W3 Classify function

[mackaseck]

Hi, I am having trouble with the Classify function. I am getting the error below. when i try to check the shape of y_pred. it says that it’s not defined, but an an empty list was created at the top y_pred = [ ] and later i fill out the code y_pred = tf.cast(d>threshold, tf.float64
Can someone assist me with this

[Deepti_Prasad]

hi @mackaseck

See if this helps you

NLP Course 3 Week 3: Confusion matrix

Hi @Taisiya_Kopytova You somehow mixed up two code lines Check if d>threshold to make predictions Here you were only suppose to check if cosine similarity is greater than threshold but you ended up adding the accuracy part of the code to this code line. Also do not hard code the path by introducing res = d > threshold (I KNOW THE HINT FROM PREVIOUS CELLS TELLS YOU TO DO SO. INSTEAD OF y_test == res, you only need to use tf.cast(d>threshold with the datatype). Next your accuracy code is…

Also check your v1 and v2 are recalled correctly, for this you can refer the below link

C3W3 classify all test passed but when graded, the score is 0

You are suppose to define the v1 and v2 according to _, n_feature and not assign values directly. Refer this image and do the changes

if issue still persist, then kindly share screenshot of complete error log as in the image you shared the lower half of the error only. When you have a lengthier error log, you can take two separate screenshots and post.

Just a reminder please make sure not to post any codes here as it is against community guidelines.

Regards
DP

[mackaseck]

Hi Deepti,

The I am still getting error. I have attached full screenshot.
Thanks.

[Deepti_Prasad]

is your pred codes correctly written. I hope you know you are not suppose to use q1 q2 rather the test_gen using the model.predict

[mackaseck]

i believe so. i message you a screenshot of the code so that i don’t have to share it here.

[Deepti_Prasad]

you haven’t used the axis argument while calculating the cosine similar as per instructions

[mackaseck]

Thank you so much Deepti!