Open erzhu222 opened 1 month ago
Warning: Found the number of input[216288] points exceeds the theoretical maximum number[200000], the default processing is to truncate.
Hi, could you provide me with the model and data so that I can reproduce this issue?
Hi, could you provide me with the model and data so that I can reproduce this issue?
thanks for your reply,the core dump problem was solved by setting max_voxels bigger,you can use more than 1000000 points to reproduce the warning, and I have a question about theoretical maximum number[200000], what does that mean? It seems in sparse conv lib
when I try to inference bevfusion model on more than 800000 points, an error occurred and core dumped:
CUDA Runtime error cudaStreamSynchronize(stream) # an illegal memory access was encountered, code = cudaErrorIllegalAddress [ 700 ] in file src/spconv/engine.cu:787 Aborted (core dumped)
could you please help me with the problem, thanks a lot!