C5 W4 A1: Scaled_dot_product_attention AttributeError: 'tuple' object has no attribute 'rank'

[TMosh]

Also, I recommend you read this thread:

C5 W4 A1 scaled_dot_product_attention - Tip

If you get an error from the tf.keras.activations.softmax() function about “tuple object has no attribute rank”, then be sure you used tf.matmul() when computing Q*K’. and not np.matmul(). The functions do the same thing, but tf.matmul() returns a tensor, which is what the Keras softmax() function requires.