C4-w2 assingmenr grader][;

[Paul_katz]

i cant seem to get my week 2 assignment to pass autograder- in my defense my laptop fell and ive been struggling with this 2017 imac while the macbook is i repair - i pass all unit tests but it gives me this whicj=h looks like a problrm with softmax and shape There was a problem compiling the code from your notebook. Details:
Exception encountered when calling layer ‘softmax_3’ (type Softmax).

{{function_node _wrapped__AddV2_device/job:localhost/replica:0/task:0/device:CPU:0}} Incompatible shapes: [1,2,2,150] vs. [1,1,1,2] [Op:AddV2] name:

Call arguments received by layer ‘softmax_3’ (type Softmax):
• inputs=tf.Tensor(shape=(1, 2, 2, 150), dtype=float32)
• mask=tf.Tensor(shape=(1, 1, 1, 2), dtype=float32)

[Girijesh]

Dear @Paul_katz,

Please send me your code to me via direct message(Click on my profile, then click on message button).

I’ll look into the issue(s) and let you know the solution(s).

[Paul_katz]

it has to be softmax enjoy your weekend - i thought i fixed first but guess not
[softmax ikssueC4W2_Assignment {Assignment notebook removed by moderator}

[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

[Paul_katz]

i do know that - im sorry i meant to dm =im having issues with backup computer ill stay off forum = until my mascbook returns

[Deepti_Prasad]

@Paul_katz

as community moderator, it is my duty to guide learners to follow guidelines. so please don’t stop from learning, you can DM your codes to the mentor who asked you to send it via personal DM.

people still post codes even after telling them many times, but we continue to assist. we only hope that learner also helps us follow the guidelines that is all.

so don’t stop from learning!

keep learning!!

regards
DP

[Paul_katz]

and thank you no need to help on this one solved it under my own power

[Deepti_Prasad]

let learner know of your power on what was the mistake you did and how you resolved it.