Tensorflow中的Tensor乘法 [英] Tensor multiplication in Tensorflow
问题描述
我正在尝试在NumPy/Tensorflow中进行张量乘法.
I am trying to carry out tensor multiplication in NumPy/Tensorflow.
我有3个张量-A (M X h), B (h X N X s), C (s X T)
.
我相信A X B X C
应该产生张量D (M X N X T)
.
这是代码(同时使用numpy和tensorflow).
Here's the code (using both numpy and tensorflow).
M = 5
N = 2
T = 3
h = 2
s = 3
A_np = np.random.randn(M, h)
C_np = np.random.randn(s, T)
B_np = np.random.randn(h, N, s)
A_tf = tf.Variable(A_np)
C_tf = tf.Variable(C_np)
B_tf = tf.Variable(B_np)
# Tensorflow
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
print sess.run(A_tf)
p = tf.matmul(A_tf, B_tf)
sess.run(p)
这将返回以下错误:
ValueError: Shape must be rank 2 but is rank 3 for 'MatMul_2' (op: 'MatMul') with input shapes: [5,2], [2,2,3].
如果仅尝试与numpy矩阵相乘,则会出现以下错误:
If we try the multiplication only with numpy matrices, we get the following errors:
np.multiply(A_np, B_np)
ValueError: operands could not be broadcast together with shapes (5,2) (2,2,3)
但是,我们可以按以下方式使用np.tensordot
:
However, we can use np.tensordot
as follows:
np.tensordot(np.tensordot(A_np, B_np, axes=1), C_np, axes=1)
TensorFlow中是否存在等效操作?
Is there an equivalent operation in TensorFlow?
在numpy中,我们将执行以下操作:
In numpy, we would do as follows:
ABC_np = np.tensordot(np.tensordot(A_np, B_np, axes=1), C_np, axes=1)
在tensorflow中,我们将执行以下操作:
In tensorflow, we would do as follows:
AB_tf = tf.tensordot(A_tf, B_tf,axes = [[1], [0]])
AB_tf_C_tf = tf.tensordot(AB_tf, C_tf, axes=[[2], [0]])
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
ABC_tf = sess.run(AB_tf_C_tf)
np.allclose(ABC_np, ABC_tf)
返回True
.
推荐答案
尝试
tf.tensordot(A_tf, B_tf,axes = [[1], [0]])
例如:
x=tf.tensordot(A_tf, B_tf,axes = [[1], [0]])
x.get_shape()
TensorShape([Dimension(5), Dimension(2), Dimension(3)])
这里是 tensordot文档,这里是相关的 github存储库.
Here is tensordot documentation, and here is the relevant github repository.
这篇关于Tensorflow中的Tensor乘法的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!