DLS 5, Week4, Exercise C7 "Wrong values in outd when training=True and use padding mask"

[rojinakashefi]

Is the unit test for C7 okay? cause my decoder layer (C6) get passed but in C7 I get
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)
235
236 outd, att_weights = decoderk(x, encoderq_output, True, look_ahead_mask, create_padding_mask(x))
→ 237 assert np.allclose(outd[1, 1], [-0.0250004, 0.50791883, -1.5877104, 1.1047921]), “Wrong values in outd when training=True and use padding mask”
238
239 print(“\033[92mAll tests passed”)

AssertionError: Wrong values in outd when training=True and use padding mask

[TMosh]

Perhaps this previous thread will be useful.

W4 Exercise 7: Decoder - AssertionError: Wrong values in outd

That you are using self.embedding(…). yes, I have self.embedding(x) That you are using tf.math.sqrt(…), and that you’re using the correct tf.cast() arguments. I think so: x *= tf.math.sqrt(tf.cast(self.embedding_dim, tf.float32)) That you are using the correct slicing in the call to self.pos_encoding(…). From the instructions, I understood pos_encoding[:, seq_len, :] That you are using training=training in the self.dropout(…). Confirmed. I used training=training in all lines with …

[rojinakashefi]

Yes, I’ve seen that before. But my pos_encoding is correct and other parts are the same as he has mentioned.

[Muhammad_Asad_Ali]

I’m facing the same issue, Please solve this bug. @staff @TMosh

[TMosh]

I do not think there is a problem with the assignment.

[TMosh]

There are quite a few places in this assignment where subtle errors in one function will trip an assert in another.

Please download your notebook ipynb file and send it to me via a private message. I’ll review it and provide comments.

[Muhammad_Asad_Ali]

No thanks, Dear My error was in coding. And it’s solved by doing some changes.

Thanks for cooperating.