run train.py with test_local.gin successfully but have a problom with hypernerf_interp_ap/ds_2d.gin

[buptseelihang]

the programe stuck when initializing model ,I have wait for 5 hours but it doesn't work .And I cant use ctrl+c to end it ,must ue kill XXX to stop it.

[keunhong]

You're likely running out of GPU or system memory. If it hangs for 5 hours maybe you ran out of system memory and it's swapping?

[buptseelihang]

You're likely running out of GPU or system memory. If it hangs for 5 hours maybe you ran out of system memory and it's swapping?

Thank you for your ansower~! I set a small batch_size and solve this problem~

I have more questions : 1.I have train model and render frames successfully,but i think the numbers of rendered frames is not enough to render a smooth video(like your example viedos 60fps)。Which parameters should i change to interpolation more frames? 2.the datasets you provide have prefix（interp，vrig，misc），for example,vrig_3dprinter,it means it must use hypernerf_vrig_ds(ap)_2d.gin to train? What's the differences between interp,vrig and misc? 3.To get the best performance ,i should set TrainConfig.use_weight_norm =True TrainConfig.use_elastic_loss = True TrainConfig.use_background_loss = True

right? Are there any other parameters that need to be adjusted？

Thank you for the brilliant work!