numpy和tensorflow中矩阵乘法的区别

np.dot

 

numpy.dot(a, b, out=None)

~~~Dot product of two arrays. Specifically,

• If both a and b are 1-D arrays, it is inner product of vectors (without complex conjugation).[one dimension的话（两个都是1维），就是数组内各个元素的乘积]
• If both a and b are 2-D arrays, it is matrix multiplication, but using matmul or a @ b is preferred.[two dimension的话（两个都是2维）就是矩阵乘法，但是推荐用np.matmull()这个方法]
• If either a or b is 0-D (scalar), it is equivalent to multiply and using numpy.multiply(a, b) or a * b is preferred.[如果两个中有一个或者都是标量的话，就直接认为是数乘即可，用np.multiply(a, b)即可，或者直接用符号*]

• If a is an N-D array and b is a 1-D array, it is a sum product over the last axis of a and b.[如果a是N维，b是1维（并不是随便的1维就行，要和a匹配上），最后就是a和b在最后axis上的积的和]

  例如： 
  a = [[1,0],[4,5]] 
  b = [3,10] 
  np.dot(a, b) 
  output:[3,62]

• If a is an N-D array and b is an M-D array (where M>=2), it is a sum product over the last axis of a and the second-to-last axis of b:

 

np.matmull()

~~~Matrix product of two arrays.

• If both arguments are 2-D they are multiplied like conventional matrices.
• If either argument is N-D, N > 2, it is treated as a stack of matrices residing in the last two indexes and broadcast accordingly.
• If the first argument is 1-D, it is promoted to a matrix by prepending a 1 to its dimensions. After matrix multiplication the prepended 1 is removed.
• If the second argument is 1-D, it is promoted to a matrix by appending a 1 to its dimensions. After matrix multiplication the appended 1 is removed. 
  Note：np.matmull()平常最常用的就是矩阵的乘法。

 

tf.matmull()

~~~Multiplies matrix a by matrix b, producing a * b. 
Note:tf.matmull()做的也是矩阵的乘法。但是np.matmull()和tf.matmull()还是有区别的，最起码他们各自的返回值是不一样的，tf返回的是tensor，np返回的是ndarray。