Discrepancy between overfitting and pre-trained model

[Sentient07]

Hello,

I'm trying to overfit the network to a single shape and I find that the training results are significantly different from the pre-trained model. Attached below is the discrepancy I'm referring to. What could be the reason?

Edit: Left in the figure is the pretrained model of UNDC Point cloud (both bool and float). Right uses the ground truth vertex positions and the connectivity is what I overfit to the single shape and try to predict the result on the same. (done for a sanity check)

[czq142857]

It seems to be underfitting. Did you train enough iterations?

[Sentient07]

Hello,

Thanks for the quick reply. I too thought the same, but this one was trained for 1000 iterations. That is sufficient I suppose?

[czq142857]

1000 is not enough. Please train more iterations until you get an overfit.

[Sentient07]

Indeed, it took about 2k iterations. Closing as issue is solved. Thank you!