C5 W4 course 5 week 4 exercise 7

5 course 5 week 4 exercise 7
Hello someone who can please help me with
I already followed the instructions of Transformer model for language understanding  |  Text  |  TensorFlow and adjusted the variables of d_model, dff to embedding_dim, fully_connected_dim according to exercise 7 but when I execute the code in the output this message appears error :

AssertionError Traceback (most recent call last)
in
1 # UNIT TEST
----> 2 Decoder_test (Decoder, create_look_ahead_mask, create_padding_mask)

~ / work / W4A1 / public_tests.py in Decoder_test (target, create_look_ahead_mask, create_padding_mask)
221 assert tf.is_tensor (outd), “Wrong type for outd. It must be a dict”
222 assert np.allclose (tf.shape (outd), tf.shape (encoderq_output)), f “Wrong shape. We expected {tf.shape (encoderq_output)}”
→ 223 assert np.allclose (outd [1, 1], [-0.2715261, -0.5606001, -0.861783, 1.69390933]), “Wrong values ​​in outd”
224
225 keys = list (att_weights.keys ())

AssertionError: Wrong values ​​in outd

The TensorFlow tutorials don’t really apply to this assignment.

Why did you adjust d_model? There is no reason to change it.

in tensor flow it is shown as:

class Decoder (tf.keras.layers.Layer):
def init __ (self, num_layers, d_model, num_heads, dff, target_vocab_size,
maximum_position_encoding, rate = 0.1):
super (Decoder, self) .
init __ ()

in exercise 7 it is shown as:

def init __ (self, num_layers, embedding_dim, num_heads, fully_connected_dim, target_vocab_size,
maximum_position_encoding, dropout_rate = 0.1, layernorm_eps = 1e-6):
super (Decoder, self) .
init __ ()

in the 2 codes there is a lot of similarity and they are for decoding
the variables that change the “name” are d_model for embedding_dim, dff for fully_connected_dim, rate = 0.1 for dropout_rate = 0.1