how many train step we need

ogroth / tf-gqn

Tensorflow implementation of Neural Scene Representation and Rendering

Apache License 2.0

188 stars 35 forks source link

how many train step we need #35

Open yuxiaoleipeng opened 5 years ago

yuxiaoleipeng commented 5 years ago

when i train the model, it can run, but when the step meet 200000 loss drop to 6900 and it never go down, i train it for 370000 step and it still 6900， do you meet this question before?

wenbingz commented 5 years ago

I met this problem, too. Does it relate to reproducibility？

ogroth commented 5 years ago

As I've explained here the loss seems to plateau because of the reconstruction term having reached the perfect means and the only thing which is optimized afterwards is the KL term which is, however, of a different order of magnitude. I admit that this loss setup is suboptimal and a bit confusing, so I'm happy about any suggestions.