no *.so files generated

running build running build_py creating build creating build/lib.linux-x86_64-3.5 creating build/lib.linux-x86_64-3.5/maskrcnn_benchmark copying maskrcnn_benchmark/init.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark creating build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota copying maskrcnn_benchmark-dota/init.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota creating build/lib.linux-x86_64-3.5/rotation copying rotation/rotate_cpu_nms.py -> build/lib.linux-x86_64-3.5/rotation copying rotation/init.py -> build/lib.linux-x86_64-3.5/rotation creating build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers copying maskrcnn_benchmark/layers/misc.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers copying maskrcnn_benchmark/layers/roi_align.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers copying maskrcnn_benchmark/layers/nms.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers copying maskrcnn_benchmark/layers/init.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers copying maskrcnn_benchmark/layers/roi_pool.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers copying maskrcnn_benchmark/layers/sigmoid_focal_loss.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers copying maskrcnn_benchmark/layers/CE_focal_loss.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers copying maskrcnn_benchmark/layers/batch_norm.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers copying maskrcnn_benchmark/layers/scale.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers copying maskrcnn_benchmark/layers/_utils.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers copying maskrcnn_benchmark/layers/iou_loss.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers copying maskrcnn_benchmark/layers/smooth_l1_loss.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark/layers ...

copying maskrcnn_benchmark-dota/data/datasets/DOTA_Rotate_ori.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets copying maskrcnn_benchmark-dota/data/datasets/init.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets copying maskrcnn_benchmark-dota/data/datasets/list_dataset.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets copying maskrcnn_benchmark-dota/data/datasets/voc.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets copying maskrcnn_benchmark-dota/data/datasets/DOTA_Rotate.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets creating build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/transforms copying maskrcnn_benchmark-dota/data/transforms/build.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/transforms copying maskrcnn_benchmark-dota/data/transforms/transforms.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/transforms copying maskrcnn_benchmark-dota/data/transforms/init.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/transforms creating build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/samplers copying maskrcnn_benchmark-dota/data/samplers/init.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/samplers copying maskrcnn_benchmark-dota/data/samplers/grouped_batch_sampler.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/samplers copying maskrcnn_benchmark-dota/data/samplers/distributed.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/samplers copying maskrcnn_benchmark-dota/data/samplers/iteration_based_batch_sampler.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/samplers creating build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets/evaluation copying maskrcnn_benchmark-dota/data/datasets/evaluation/init.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets/evaluation creating build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets/evaluation/coco copying maskrcnn_benchmark-dota/data/datasets/evaluation/coco/init.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets/evaluation/coco copying maskrcnn_benchmark-dota/data/datasets/evaluation/coco/coco_eval.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets/evaluation/coco creating build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets/evaluation/voc copying maskrcnn_benchmark-dota/data/datasets/evaluation/voc/init.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets/evaluation/voc copying maskrcnn_benchmark-dota/data/datasets/evaluation/voc/voc_eval.py -> build/lib.linux-x86_64-3.5/maskrcnn_benchmark-dota/data/datasets/evaluation/voc running build_ext building 'maskrcnn_benchmark._C' extension creating build/temp.linux-x86_64-3.5 creating build/temp.linux-x86_64-3.5/root creating build/temp.linux-x86_64-3.5/root/autodl-tmp creating build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh creating build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master creating build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark creating build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc creating build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu creating build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda gcc -pthread -B /root/miniconda3/envs/axis/compiler_compat -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/TH -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/THC -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/vision.cpp -o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/vision.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ gcc -pthread -B /root/miniconda3/envs/axis/compiler_compat -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/TH -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/THC -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.cpp -o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/ATen.h:9:0, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/all.h:4, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/extension.h:4, from /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/vision.h:3, from /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.cpp:2: /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.cpp: In lambda function: /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/Dispatch.h:71:52: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)’ is deprecated [-Wdeprecated-declarations] at::ScalarType _st = ::detail::scalar_type(TYPE); \ ^ /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.cpp:242:3: note: in expansion of macro ‘AT_DISPATCH_FLOATING_TYPES’ AT_DISPATCH_FLOATING_TYPES(input.type(), "ROIAlign_forward", [&] { ^~~~~~ /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/Dispatch.h:47:23: note: declared here inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties &t) { ^~~ gcc -pthread -B /root/miniconda3/envs/axis/compiler_compat -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/TH -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/THC -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/nms_cpu.cpp -o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/nms_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/ATen.h:9:0, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/all.h:4, from /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/extension.h:4, from /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/vision.h:3, from /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/nms_cpu.cpp:2: /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/nms_cpu.cpp: In lambda function: /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/Dispatch.h:71:52: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)’ is deprecated [-Wdeprecated-declarations] at::ScalarType _st = ::detail::scalar_type(TYPE); \ ^ /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/nms_cpu.cpp:71:3: note: in expansion of macro ‘AT_DISPATCH_FLOATING_TYPES’ AT_DISPATCH_FLOATING_TYPES(dets.type(), "nms", [&] { ^~~~~~ /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/Dispatch.h:47:23: note: declared here inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties &t) { ^~~ /usr/local/cuda/bin/nvcc -DWITH_CUDA -I/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/TH -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/THC -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/nms.cu -o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/nms.o -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS --compiler-options '-fPIC' -DCUDA_HAS_FP16=1 -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 /usr/local/cuda/bin/nvcc -DWITH_CUDA -I/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/TH -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/THC -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/SigmoidFocalLoss_cuda.cu -o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/SigmoidFocalLoss_cuda.o -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS --compiler-options '-fPIC' -DCUDA_HAS_FP16=1 -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/cuda/NumericLimits.cuh(83): warning: calling a constexpr host function("from_bits") from a host device function("lowest") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/cuda/NumericLimits.cuh(84): warning: calling a constexpr host function("from_bits") from a host device function("max") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/cuda/NumericLimits.cuh(85): warning: calling a constexpr host function("from_bits") from a host device function("lower_bound") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/cuda/NumericLimits.cuh(86): warning: calling a constexpr host function("from_bits") from a host device function("upper_bound") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/SigmoidFocalLoss_cuda.cu: In lambda function: /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/SigmoidFocalLoss_cuda.cu:128:122: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)’ is deprecated [-Wdeprecated-declarations] AT_DISPATCH_FLOATING_TYPES(logits.type(), "SigmoidFocalLoss_forward", [&] { ^ /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/Dispatch.h:47:1: note: declared here inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties &t) { ^~~ /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/SigmoidFocalLoss_cuda.cu: In lambda function: /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/SigmoidFocalLoss_cuda.cu:172:122: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)’ is deprecated [-Wdeprecated-declarations] AT_DISPATCH_FLOATING_TYPES(logits.type(), "SigmoidFocalLoss_backward", [&] { ^ /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/Dispatch.h:47:1: note: declared here inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties &t) { ^~~ /usr/local/cuda/bin/nvcc -DWITH_CUDA -I/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/TH -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/THC -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIPool_cuda.cu -o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIPool_cuda.o -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS --compiler-options '-fPIC' -DCUDA_HAS_FP16=1 -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/cuda/NumericLimits.cuh(83): warning: calling a constexpr host function("from_bits") from a host device function("lowest") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIPool_cuda.cu: In lambda function: /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIPool_cuda.cu:137:120: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&’ is deprecated [-Wdeprecated-declarations] AT_DISPATCH_FLOATING_TYPES(input.type(), "ROIPool_forward", [&] { ^ /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/Dispatch.h:47:1: note: declared here inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties &t) { ^~~ /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIPool_cuda.cu: In lambda function: /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIPool_cuda.cu:185:118: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&’ is deprecated [-Wdeprecated-declarations] AT_DISPATCH_FLOATING_TYPES(grad.type(), "ROIPool_backward", [&] { ^ /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/Dispatch.h:47:1: note: declared here inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties &t) { ^~~ /usr/local/cuda/bin/nvcc -DWITH_CUDA -I/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/torch/csrc/api/include -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/TH -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/THC -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIAlign_cuda.cu -o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIAlign_cuda.o -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS --compiler-options '-fPIC' -DCUDA_HAS_FP16=1 -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/cuda/NumericLimits.cuh(83): warning: calling a constexpr host function("from_bits") from a host device function("lowest") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIAlign_cuda.cu: In lambda function: /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIAlign_cuda.cu:283:120: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)’ is deprecated [-Wdeprecated-declarations] AT_DISPATCH_FLOATING_TYPES(input.type(), "ROIAlign_forward", [&] { ^ /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/Dispatch.h:47:1: note: declared here inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties &t) { ^~~ /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIAlign_cuda.cu: In lambda function: /root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIAlign_cuda.cu:329:118: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)’ is deprecated [-Wdeprecated-declarations] AT_DISPATCH_FLOATING_TYPES(grad.type(), "ROIAlign_backward", [&] { ^ /root/miniconda3/envs/axis/lib/python3.5/site-packages/torch/include/ATen/Dispatch.h:47:1: note: declared here inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties &t) { ^~~ g++ -pthread -shared -L/root/miniconda3/envs/axis/lib -B /root/miniconda3/envs/axis/compiler_compat -Wl,-rpath=/root/miniconda3/envs/axis/lib,--no-as-needed build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/vision.o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cpu/nms_cpu.o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/nms.o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/SigmoidFocalLoss_cuda.o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIPool_cuda.o build/temp.linux-x86_64-3.5/root/autodl-tmp/rxh/AxisLearning-master/maskrcnn_benchmark/csrc/cuda/ROIAlign_cuda.o -L/usr/local/cuda/lib64 -lcudart -o build/lib.linux-x86_64-3.5/maskrcnn_benchmark/_C.cpython-35m-x86_64-linux-gnu.so running develop running egg_info creating maskrcnn_benchmark.egg-info writing dependency_links to maskrcnn_benchmark.egg-info/dependency_links.txt writing maskrcnn_benchmark.egg-info/PKG-INFO writing top-level names to maskrcnn_benchmark.egg-info/top_level.txt writing manifest file 'maskrcnn_benchmark.egg-info/SOURCES.txt' reading manifest file 'maskrcnn_benchmark.egg-info/SOURCES.txt' writing manifest file 'maskrcnn_benchmark.egg-info/SOURCES.txt' running build_ext copying build/lib.linux-x86_64-3.5/maskrcnn_benchmark/_C.cpython-35m-x86_64-linux-gnu.so -> maskrcnn_benchmark Creating /root/miniconda3/envs/axis/lib/python3.5/site-packages/maskrcnn-benchmark.egg-link (link to .) maskrcnn-benchmark 0.1 is already the active version in easy-install.pth

Installed /root/autodl-tmp/rxh/AxisLearning-master Processing dependencies for maskrcnn-benchmark==0.1 Finished processing dependencies for maskrcnn-benchmark==0.1

(axis) root@container-88b111a1ac-1e7ebbf3:~/autodl-tmp/rxh/AxisLearning-master# python rotation_setup.py build running build running build_ext skipping 'rotation/rotate_cython_nms.c' Cython extension (up-to-date) skipping 'rotation/iou_cpu.c' Cython extension (up-to-date) skipping 'rotation/rotate_circle_nms.c' Cython extension (up-to-date) skipping 'rotation/rotate_gpu_nms.cpp' Cython extension (up-to-date) skipping 'rotation/rbbox_overlaps.cpp' Cython extension (up-to-date) skipping 'rotation/rotate_polygon_nms.cpp' Cython extension (up-to-date) skipping 'rotation/reorg_cls_centerness.cpp' Cython extension (up-to-date) building 'rotation.rotate_cython_nms' extension creating build/temp.linux-x86_64-3.5/rotation gcc -pthread -B /root/miniconda3/envs/axis/compiler_compat -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include -I/root/miniconda3/envs/axis/include/python3.5m -c rotation/rotate_cython_nms.c -o build/temp.linux-x86_64-3.5/rotation/rotate_cython_nms.o -Wno-cpp -Wno-unused-function gcc -pthread -shared -L/root/miniconda3/envs/axis/lib -B /root/miniconda3/envs/axis/compiler_compat -Wl,-rpath=/root/miniconda3/envs/axis/lib,--no-as-needed build/temp.linux-x86_64-3.5/rotation/rotate_cython_nms.o -o build/lib.linux-x86_64-3.5/rotation/rotate_cython_nms.cpython-35m-x86_64-linux-gnu.so building 'rotation.iou_cpu' extension gcc -pthread -B /root/miniconda3/envs/axis/compiler_compat -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include -I/root/miniconda3/envs/axis/include/python3.5m -c rotation/iou_cpu.c -o build/temp.linux-x86_64-3.5/rotation/iou_cpu.o -Wno-cpp -Wno-unused-function gcc -pthread -shared -L/root/miniconda3/envs/axis/lib -B /root/miniconda3/envs/axis/compiler_compat -Wl,-rpath=/root/miniconda3/envs/axis/lib,--no-as-needed build/temp.linux-x86_64-3.5/rotation/iou_cpu.o -o build/lib.linux-x86_64-3.5/rotation/iou_cpu.cpython-35m-x86_64-linux-gnu.so building 'rotation.rotate_circle_nms' extension gcc -pthread -B /root/miniconda3/envs/axis/compiler_compat -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include -I/root/miniconda3/envs/axis/include/python3.5m -c rotation/rotate_circle_nms.c -o build/temp.linux-x86_64-3.5/rotation/rotate_circle_nms.o -Wno-cpp -Wno-unused-function rotation/rotate_circle_nms.c: In function ‘pyx_pf_8rotation_17rotate_circle_nms_2rotate_cpu_nms.isra.6’: rotation/rotate_circle_nms.c:2647:54: warning: ‘pyx_v_s’ may be used uninitialized in this function [-Wmaybe-uninitialized] pyx_t_38 = PyFloat_FromDouble((pyx_v_s + pyx_v_d)); if (unlikely(!pyx_t_38)) {pyx_filename = pyx_f[0]; pyx_lineno = 76; __pyx_clineno = LINE; goto pyx_L1_error;}


rotation/rotate_circle_nms.c:2739:24: warning: ‘__pyx_v_x2’ may be used uninitialized in this function [-Wmaybe-uninitialized]
           __pyx_t_36 = PyFloat_FromDouble(__pyx_v_x2); if (unlikely(!__pyx_t_36)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 78; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
                        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
rotation/rotate_circle_nms.c:2706:24: warning: ‘__pyx_v_x1’ may be used uninitialized in this function [-Wmaybe-uninitialized]
           __pyx_t_10 = PyFloat_FromDouble(__pyx_v_x1); if (unlikely(!__pyx_t_10)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 78; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
                        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
gcc -pthread -shared -L/root/miniconda3/envs/axis/lib -B /root/miniconda3/envs/axis/compiler_compat -Wl,-rpath=/root/miniconda3/envs/axis/lib,--no-as-needed build/temp.linux-x86_64-3.5/rotation/rotate_circle_nms.o -o build/lib.linux-x86_64-3.5/rotation/rotate_circle_nms.cpython-35m-x86_64-linux-gnu.so
building 'rotation.rotate_gpu_nms' extension
/usr/local/cuda/bin/nvcc -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c rotation/rotate_nms_kernel.cu -o build/temp.linux-x86_64-3.5/rotation/rotate_nms_kernel.o -arch=sm_35 --ptxas-options=-v -c --compiler-options '-fPIC'
nvcc warning : The 'compute_35', 'compute_37', 'compute_50', 'sm_35', 'sm_37' and 'sm_50' architectures are deprecated, and may be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
ptxas info    : 0 bytes gmem
ptxas info    : Compiling entry function '_Z17rotate_nms_kernelifPKfPy' for 'sm_35'
ptxas info    : Function properties for _Z17rotate_nms_kernelifPKfPy
    0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
ptxas info    : Used 35 registers, 1536 bytes smem, 344 bytes cmem[0], 64 bytes cmem[2]
gcc -pthread -B /root/miniconda3/envs/axis/compiler_compat -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c rotation/rotate_gpu_nms.cpp -o build/temp.linux-x86_64-3.5/rotation/rotate_gpu_nms.o -Wno-unused-function
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from /root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/ndarraytypes.h:1832:0,
                 from /root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/ndarrayobject.h:12,
                 from /root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/arrayobject.h:4,
                 from rotation/rotate_gpu_nms.cpp:251:
/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/npy_1_7_deprecated_api.h:17:2: warning: #warning "Using deprecated NumPy API, disable it with " "#define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION" [-Wcpp]
 #warning "Using deprecated NumPy API, disable it with " \
  ^~~~~~~
g++ -pthread -shared -L/root/miniconda3/envs/axis/lib -B /root/miniconda3/envs/axis/compiler_compat -Wl,-rpath=/root/miniconda3/envs/axis/lib,--no-as-needed build/temp.linux-x86_64-3.5/rotation/rotate_nms_kernel.o build/temp.linux-x86_64-3.5/rotation/rotate_gpu_nms.o -L/usr/local/cuda/lib64 -Wl,-R/usr/local/cuda/lib64 -lcudart -o build/lib.linux-x86_64-3.5/rotation/rotate_gpu_nms.cpython-35m-x86_64-linux-gnu.so
building 'rotation.rbbox_overlaps' extension
/usr/local/cuda/bin/nvcc -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c rotation/rbbox_overlaps_kernel.cu -o build/temp.linux-x86_64-3.5/rotation/rbbox_overlaps_kernel.o -arch=sm_35 --ptxas-options=-v -c --compiler-options '-fPIC'
nvcc warning : The 'compute_35', 'compute_37', 'compute_50', 'sm_35', 'sm_37' and 'sm_50' architectures are deprecated, and may be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
ptxas info    : 24 bytes gmem, 48 bytes cmem[3]
ptxas info    : Compiling entry function '_Z15overlaps_kerneliiPKfS0_Pf' for 'sm_35'
ptxas info    : Function properties for _Z15overlaps_kerneliiPKfS0_Pf
    0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
ptxas info    : Used 58 registers, 512 bytes smem, 352 bytes cmem[0], 292 bytes cmem[2]
ptxas info    : Function properties for __internal_accurate_pow
    0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
ptxas info    : Compiling entry function '_Z10IOU_kerneliPfPKfS_' for 'sm_35'
ptxas info    : Function properties for _Z10IOU_kerneliPfPKfS_
    128 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
ptxas info    : Used 90 registers, 352 bytes cmem[0], 84 bytes cmem[2]
gcc -pthread -B /root/miniconda3/envs/axis/compiler_compat -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c rotation/rbbox_overlaps.cpp -o build/temp.linux-x86_64-3.5/rotation/rbbox_overlaps.o -Wno-unused-function
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from /root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/ndarraytypes.h:1832:0,
                 from /root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/ndarrayobject.h:12,
                 from /root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/arrayobject.h:4,
                 from rotation/rbbox_overlaps.cpp:612:
/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/npy_1_7_deprecated_api.h:17:2: warning: #warning "Using deprecated NumPy API, disable it with " "#define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION" [-Wcpp]
 #warning "Using deprecated NumPy API, disable it with " \
  ^~~~~~~
g++ -pthread -shared -L/root/miniconda3/envs/axis/lib -B /root/miniconda3/envs/axis/compiler_compat -Wl,-rpath=/root/miniconda3/envs/axis/lib,--no-as-needed build/temp.linux-x86_64-3.5/rotation/rbbox_overlaps_kernel.o build/temp.linux-x86_64-3.5/rotation/rbbox_overlaps.o -L/usr/local/cuda/lib64 -Wl,-R/usr/local/cuda/lib64 -lcudart -o build/lib.linux-x86_64-3.5/rotation/rbbox_overlaps.cpython-35m-x86_64-linux-gnu.so
building 'rotation.rotate_polygon_nms' extension
/usr/local/cuda/bin/nvcc -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c rotation/rotate_polygon_nms_kernel.cu -o build/temp.linux-x86_64-3.5/rotation/rotate_polygon_nms_kernel.o -arch=sm_35 --ptxas-options=-v -c --compiler-options '-fPIC'
nvcc warning : The 'compute_35', 'compute_37', 'compute_50', 'sm_35', 'sm_37' and 'sm_50' architectures are deprecated, and may be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
ptxas info    : 144 bytes gmem
ptxas info    : Compiling entry function '_Z17rotate_nms_kernelifPKfPy' for 'sm_35'
ptxas info    : Function properties for _Z17rotate_nms_kernelifPKfPy
    176 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
ptxas info    : Used 78 registers, 1536 bytes smem, 344 bytes cmem[0], 200 bytes cmem[2]
ptxas info    : Function properties for __internal_trig_reduction_slowpathd
    0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
gcc -pthread -B /root/miniconda3/envs/axis/compiler_compat -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c rotation/rotate_polygon_nms.cpp -o build/temp.linux-x86_64-3.5/rotation/rotate_polygon_nms.o -Wno-unused-function
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from /root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/ndarraytypes.h:1832:0,
                 from /root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/ndarrayobject.h:12,
                 from /root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/arrayobject.h:4,
                 from rotation/rotate_polygon_nms.cpp:251:
/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/npy_1_7_deprecated_api.h:17:2: warning: #warning "Using deprecated NumPy API, disable it with " "#define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION" [-Wcpp]
 #warning "Using deprecated NumPy API, disable it with " \
  ^~~~~~~
g++ -pthread -shared -L/root/miniconda3/envs/axis/lib -B /root/miniconda3/envs/axis/compiler_compat -Wl,-rpath=/root/miniconda3/envs/axis/lib,--no-as-needed build/temp.linux-x86_64-3.5/rotation/rotate_polygon_nms_kernel.o build/temp.linux-x86_64-3.5/rotation/rotate_polygon_nms.o -L/usr/local/cuda/lib64 -Wl,-R/usr/local/cuda/lib64 -lcudart -o build/lib.linux-x86_64-3.5/rotation/rotate_polygon_nms.cpython-35m-x86_64-linux-gnu.so
building 'rotation.reorg_cls_centerness' extension
/usr/local/cuda/bin/nvcc -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c rotation/reorg_cls_centerness_kernel.cu -o build/temp.linux-x86_64-3.5/rotation/reorg_cls_centerness_kernel.o -arch=sm_35 --ptxas-options=-v -c --compiler-options '-fPIC'
nvcc warning : The 'compute_35', 'compute_37', 'compute_50', 'sm_35', 'sm_37' and 'sm_50' architectures are deprecated, and may be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
ptxas info    : 0 bytes gmem
ptxas info    : Compiling entry function '_Z12reorg_kerneliiiiPKfPf' for 'sm_35'
ptxas info    : Function properties for _Z12reorg_kerneliiiiPKfPf
    0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
ptxas info    : Used 44 registers, 352 bytes cmem[0], 260 bytes cmem[2]
ptxas info    : Function properties for __internal_accurate_pow
    0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
gcc -pthread -B /root/miniconda3/envs/axis/compiler_compat -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include -I/usr/local/cuda/include -I/root/miniconda3/envs/axis/include/python3.5m -c rotation/reorg_cls_centerness.cpp -o build/temp.linux-x86_64-3.5/rotation/reorg_cls_centerness.o -Wno-unused-function
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from /root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/ndarraytypes.h:1832:0,
                 from /root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/ndarrayobject.h:12,
                 from /root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/arrayobject.h:4,
                 from rotation/reorg_cls_centerness.cpp:612:
/root/miniconda3/envs/axis/lib/python3.5/site-packages/numpy/core/include/numpy/npy_1_7_deprecated_api.h:17:2: warning: #warning "Using deprecated NumPy API, disable it with " "#define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION" [-Wcpp]
 #warning "Using deprecated NumPy API, disable it with " \
  ^~~~~~~
g++ -pthread -shared -L/root/miniconda3/envs/axis/lib -B /root/miniconda3/envs/axis/compiler_compat -Wl,-rpath=/root/miniconda3/envs/axis/lib,--no-as-needed build/temp.linux-x86_64-3.5/rotation/reorg_cls_centerness_kernel.o build/temp.linux-x86_64-3.5/rotation/reorg_cls_centerness.o -L/usr/local/cuda/lib64 -Wl,-R/usr/local/cuda/lib64 -lcudart -o build/lib.linux-x86_64-3.5/rotation/reorg_cls_centerness.cpython-35m-x86_64-linux-gnu.so

mjq11302010044 / RRPN_pytorch

no *.so files generated #65