Should I keep training my model for more Epochs to get a better R Squared value?

user200509 0
Viewed 21

This is my model, using Adam optimiser and lr of 0.0001.

enter image description here

This is the Training and the Validation loss plot below: enter image description here

The value of mse=0.049 and r2=70.3%. My problem is the more images i include into my training model, the worse it gets but mse and r2 increases so this is very counterintuitive. This is a regression model using Nvidia's Model. I input the images and need a steering angle output. Am i actually making things more difficuilt than it needs to be by increasing data and epochs? I am training with only 1600 Images for 30 epochs. Will appreciate any suggestion from the experts as im relatively new to NNs.Will provide more details if needed thanks :)

linear-regression conv-neural-network keras validation python
1 Answers

Observing the graph that shows the results of the training and validation loss we can see that after 12 epochs (more or less), the validation value does not improve too much as the epochs go up. I think that the most logical thing would be to look for the value from which the validation/training loss does not have much improvement left.

Also remember that it is important not to overfit the model to the training data, as this can lead to errors when validating. I hope my answer will help you. Good luck!

a-Alarcon0
Related