How to handle tensor multiplication with dimension None

Question

For example I have 2 tensors A and B both with dimension (None, HWC), when I use

tf.matmul(tf.transpose(A),B)

The result dimension will be (HWC,HWC), this is correct but I want to keep the None dimension so it can be(None, HWC, HWC). Is there anyway to achieve this?

Answer 1

Maybe try something like this:

import tensorflow as tf

input1 = tf.keras.layers.Input(((32, 32, 3)))
input2 = tf.keras.layers.Input(((32, 32, 3)))
a = tf.keras.layers.Conv2D(64, (1, 1))(input1)
b = tf.keras.layers.Conv2D(64, (1, 1))(input2)
z = tf.matmul(a, b, transpose_a=True)
model = tf.keras.Model([input1, input2], z)
print(model.summary())

Model: "model_1"
__________________________________________________________________________________________________
 Layer (type)                   Output Shape         Param #     Connected to                     
==================================================================================================
 input_11 (InputLayer)          [(None, 32, 32, 3)]  0           []                               
                                                                                                  
 input_12 (InputLayer)          [(None, 32, 32, 3)]  0           []                               
                                                                                                  
 conv2d_17 (Conv2D)             (None, 32, 32, 64)   256         ['input_11[0][0]']               
                                                                                                  
 conv2d_18 (Conv2D)             (None, 32, 32, 64)   256         ['input_12[0][0]']               
                                                                                                  
 tf.linalg.matmul_4 (TFOpLambda  (None, 32, 64, 64)  0           ['conv2d_17[0][0]',              
 )                                                                'conv2d_18[0][0]']              
                                                                                                  
==================================================================================================
Total params: 512
Trainable params: 512
Non-trainable params: 0
__________________________________________________________________________________________________
None