0
$\begingroup$

I have a graph for a model on train accuracy and validation accuracy:

enter image description here

But I'm having trouble interpreting it. By the way i interpreted, I would say it is of poor performance. But I would like to know how this graph is interpreted in a more broad manner.

As in if we were to look at the point where the validation acc begins to bisect the train acc line, and went all the way down, what does this indicate? Would appreciate some help on this as I'm horrible at interpreting graphs.

$\endgroup$
1
$\begingroup$

https://en.wikipedia.org/wiki/Overfitting

This model is over-fitting. Better train accuracy (and validation accuracy that gets worse with successive iterations) indicates over-fit.

For CNN Next steps should be to reduce complexity of the model and adding droputs / batch normalization.

Few articles on this :

https://towardsdatascience.com/handling-overfitting-in-deep-learning-models-c760ee047c6e

https://machinelearningmastery.com/how-to-reduce-overfitting-with-dropout-regularization-in-keras/

$\endgroup$
0
$\begingroup$

I think there is a bug. Or too little data. The training accuracy is - in the best case - close to the validation accuracy. That the validation accuracy gets lower than the training accuracy is a strong indicator for a bug. Or too little data, which means the difference of 2% might not be relevant.

$\endgroup$

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.