C4-w2 assingmenr grader][;

[Deepti_Prasad]

@Paul_katz

i guess till now you know you are not suppose to post codes, share assignment which are graded on public posts.

in case you forgot, kindly check FAQ SECTION for CODE OF CONDUCT.

the mentor asked you to send the codes via personal DM.

Also check similar threads already created by learners, go through the whole thread to understand if you have done similar code errors which help you in debugging your codes

C4W2 cannot graded

For future learners - the OP’s mistake was in defining the dec_padding_mask. Note, that when creating padding mask for the decoder’s second attention block - we use the encoder_input. In other words, we inform the decoder to not pay attention to padding tokens of the document to be summarized. Also note, that this is different from look_ahead_mask (causal mask) where decoder is only allowed to pay attention to itself and its previous tokens. Cheers

C4W2 - Grading Error

Hi @Sadiah_Safirah This error indicates that the shape of the mask is not the same as shape of the inputs (in the scaled_dot_product_attention case the inputs are scaled_attention_logits). So the most probable place to look for a mistake is below the code comment: # add the mask to the scaled tensor. Here you would calculate the masked “inputs” for the softmax. (The hint suggests: Reminder: The boolean mask parameter can be passed in as none or as either padding or look-ahead. Multiply (1…

Kindly use search tool, there are already so many threads with same error which will help you resolve your issue. otherwise, the mentor who asked you to send codes will guide you further.

If still unable to get the resolution of your issue, kindly let us know.

Also it is humble request again not to post codes from grade cell, not share assignment notebook in future on post threads.

Regards
DP