socialways icon indicating copy to clipboard operation
socialways copied to clipboard

Published 20 hours ago • verified publisher icon crowdbotp

Training with custom dataset yields bad results with info loss only

Open selflein opened this issue 4 years ago • 0 comments

Hi, thank you for publishing code for your paper. Currently, I am trying to train with a custom dataset (dataset.zip). It is a intersection with 3 modes. There are 8 input points and 12 predicted points.

Samples from dataset look like this: image When I try to train with the InfoGAN objective only, I receive really bad results.

result_socialways

I switched off social features and hyperparameters are the default ones. Do you have an explanation for the results? Or do you think there is a bug somewhere?

selflein avatar Mar 05 '20 22:03 selflein