NN Getting Same Training and Testing Accuracies?

[TheCedarPrince]

@jeremiedb

Another tricke would be to substitute your current image dataset by the MNIST ones or equivalent. If the model learns over the MNIST but not when switching to you dataset, then perhaps the issue is on that side.

Oh this is interesting. Indeed when I switch over to MNIST, it does learn and train but then not over the other dataset. Hm. I wonder if there is an error with the data somewhere?

@jeremiedb

Also what is the range of the values found in the image dataset? Values should be roughly normally distributed. Otherwise, prepross them or add a BatchNorm operator as an initial layer.

Good thinking! However, I did try the BatchNorm function and no luck unfortunately. The values range between 0 to 1.

I’ll think on this some more but I think I shall also take a step back and see if there is something more fundamentally wrong with my data.

Thanks so much for the help!