Assignment 2 - Named Entity Recognition (NER)_Exercise 5_masked_accuracy

[vemula_suman]

hi ,
I could not able to resolve the below issue ,please correct me where i made mistake.

thank you

[Deepti_Prasad]

Hi @vemula_suman

please go through the below post

C3W2: Exercise 2,5 and error

Hi @Juan_David_Vargas_Al This error message is a bit misleading since it “Expected” and “Got” do not match because of -1 and 0, but not because -1 are not “post”. So make sure you use pad value of -1 (and also how your label_ids are constructed). As for Exercise 5 and the mask creation - you need to check if the labels (the y_true) do not equal -1. One way of doing it could be (y_true != -1) which would return a boolean tensor which later you would need to cast to tf.float32) and that would b…

Let me know if issue still persist after the correction.

Regards
DP

[vemula_suman]

Hi Deepthi ,
I went through you reference ,but still getting the same error.

[Deepti_Prasad]

hi @vemula_suman

For code line

Compute masked accuracy (quotient between the total matches and the total valid values, i.e., the amount of non-masked values)
Here you have used incorrect code for total valid values(denominator) where you used len function to the y_pred instead you were suppose to use tf.reduce_sum function to the mask values.

Regards
DP

[vemula_suman]

Thank you very much Deepti
got solution

[Deepti_Prasad]

@vemula_suman

I suppose you are quite old to this platform to know that sharing codes is against community guidelines and your image shows part of the code from grade cell, so kindly remove it.

Happy to help!

Keep Learning!!

Regards
DP

[vemula_suman]

Sorry ,I have mistakenly sent code part