C3_W3_Exercise2

[pongyuenlam]

My codes generated 2.41 instead of 0.70. Any advice?

[pongyuenlam]

Will advice from anyone?

[Nevermnd]

I’ve just started this course so will let you know when I get there.

[Nevermnd]

@pongyuenlam I am working on this week / assignment tomorrow, so I should have an answer for you (or, err… more like, ‘at least a best guess’-- Seeing as I am taking it and it is not like they secretly give me the answers or something).

I will let you know then.

** However, said that though now that I am thinking about the videos I’ve watch so far, I mean isn’t the range for the triplet loss supposed to be like min -1 max 1 ?

So how did you get 2 something ? I would check how you calculated/put together/implemented your

TripletLossFn() (i.e. are your calcs for cosine distance right ?)

otherwise, like I said, till then…

[Deepti_Prasad]

Hi @pongyuenlam

go through below comment links

NLP course Sequence Models Week 3 final programming assignment doubt

Hi @Rashmi11 Refrain from posting any grade cell codes in future. It is against community guidelines and continuing to do so can affect your use of discourse community. Your scores code recall requires you to mention v2 before v1. your compute tf.maximum among 0.0 and A as well as for B is incorrect. Read the instructions carefully again. it first mentions you subtracts margin-positive and then that value to be added to mean_negative for A and in case of B margin-positive and then added t…

C3W3 Triplet Loss Function

Hi @roses_r_red Your code requires correction for triplet_loss1 and triplet_loss2 While calculating the A and B A = subtract positive from margin and add closest_negative B = subtract positive from margin and add mean_negative You have used correctly the codes but because you have missed tuppling in these codes caused these error. Remember the instructions mentions first to subtract (margin-positive) and then add closest negative for A and mean_negative for B Also while recalling triplet …

C3W3 NLP - Ex 2 - Struggling with data types

The hint is a bit misleading, even I was stuck because of the same, arvyzukai NLP mentor guided me through So based on the instruction previous shared, axis should be 1 For the mask exclude positives, your code is correct. Next thing, check if the score codes is recalled as (v2, v1, transpose_b=true), note v2 is placed before v1

let me know if you still have issue.

Regards
DP

[pongyuenlam]

@Deepti_Prasad @Nevermnd Thanks a lot for the advice and suggestion. @Deepti_Prasad Your following suggestion can help me pass all tests of this exercise. “check if the score codes is recalled as (v2, v1, transpose_b=true), note v2 is placed before v1”