ICP備15016281號(hào)-3|閩公網(wǎng)安備35020302033924號(hào)
違法和不良信息舉報(bào)電話(huà):173-0602-2364|舉報(bào)郵箱:jubao@eeedong.com
掃描二維碼
下載編程獅App
編程獅公眾號(hào)
聯(lián)系方式:
更多建議: