search

craigleili / 3DLocalMultiViewDesc

End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds (CVPR2020)
MIT License
60 stars 8 forks source link

A question about “soft_rasterize_cuda” #3

Closed QWTforGithub closed 3 years ago

QWTforGithub commented 3 years ago

Hi,When I run this code, I have the following problem:

/home/ls/anaconda3/envs/qwt_py38/bin/python /home/qwt/code/3DLocalMultiViewDesc-master/scripts/main_mvdesc.py Using /home/qwt/.cache/torch_extensions as PyTorch extensions root... Detected CUDA files, patching ldflags Emitting ninja build file /home/qwt/.cache/torch_extensions/soft_rasterize_cuda/build.ninja... Building extension module soft_rasterize_cuda... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) [1/3] /usr/local/cuda/bin/nvcc --generate-dependencies-with-compile --dependency-output soft_rasterize_cuda_kernel.cuda.o.d -DTORCH_EXTENSION_NAME=soft_rasterize_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/TH -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/ls/anaconda3/envs/qwt_py38/include/python3.6m -D_GLIBCXX_USE_CXX11_ABI=0 -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_BFLOAT16_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS --expt-relaxed-constexpr -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 --compiler-options '-fPIC' -std=c++14 -c /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda_kernel.cu -o soft_rasterize_cuda_kernel.cuda.o FAILED: soft_rasterize_cuda_kernel.cuda.o /usr/local/cuda/bin/nvcc --generate-dependencies-with-compile --dependency-output soft_rasterize_cuda_kernel.cuda.o.d -DTORCH_EXTENSION_NAME=soft_rasterize_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/TH -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/ls/anaconda3/envs/qwt_py38/include/python3.6m -D_GLIBCXX_USE_CXX11_ABI=0 -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_BFLOAT16_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS --expt-relaxed-constexpr -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 --compiler-options '-fPIC' -std=c++14 -c /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda_kernel.cu -o soft_rasterize_cuda_kernel.cuda.o nvcc fatal : Unsupported gpu architecture 'compute_86' [2/3] c++ -MMD -MF soft_rasterize_cuda.o.d -DTORCH_EXTENSION_NAME=soft_rasterize_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/TH -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/ls/anaconda3/envs/qwt_py38/include/python3.6m -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -c /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp -o soft_rasterize_cuda.o FAILED: soft_rasterize_cuda.o c++ -MMD -MF soft_rasterize_cuda.o.d -DTORCH_EXTENSION_NAME=soft_rasterize_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/TH -isystem /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/ls/anaconda3/envs/qwt_py38/include/python3.6m -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -c /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp -o soft_rasterize_cuda.o /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp: In function ‘void soft_rasterize_forward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, float, float, float, float, float, float, int, bool, bool, bool, at::Tensor, at::Tensor, at::Tensor, at::Tensor)’: /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:79:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(mvps); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:23: error: ‘AT_CHECK’ was not declared in this scope

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:79:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(mvps); ^~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:23: note: suggested alternative: ‘DCHECK’

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:79:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(mvps); ^~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:80:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(vertices); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:81:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(radii); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:82:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(colors); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:83:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(locks); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:84:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(weights); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:85:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(color_map); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:86:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(depth_map); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:87:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(pseudo_depth_map); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp: In function ‘void soft_rasterize_backward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, float, float, float, float, float, float, int, bool, bool, at::Tensor)’: /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:132:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(mvps); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:23: error: ‘AT_CHECK’ was not declared in this scope

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:132:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(mvps); ^~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:23: note: suggested alternative: ‘DCHECK’

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:132:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(mvps); ^~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:133:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(vertices); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:134:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(colors); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:135:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(weights); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:136:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(grad_color_map); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:137:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(grad_depth_map); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:51:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]

define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDA tensor")

                                   ^

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:53:24: note: in expansion of macro ‘CHECK_CUDA’

define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)

                    ^~~~~~~~~~

/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:138:5: note: in expansion of macro ‘CHECK_INPUT’ CHECK_INPUT(grad_mvps); ^~~ In file included from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3:0, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/Context.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/ATen.h:9, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8, from /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/torch/extension.h:4, from /home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/soft_rasterize_cuda.cpp:1: /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here DeprecatedTypeProperties & type() const { ^~~~ ninja: build stopped: subcommand failed. Traceback (most recent call last): File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1673, in _run_ninja_build env=env) File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/subprocess.py", line 438, in run output=stdout, stderr=stderr) subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "/home/qwt/code/3DLocalMultiViewDesc-master/scripts/main_mvdesc.py", line 21, in from models.mvdesc import RenderModel, MV_MODELS File "/home/qwt/code/3DLocalMultiViewDesc-master/models/mvdesc.py", line 18, in from soft_renderer.transform import MultiViewRenderer File "/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/transform.py", line 17, in from soft_renderer.cuda.jit import soft_rasterize_cuda as src File "/home/qwt/code/3DLocalMultiViewDesc-master/soft_renderer/cuda/jit.py", line 8, in verbose=True) File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1091, in load keep_intermediates=keep_intermediates) File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1302, in _jit_compile is_standalone=is_standalone) File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1407, in _write_ninja_file_and_build_library error_prefix=f"Error building extension '{name}'") File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1683, in _run_ninja_build raise RuntimeError(message) from e RuntimeError: Error building extension 'soft_rasterize_cuda'

What should I do about it?Thank you.

craigleili commented 3 years ago

Hi, In the error log, there is a line saying nvcc fatal : Unsupported gpu architecture 'compute_86' So you may have a check at your GPU compute capability and the installed cuda version. The code was developed with an Nvidia 1080Ti GPU.