'Cannot compile nms_cuda in mmdetection using colaboratory

/usr/local/lib/python3.6/dist-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
mmdet/ops/nms/src/nms_cuda.cpp:4:23: error: ‘AT_CHECK’ was not declared in this scope
 #define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
                       ^
mmdet/ops/nms/src/nms_cuda.cpp:4:23: note: in definition of macro ‘CHECK_CUDA’
 #define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
                       ^~~~~~~~
mmdet/ops/nms/src/nms_cuda.cpp:4:23: note: suggested alternative: ‘DCHECK’
 #define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
                       ^
mmdet/ops/nms/src/nms_cuda.cpp:4:23: note: in definition of macro ‘CHECK_CUDA’
 #define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
                       ^~~~~~~~
error: command 'x86_64-linux-gnu-gcc' failed with exit status 1

Now all the info I get:

  • sys.version 8.2
  • /usr/bin/gcc 7
  • gcc versio 7.5

Is it normal? What happened? Cuda error? gcc error? How to solve. I'm hurried to use it to run mmdetection program.

google-colaboratoryobject-detection


Solution 1:[1]

The solution is:

conda install pytorch cudatoolkit==10.0 torchvision -c pytorch -y

if using branch earlier than v2.0.0.

or:

conda install pytorch cudatoolkit torchvision -c pytorch -y

if branch is equal to v2.0.0.

Took me 3 days to figure this out. Basically if you install cudatoolkit==10.0 this will force pytorch to be downgraded to pytorch version 1.4 which makes the whole thing work. Its not at all obvious. And is in my opinion a bug in the mmdetection installation guide.

Solution 2:[2]

AT_CHECK is not used in the new version of pytorch.

Solution: Try to replace all AT_CHECK with TORCH_CHECK

Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution Source
Solution 1 Eamonn Kenny
Solution 2 yixianye_eric

Related Questions