from tensorflow.keras.layers import Layer
from tensorflow.keras import backend as K

class Attention(Layer):

def __init__(self, return_sequences=True):
    self.return_sequences = return_sequences
    super(Attention,self).__init__()
    
def build(self, input_shape):
    
    self.W=self.add_weight(name="att_weight", shape=(input_shape[-1],1),
                           initializer="normal")
    self.b=self.add_weight(name="att_bias", shape=(input_shape[1],1),
                           initializer="zeros")
    
    super(Attention,self).build(input_shape)
    
def call(self, x):
    
    e = K.tanh(K.dot(x,self.W)+self.b)
    a = K.softmax(e, axis=1)
    output = x*a
    
    if self.return_sequences:
        return output
    
    return K.sum(output, axis=1)

calling this with in CNN block with this:

Attention()[x,x] where x in output of previous layer

need architectural diagram of this code