search

lishaobingdong / mip-splatting-jittor

the implementation with jittor for mip-splatting
0 stars 0 forks source link

使用colors_precomp进行渲染 #3

Open yuedumingz opened 13 hours ago

yuedumingz commented 13 hours ago

你好，我发现目前的代码貌似只支持使用shs进行渲染，当我尝试将shs设为None，而使用colors_precomp时，会有如下报错。 num_rendered, color, radii, geomBuffer, binningBuffer, imgBuffer = rasterize_points.RasterizeGaussiansCUDA(*args) File "/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater/rasterize_points.py", line 201, in RasterizeGaussiansCUDA binningBuffer = jt.array(jt.zeros([binning_size[0].item()],dtype='uint8')) RuntimeError: Wrong inputs arguments, Please refer to examples(help(jt.item)).

Types of your inputs are: self = Var, args = (),

The function declarations are: ItemData item()

Failed reason:[f 0919 08:19:18.149460 84 parallel_compiler.cc:331] Error happend during compilation: [Error] source file location:/root/.cache/jittor/jt1.3.9/g++11.4.0/py3.10.14/Linux-5.15.0-1x23/IntelRXeonRSilx06/a9f0/default/cu11.8.89_sm_86/jit/codeIN_SIZE_12in0_dim_1in0_type_float32in1_dim_2in1_type_float32in2_dim_2__in2___hash_9fc5af055bbf9621_op.cc Compile operator(5/6)failed:Op(2215:11:3:3:i15:o3:s0:g1,code->...)

Reason: [f 0919 08:19:17.765471 28:C5 log.cc:608] Check failed ret(256) == 0(0) Run cmd failed: "/usr/local/cuda/bin/nvcc" "/root/.cache/jittor/jt1.3.9/g++11.4.0/py3.10.14/Linux-5.15.0-1x23/IntelRXeonRSilx06/a9f0/default/cu11.8.89_sm_86/jit/codeIN_SIZE_12in0_dim_1in0_type_float32in1_dim_2in1_type_float32in2_dim_2in2_hash_9fc5af055bbf9621_op.cc" -std=c++14 -Xcompiler -fPIC -Xcompiler -march=native -Xcompiler -fdiagnostics-color=always -lstdc++ -ldl -shared -I"/root/miniconda3/envs/mip_splat/lib/python3.10/site-packages/jittor/src" -I/root/miniconda3/envs/mip_splat/include/python3.10 -I/root/miniconda3/envs/mip_splat/include/python3.10 -DHAS_CUDA -DIS_CUDA -I"/usr/local/cuda/include" -I"/root/miniconda3/envs/mip_splat/lib/python3.10/site-packages/jittor/extern/cuda/inc" -lcudart -L"/usr/local/cuda/lib64" -Xlinker -rpath="/usr/local/cuda/lib64" -I"/root/.cache/jittor/jt1.3.9/g++11.4.0/py3.10.14/Linux-5.15.0-1x23/IntelRXeonRSilx06/a9f0/default/cu11.8.89_sm_86" -L"/root/.cache/jittor/jt1.3.9/g++11.4.0/py3.10.14/Linux-5.15.0-1x23/IntelRXeonRSilx06/a9f0/default/cu11.8.89_sm_86" -Xlinker -rpath="/root/.cache/jittor/jt1.3.9/g++11.4.0/py3.10.14/Linux-5.15.0-1x23/IntelRXeonRSilx06/a9f0/default/cu11.8.89_sm_86" -L"/root/.cache/jittor/jt1.3.9/g++11.4.0/py3.10.14/Linux-5.15.0-1x23/IntelRXeonRSilx06/a9f0/default" -Xlinker -rpath="/root/.cache/jittor/jt1.3.9/g++11.4.0/py3.10.14/Linux-5.15.0-1x23/IntelRXeonRSilx06/a9f0/default" -l:"jit_utils_core.cpython-310-x86_64-linux-gnu".so -l:"jittor_core.cpython-310-x86_64-linux-gnu".so -x cu --cudart=shared -ccbin="/usr/bin/g++" --use_fast_math -w -I"/root/miniconda3/envs/mip_splat/lib/python3.10/site-packages/jittor/extern/cuda/inc" -arch=compute_86 -code=sm_86 -I"/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater/cuda_rasterizer" -I"/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater/third_party/glm" -l"CudaRasterizer" -L"/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater" -Xlinker -rpath="/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater" -I"/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater/cuda_rasterizer" -I"/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater/third_party/glm" -l"CudaRasterizer" -L"/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater" -Xlinker -rpath="/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater" -I"/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater/cuda_rasterizer" -I"/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater/third_party/glm" -l"CudaRasterizer" -L"/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater" -Xlinker -rpath="/root/mip-splatting-jittor/gaussian_renderer/diff_gaussian_rasterizater" -o "/root/.cache/jittor/jt1.3.9/g++11.4.0/py3.10.14/Linux-5.15.0-1x23/IntelRXeonRSilx06/a9f0/default/cu11.8.89_sm_86/jit/codeIN_SIZE_12in0_dim_1in0_type_float32in1_dim_2in1_type_float32in2_dim_2in2_hash_9fc5af055bbf9621_op.so"  这将会导致添加深度监督和发现监督变得困难，你能给出解决方案吗