zsef123 / connected_components_pytorch Goto Github PK

I tried to compile your code with my c++ code.
However I get the error:

error: ‘atomicMin’ was not declared in this scope

Could you help me?

My CMakeLists looks like this

cmake_minimum_required(VERSION 3.0.0)
project(TTEST VERSION 0.1.0)

include(CTest)
enable_testing()
set(Torch_DIR "/path/to/torch/share/cmake/Torch")
find_package(Torch REQUIRED)
message(STATUS "Torch INCLUDE_DIR:${TORCH_INCLUDE_DIRS}")
message(STATUS "Torch LIBRARIES:${TORCH_LIBRARIES}")

enable_language(CUDA)
message(STATUS "CUDA INCLUDE_DIR:${CUDA_INCLUDE_DIRS}")
message(STATUS "CUDA LIBRARIES:${CUDA_LIBRARIES}")

include_directories("./include") #directory of buf.h
add_executable(TTEST main.cpp buf_3d.cu)
target_link_libraries(TTEST ${TORCH_LIBRARIES} ${CUDA_LIBRARIES})

I got Error in import _C

what is the _C ??

thank you

Hi, thanks for this work... I tried installing it with the latest version of pytorch 1.9, but it doesn't work.
Do you plan to update this to run on the latest version?

Many thanks!

If the 2D code is applied on a tensor that is a 2D slice of a larger tensor, e.g.

x.shape == [B, H, W, C]

correct_out = connected_components_labeling(x[0, :, :, 0].contiguous())
incorrect_out = connected_components_labeling(x[0, :, :, 0])

the expected output correct_out:

then incorrect_out will be a weird strided version of the correct_out:

the input was generated as follows, reusing the example code:
x = torch.tensor(cleared_copy).to("cuda", torch.uint8)[None, :, :, None].repeat(1024, 1, 1, 2)

Fixes

The quick fix is to call .contiguous() on every slice, the correct fix would be to either throw an error if the input is not contiguous or take the tensor strides into consideration on the cuda backend.

Hope this might help someone who got unexpected results.
Nevertheless, this implementations is very quick and is an awesome starting point, so thank you! <3

Hello,

I am interested in updating your tool to ensure its compatibility with the programming environment expected in 2024, including support for CUDA 11.8. Could you provide guidance on the necessary modifications or steps required to achieve this?

Thank you for your time and support.

I am not firm with the cuda language. so sorry for that question: How are the label-idx created?

I would expect label to be [0, 1, 2 ....n] but got [0, 1, 34534, 340394]