I am working on Digit Recogniser and after training the fully connected model with 3 CNN layers and 2 dense network layers with rely and softmax activation functions, getting below curve.Screen%20Shot%202019-01-17%20at%209.12.56%20PM.png
What i understood is model has high variance problem because after some time gap between training loss and validation loss is increasing. Is my understanding correct?
It looks like your model becomes overtrained right around "3". That is where the evaluation curves diverge.