change language feature encoder to dim=4 - CUDA error: an illegal memory access was encountered about langsplat HOT 6 OPEN

could you plz provide more details concerning rebuilding and reinstalling?I'm also making a try to a higher language feature dimension.

@Zhirui86
Hi, finally I figured out where the issue is:

if you met error like: RuntimeError: Function _RasterizeGaussiansBackward returned an invalid gradient at index 4 - got [2228907, 4] but expected shape compatible with [2228907, 3]

We need to edit following files:

1. LangSplat/submodules/langsplat-rasterization/cuda_rasterizer/config.h
   change NUM_CHANNELS_language_feature to the desired dim. Delete the local package and rebuild it.- remember to remove LangSplat/submodules/langsplat-rasterization/build folder if you have one, otherwise, it will use the cache.

2. LangSplat/scene/gaussian_model.py
   https://github.com/minghanqin/LangSplat/blob/main/scene/gaussian_model.py#L206C1-L206C87
   change the line:

                language_feature = torch.zeros((self._xyz.shape[0], 3), device="cuda")

We need to initialize the language_feature as the desired dim here, as for me it should be:

                language_feature = torch.zeros((self._xyz.shape[0], 4), device="cuda")

Cheers!

from langsplat.

Hello, did you solve the error in brackets by just creating a new environment?（RuntimeError: CUDA error: an illegal memory access was encountered
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.）

from langsplat.

The issue was solved by creating a new environment on WSL2 cuda118. I am going to explore more to reproduce this issue.

Currently I met a new issue when changing language features dimensions to 4:

RuntimeError: Function RasterizeGaussiansBackward returned an invalid qradient at index 4 - got[2228907，4] but expected shape compatible with [2228907，3]

Any help would be appreciated!

from langsplat.

could you plz provide more details concerning rebuilding and reinstalling?I'm also making a try to a higher language feature dimension.

from langsplat.

Have you ever tried a 512-dimension feature?I can build successfully in a lower level while it turns out as follows when setting dimension into 512:

from langsplat.

Have you ever tried a 512-dimension feature?I can build successfully in a lower level while it turns out as follows when setting dimension into 512:

Hi! I have the similar issue. Have you resolved this problem?

from langsplat.