Application is crashing

#1

I am running the model in jupyter notebook . When algorithm encounters more than 2 people in a single frame then CV.resize is throwing error every time.

But if number of people in frame < =2 then it is working fine .Can you please help me with this.

#2

Make sure you are resizing the right variable, and share your code after saving it on cb.lk/ide.

#3

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.

#4

Hi I am not able to ask doubt ? Getting warning like doubt support has ended

#5

Hi Team , i have find the area in image where eyes are there using eye_XML file. Now when i have tried to make modification in the main image i am getting o/p something like this : https://imgur.com/a/BLXkEgg when i am trying to read the glass png image it is being loaded like that black patch only . But when i am trying to open it in my laptop it is opening properly . Any work around this ?

#6

The image is of type png which means there are 4 channels and not 3, i.e. rgba, forth channel ‘a’ is for opacity, so you need to replace pixel values only when a>0. Also you need to resize the glass frame as well.

Hope this cleared your doubt. :blush:

#7

Hi Why i am not able to ask doubt ???

#8

second … In snapchat filter i am having doubt …

#9

I have got the same output image as expected . but when i am saving the image in csv format and calculating the accuracy i am getting accuracy as -ve value . Please find the link of the o/p which i got : https://imgur.com/3vkZaQ5 any suggestion how i have to convert the image.

#10

You are requested to refrain from opening the previously resolved doubts and than posting the new doubt there. We have made something to protect our portal from so called “Spamming” and that’s the reason you are not able to post new doubts.

First of all you need to reshape the final image array to shape (-1,3) and than include the header as channel 1 , channel 2 etc as in submission file.

pd.Dataframe(numpy_array).to_csv(‘submission.csv’, header= [‘Channel 1’,‘Channel 2’,‘Channel 3’], index = False)

Hope this resolved your doubt. And next time take care of the said measures.

#11

If you’re not able to post doubt using the “Ask Doubt” section, Please mail your issue at [email protected]
They will respond to you within 24 hours

Happy Learning :sunny:

#12

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.