TensorFlow Error: Shape must be rank 2 but are rank 3 for ' Matmul ' (op: ' Matmul ') __ Depth study

TensorFlow matrix multiplication, rank different error

In the TensorFlow wrote such a sentence:

[python] view plain copy print? Y_out = Tf.matmul (outputs, W)

Y_out = Tf.matmul (outputs, W)

Where the shape of the outputs [16,336,400],w shape is [400,1]

The following error occurred:

Shape must be rank 2 but are rank 3 for ' Matmul ' (op: ' Matmul ') with input shapes: [16,336,400], [400,1].

NumPy, there's no problem with the same wording.

[Python] View Plain copy print? import numpy as np      A = np.array ([[[1, 2, 3, 4],            [5, 6, 7, 8],            [9, 0, 1, 2]],            [[4, 3, 2, 1],            [8, 7, 6, 5],                   [2, 1, 0, 9]])    print (A)    print (A.shape)    print (' ————————— ')       b = np.array ([1], [2], [3], [4 ]]    print (B)    print (B.shape)    print (' ————————— ')       c  = np.matmul (a, b)    print (C)    print (C.shape)   

Import NumPy as np

A = Np.array ([[[1, 2, 3, 4],
[5, 6, 7, 8],
[9, 0, 1, 2]],  [[ 4, 3, 2, 1],
[8, 7, 6, 5], [2, 1, 0, 9]]]
print (A) print (a.shape) print (
'----- ----------------------')

B = Np.array ([[1], [2], [3], [4]]) print (
B)
print (b.shape) print (
'---- -----------------------')

C = Np.matmul (A, B)
print (c)
print (C.shape)

Output results:

[python] view plain copy print?   [[[1 2 3 4] [5 6 7 8] [9 0 1 2]] [[4 3 2 1] [8 7 6 5] [2 1 0 9]]]     (2, 3, 4) ————————— [[1] [2] [3] [4]] (4, 1) ————————— [[[30] [70] [20]] [[20] [60] [40]]] (2, 3, 1)

[[[1 2 3 4] [5 6 7 8] [9 0 1 2]] [[4 3 2 1] [8 7 6 5] [2 1 0 9
  ]]]

(2, 3, 4)---------------------------[[1] [2] [3] [4]] (4, 1)---------------------------[[[30] [70] [20]] [[20] [60] [4 0]]] (2, 3, 1)

Solutions

[Python] View Plain copy print? import numpy as np   import tensorflow as tf   sess =  TF. Session ()       A = np.array ([[[1, 2, 3, 4],                   [5, 6, 7, 8],                   [9,  0, 1, 2]],                  [[4, 3, 2, 1],                   [8, 7, 6, 5],                   [2, 1, 0, 9]]]    B =  np.array ([[[1], [2], [3], [4]]])       a = tf.caSt (Tf.convert_to_tensor (A),  tf.int32)  # shape=[2, 3, 4]   b =  Tf.cast (Tf.convert_to_tensor (B),  tf.int32)  # shape=[4, 1]      # ———————— ————— – Modify part (start) ————————————— –   #要想让A和B进行tf. Matmul operation, the first dimension must be consistent. So the first dimension of B-tile is converted to [2, 4, 1]    b_ = tf.tile (b, [2, 1]) # b to replicate twice times, Second dimensional replication 1 time times    B = tf.reshape (b_, [2, 4, 1])    #  or   more general modification:    #B_  = tf.tile (B, [tf.shape (A) [0], 1])    #B  = tf.reshape (b_,  [tf.shape (A) [0], tf.shape (b) [0], tf.shape (b) [1]])    # —————————————-Modify part (end) —————————— ——— –      #此时就可以matmul了    c = tf.matmul (a, b)    print (' C: ', C.get_shape (). As_list ())    Sess.run (C)   

import NumPy as NP import TensorFlow as tf sess = tf. Session () A = Np.array ([[[[1, 2, 3, 4],                 [5, 6, 7, 8],                [9, 0, 1, 2]] ,               [[4, 3, 2, 1],                 [8, 7, 6, 5],                 [2, 1, 0, 9]]) B = Np.array ([[1], [2], [3], [4]]) A = Tf.cast (TF. Convert_to_tensor (A), Tf.int32) # shape=[2, 3, 4] B = Tf.cast (Tf.convert_to_tensor (B), Tf.int32) # shape=[4, 1] 

#-----------------------------------------Modify part (start)-----------------------------------------# For A and B to Tf.matmul operations, the first dimension must be consistent. So we have to tile B first and then turn it into [2, 4, 1] D b_ = Tf.tile (b, [2, 1]) # b The first-dimension copy twice times, the second dimension replicates 1 time times B = Tf.reshape (B_, [2, 4, 1]) # or more general modification: #B_ = tf.tile (b, [Tf.shape (a) [0], 1]) #B = Tf.reshape (B_, [Tf.shape (a) [0], Tf.shape (b) [0], Tf.shape (b) [1]]) #----------------------- ------------------Modify part (end)-----------------------------------------#此时就可以matmul了 C = Tf.matmul (A, B) print (' C: ', C.get_shape (). As_list ()) Sess.run (C)

Output results:

[python] view plain copy print?  (' C: ', [2, 3, 1]) array ([[[[30], [70], [20]], [[20], [60], [40]]], DTYPE=INT32)

(' C: ', [2, 3, 1])

Array ([[[[M],
        [M], [[]]
        ],

       [[M], [m],
        []]]
        , Dtype=int32

Transfer from blog: http://blog.csdn.net/blythe0107/article/details/74171870