Pythonix Huang

> First, your video frame should be preprocessed to square, That's to say, the height and width should be the same. > Second, extract smpl infomation of your frames. You...

> ot a branch `alex/4k_nerf` that is open right now that adds in some of the 4k_nerf techniques with the Nerfacto method. Thoug Thanks, I will take a look.

> > Its a bit confusing, this is the structure for the command, `ns-train nerfacto {training args} nerfstudio-data {data args}` So for downscaling the image you should add `--downscale-factor` in...

> It's just a bit on the ugly side, do you have time to actually pass an argument in the constructor giving the device instead of the if/elses and if...

But you are right, use a device argument should be more reasonable, maybe for users with less VRAM and RAM to put their images, specify the device as disk might...

> I mean that we should pass an argument, arg_device to the constructor that is either torch.device or a string "cpu" or "cuda" which later can be used like this:...

> Thank you, we really appreciate the effort and your help! On Tue, Jul 11, 2023 at 7:26 PM Pythonix Huang ***@***.***> wrote: > […](#) > I mean that we...

Currently, on my A10 machine, the training speed will reduce from 13.02it/s to 11.87it/s when using CPU to hold data