tf.matmul函數用法

matmul(
    a,
    b,
    transpose_a=False,
    transpose_b=False,
    adjoint_a=False,
    adjoint_b=False,
    a_is_sparse=False,
    b_is_sparse=False,
    name=None
)

# 2-D tensor `a`
a = tf.constant([1, 2, 3, 4, 5, 6], shape=[2, 3]) => [[1. 2. 3.]
                                                      [4. 5. 6.]]
# 2-D tensor `b`
b = tf.constant([7, 8, 9, 10, 11, 12], shape=[3, 2]) => [[7. 8.]
                                                         [9. 10.]
                                                         [11. 12.]]
c = tf.matmul(a, b) => [[58 64]
                        [139 154]]

# 3-D tensor `a`
a = tf.constant(np.arange(1, 13, dtype=np.int32),
                shape=[2, 2, 3])                  => [[[ 1.  2.  3.]
                                                       [ 4.  5.  6.]],
                                                      [[ 7.  8.  9.]
                                                       [10. 11. 12.]]]

# 3-D tensor `b`
b = tf.constant(np.arange(13, 25, dtype=np.int32),
                shape=[2, 3, 2])                   => [[[13. 14.]
                                                        [15. 16.]
                                                        [17. 18.]],
                                                       [[19. 20.]
                                                        [21. 22.]
                                                        [23. 24.]]]
c = tf.matmul(a, b) => [[[ 94 100]
                         [229 244]],
                        [[508 532]
                         [697 730]]]

transpose_a：如果 True,a 在乘法之前轉置.
transpose_b：如果 True,b 在乘法之前轉置.

1、如果transpose_b參數設置爲False，那麼x的最後一維要跟y的倒數第二維相等，即:

tf.matmul(x, y, transpose_b = False)
x.shape = [..., x1, x2]
y.shape = [..., y1, y2]
x2 = y1

2、如果transpose_b參數設置爲True，那麼x的最後一維要跟y的最後一維相等，transpose_b=True只是把第二個矩陣（這裏就是y）的最後兩維換了下，即:

tf.matmul(x, y, transpose_b = True)
x.shape = [..., x1, x2]
y.shape = [..., y1, y2]
x2 = y2