nerfacc icon indicating copy to clipboard operation
nerfacc copied to clipboard

Published 20 hours ago • verified publisher icon nerfstudio-project

Test Error

Open aiyb1314 opened this issue 1 year ago • 3 comments

RuntimeError: CUDA error: invalid configuration argument CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

aiyb1314 avatar Jun 12 '23 08:06 aiyb1314

Hi it is hard to tell what could be wrong from this among of information. One possible trigger of this might be zero shape tensor being sent to tiny-cuda-nn.

liruilong940607 avatar Jun 12 '23 20:06 liruilong940607

I hit this as well when running train_ngp_nerf_occ.py. It always occurs after training so my suspicion is that render_image_with_occgrid_test is somehow the offender. I tested this using the nerf synthetic datasets

sweeneychris avatar Aug 07 '23 23:08 sweeneychris

During the model testing phase, the following error occurs ： File "/home/xuj/anaconda3/envs/nerfacc/lib/python3.10/site-packages/tinycudann-1.7-py3.10-linux-x86_64.egg/tinycudann/modules.py", line 89, in forward native_ctx, output = native_tcnn_module.fwd(input, params) RuntimeError: /home/xuj/tiny-cuda-nn/include/tiny-cuda-nn/cutlass_matmul.h:332 status failed with error Error Internal After debugging, it is found that it is caused by the number of sampling points in the test phase is 0. How to avoid this phenomenon?

aiyb1314 avatar Nov 06 '23 06:11 aiyb1314