关于tf.matmul() 和tf.multiply() 的区别说明

# a
# [[1, 2, 3],
# [4, 5, 6]] a = tf.constant([1, 2, 3, 4, 5, 6], shape=[2, 3])

# b1
# [[ 7, 8],
# [ 9, 10],
# [11, 12]] b1 = tf.constant([7, 8, 9, 10, 11, 12], shape=[3, 2])

#b2
#[[ 7 8 9]
# [10 11 12]] b2 = tf.constant([7, 8, 9, 10, 11, 12], shape=[2, 3])

# c矩阵相乘 第一个矩阵的列数（column）等于第二个矩阵的行数（row）
# [[ 58, 64],
# [139, 154]] c = tf.matmul(a, b1)

# d`数元素各自相乘
#[[ 7 16 27]
# [40 55 72]] d = tf.multiply(a, b2) #维度必须相等 with tf.Session():
 print(d.eval())

b3 = tf.constant([7, 8, 9,], shape=[1, 3])
tf.multiply(a, b3)
结果是
[[ 7 16 27]
 [28 40 54]]

b4 = tf.constant([7, 8], shape=[2, 1])
tf.multiply(a, b4)
结果是
[[ 7 14 21]
 [32 40 48]]

b5 = tf.constant([7], shape=[1, 1])
tf.multiply(a, b5)

结果是

[[ 7 14 21]
 [28 35 42]]

> import torch
> a=torch.rand((1000,5,10))
> b=torch.rand((1000,10,12))
> c=torch.matmul(a,b)
> c.shape
torch.Size([1000, 5, 12])

> a=torch.rand((50,1000,5,10))
> b=torch.rand((1000,10,12))
> c=torch.matmul(a,b)
> c.shape
torch.Size([50, 1000, 5, 12])