0
$\begingroup$

I am working on image classification project. I have trained model on car dataset. So it gives good accuracy but when I predict BMW car with my model it gives below results.

BMW :- 98% Audi :- 91%

Why Audi labels shows 91% it should be low. How to solve this issue? I am using resnet 50 pre trained model.

$\endgroup$
2
  • $\begingroup$ it can happen, more than one label may be plausible, simply choose the largest predition $\endgroup$
    – Nikos M.
    Feb 2 at 19:06
  • $\begingroup$ I found a solution that we should use the softmax activation function. previously I used the sigmoid activation function. $\endgroup$ Feb 3 at 3:44
0
$\begingroup$

I found a solution that we should use the softmax activation function in the last layer. previously I used the sigmoid activation function

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.