W4_A1_Ex-5_Local variable referenced

[Shiangtang]

Hi, I am stuck at this exercise, I couldn’t fix the traceback. Could you please help? Thanks!

{code removed by mentor}

[rmwkwok]

Hello @Shiangtang,

I think your solution was having the same problem as this post that I had answered previously. Please check it out.

[DLS Course1] week4 last assignment issue

Hello @yusinjeong5859 씨 This error is very tricky. I followed the error traceback to the definition of linear_activation_forward which is inside dnn_app_utils_v3.py (avaiable to you as well). If we look at its code: [image] then you can see that the function expected either "sigmoid" or "relu" as the value for activiation. If we have provided anything other than those, then A will never be assigned any value. Consequently, as it ran assert (A.shape == (W.shape[0], A_prev.shape[…

Cheers,
Raymond

PS: I have removed your code since sharing it violates the honor code.

[Shiangtang]

Hi, Raymond, thanks for your reply. I went through the other post you referenced, which says something about the function expects either sigmoid or relu as the value for activation. But I still don’t know what’s wrong with my codes, since I used sigmoid/relu as the value inside the function in question. Could you say more about this? Also I’m not able to see the entire traceback on Coursera Jupiter.

PS: what’s the correct way to ask a question about my code if we are not allowed to post it here?

Thanks!

[rmwkwok]

Hello @Shiangtang,

@Shiangtang

what’s the correct way to ask a question about my code if we are not allowed to post it here?

The error traceback which you have provided. (the image that I have not removed)

@Shiangtang

since I used sigmoid/relu as the value inside the function in question. Could you say more about this?

Note that from the post which I have shared, the program was checking if the activation input is among one of ['relu', 'sigmoid'].

Cheers,
Raymond

[paulinpaloalto]

Yes, we can see the bug that Raymond is pointing out in the exception trace.