Is this loss valid?


(Priyanshu Sinha) #1

Hi,

I am training a model for end to end driving, i.e., predicting steering angles using images. I followed NVIDIA’s pilotnet architecture.

I know that loss should decrease, but in the end, it fluctuates between 0.01 - 0.05. I don’t know reason for this. I have searched SO, but was not able to find anything.

I have trained my network for 30 epochs, with batch size 100 and my training images are 675600.

Attached is screenshot from tensorboard.

Any help is highly appreciated.


#2

It looks like the model trains quickly. One reason for the fluctuation could be that different images are in each minibatch – why would you expect the error to be identical for each subset of images?


(Priyanshu Sinha) #3

Thanks @zearo

I haven’t expected it to be identical, but what my understanding was that it should not fluctuate. Thanks for clearing my doubt.