I'm using 3 layer CNN with 8, 16, and 32 filters, each of size 5 X 5. I'm getting an training accuracy of 99.97%. Testing accuracy of 41.11%.

Total classes: 605

Train Set: Each class has 7 samples

Test Set: Each class has 1 sample.

Is the ratio of train and test set causing the huge difference in the train and test accuracy?

  • $\begingroup$ Can you share the some more information regarding your model? $\endgroup$ – user234584 Apr 7 at 14:16
  • 1
    $\begingroup$ @ShubhamPanchal Conv->Relu->MaxPool->Conv->ReLU->MaxPool->Conv->ReLU->MaxPool $\endgroup$ – somerandomguy Apr 7 at 16:24
  • $\begingroup$ You can try using LeakyReLU layers and Dropout layers. $\endgroup$ – user234584 Apr 8 at 1:37

Your Answer

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

Browse other questions tagged or ask your own question.