yt2639

TEM loss is not really decreasing

3

Hey @JJBOY, thanks for your implementation and I found it extremely useful. I now have a problem during training, the PEM loss is decreasing normally, but TEM loss is not...

Hi friends, I have issues using deepspeed on different servers with different cuda version. I installed deepspeed via `pip install deepspeed` and the version is 0.5.8. So basically the servers...

**Describe the bug** When using deepspeed, during `model.backward(loss)` step, it reports **"SystemError: returned NULL without setting an error"** It was working somehow before, but today it is just not working....

Labels: background as 1, foreground as 0?

1

Hi guys, thanks for your work and sharing the code. I have a question about the labels input to calculate the loss. So I understand it as if we have...

Exporting camera parameters and poses as well as 3D points to COLMAP-style files

2

Hii guys, has anyone figured out how to export the `scene` to NeRFStudio transforms.json or COLMAP-style (Cameras.txt, images.txt, points3D.txt) yet? I have tried the solution mentioned in this issue #8....

Any plan to integrate MCMC strategy into NeRFStudio?

1

Hii, is there any plan to integrate MCMC strategy into NeRFStudio's splatfacto? I've tried myself but it seems not working. I essentially add `MCMCStrategy.step_post_backward` [link](https://github.com/nerfstudio-project/gsplat/blob/8f8e397f80d46bf0ebc9dc77e4c7721d7c76b634/gsplat/strategy/mcmc.py#L103) in `trainer.py` between `self.grad_scaler.scale(loss).backward()` [link](https://github.com/nerfstudio-project/nerfstudio/blob/b70772795080730ec36b0841641993b34807aada/nerfstudio/engine/trainer.py#L499)...

Hii, I have a question about the comments in **sparse_scene_optimizer.py**. As this part seems not to be in the paper (please correct me if I'm wrong ^^) I want to...