Closed BooPatienze closed 3 years ago
I'm not sure. Maybe you can post your question here: https://github.com/facebookresearch/maskrcnn-benchmark/issues
I'm not sure. Maybe you can post your question here: https://github.com/facebookresearch/maskrcnn-benchmark/issues
谢谢~在您发的链接里找到了合适我的解决方法:https://blog.csdn.net/mm1327/article/details/106878984#commentBox
❓ Questions and Help
I follow the instruction to do:
but this problem is occurred when I run
python setup.py install --cuda_ext --cpp_ext
.Detail outputs:
...... csrc/mlp.cpp:147:46: error: expected primary-expression before ‘>’ token grad_o.contiguous().data_ptr<scalar_t>(), ^ /home/lpz/workspace/SceneGraphParse/sgg_benchmark/lib/python3.6/site-packages/torch/include/ATen/Dispatch.h:12:12: note: in definition of macro ‘AT_PRIVATE_CASE_TYPE’ return __VA_ARGS__(); \ ^~~~~~~~~~~ csrc/mlp.cpp:123:3: note: in expansion of macro ‘AT_DISPATCH_FLOATING_TYPES_AND_HALF’ AT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), "mlp_backward", [&] { ^ csrc/mlp.cpp:147:48: error: expected primary-expression before ‘)’ token grad_o.contiguous().data_ptr<scalar_t>(), ^ /home/lpz/workspace/SceneGraphParse/sgg_benchmark/lib/python3.6/site-packages/torch/include/ATen/Dispatch.h:12:12: note: in definition of macro ‘AT_PRIVATE_CASE_TYPE’ return __VA_ARGS__(); \ ^~~~~~~~~~~ csrc/mlp.cpp:123:3: note: in expansion of macro ‘AT_DISPATCH_FLOATING_TYPES_AND_HALF’ AT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), "mlp_backward", [&] { ^ csrc/mlp.cpp:148:43: error: expected primary-expression before ‘>’ token ......
here is my envirnment params: CUDA: 10.0.130 gcc version: 7.3.0 python: 3.6 torch: 1.2.0 torchvision: 0.4.0 System: Ubuntu 18.04
Finally, thanks for your help!