Community

Accuracy greater th...
 
Share:

Accuracy greater than 100% on loading a keras model and training it further  

  RSS

hunny9891
(@hunny9891)
Active Member
Joined: 8 months ago
Posts: 5
17/03/2019 11:20 pm  

Hi,

I am into this weird problem where i loaded a pre trained keras model which was trained for 300 iteration on cifar10 dataset and had a test accuracy of 67%. Now i loaded the model and trained it for few iterations more but this time got test accuracy of 267%.

How is that possible? What would be possibly wrong?


Quote
hunny9891
(@hunny9891)
Active Member
Joined: 8 months ago
Posts: 5
21/03/2019 11:45 pm  

Never mind it was a silly bug. Sorry for posting this.


ReplyQuote
devanshi.bhimjiyani
(@devanshi-bhimjiyani)
New Member
Joined: 5 months ago
Posts: 1
03/06/2019 12:25 pm  

Hi could you please mention what went wrong? thanks. I'm having the same problem where the accuracy is 179% (which is wild imo)


ReplyQuote
hunny9891
(@hunny9891)
Active Member
Joined: 8 months ago
Posts: 5
04/06/2019 12:39 am  

Hello Devanshi,

In my case I was printing test loss instead of test accuracy.

 

test_loss, test_accuracy = trained_model.evaluate(X_test, y_test)

 

If you see above code snippet I was printing test_loss  from this in accuracy print statement.


ReplyQuote
Mo Rebaie
(@mo-rebaie)
Estimable Member
Joined: 7 months ago
Posts: 103
19/07/2019 8:28 am  

Hello, a cool question with its cool answer 🙂

I have faced also a lot of silly problems while coding, it's a common funny issue!

Good luck!

M.R


ReplyQuote
Share:

We use cookies to collect information about our website and how users interact with it. We’ll use this information solely to improve the site. You are agreeing to consent to our use of cookies if you click ‘OK’. All information we collect using cookies will be subject to and protected by our Privacy Policy, which you can view here.

OK
  
Working

Please Login or Register