Invalid value encountered in true_divide

#1

C:\Users\Saquib\Anaconda3\lib\site-packages\ipykernel_launcher.py:3: RuntimeWarning: invalid value encountered in true_divide
This is separate from the ipykernel package so we can avoid doing imports until

#2

sir in neural network this error is come always when i am trying to train my models different datasets

#3

Hey @mohd_saquib plz share your ipynb by uploading it on google drive and sharing the link here

#4

https://drive.google.com/open?id=1Dom62V2pWLRVRadIK293YgbveuJiuwcp

#5

i drop two columns ‘SkinThickness’, ‘Insulin’ by wrapper method still get 78% accuracy…

#6

Hey @mohd_saquib, with knn maximum achievable accuracy is 78%, If you want to achieve more you need to switch to deep learning techniques, and that you have to do on your own. You can try out as many things as you want, but you have qualified the criteria for this, i.e. 78% which was of our concern. So if you want to apply dl techniques, plz don’t expect we will check your codes line by line, etc, it is not feasible at our end.

Hope you understand what i meant to say. Happy Learning :blush:

#7

i apply neural netwoks also but only dense layers is convoution layer helps should i add

#8

sir you see my submission i do since morning can you share the code 84% accuracy

#9

Hey @mohd_saquib, we didn’t have that one with us, the problem is part of knn, so its logical to use that only. But those who explored more, have achieved more, which they themselves don’t want to reveal.

#10

sir you said send the code link i willl send it yesterday still no reply sir this is my neural network code and i will tell you what is the error

#11

ok i will also explore more but help me to remove my errors

#12

sir i will tell you my problems or error when i have option see the errors on internet and discuss with friends then after i will discuss to you so please help me

#13

Hey @mohd_saquib, i have seen your code, the error is that, you have used ‘mse’ loss function, you need to use binary cross entropy or categorical cross entropy. And change all gradient descend formulas accordingly.
Binary cross entropy when last layer has sigmoid activation and one output value, other wise when you use 2 output values for each class, you need to use categorical cross entropy. Both formulas derivation is not that easy, better implement with the help of keras library.

Happy Leaning :blush:

#14

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.