issue when running python $DENSEPOSE/detectron/tests/test_zero_even_op.py about densepose_installation

[Johnqczhang]

http://linkinpark213.com/2018/11/18/densepose-minesweeping/#2-10-Undefined-symbol-ZN6caffe219CPUOperatorRegistryB5cxx11Ev

[hanabi7]

i install pytorch=1.1.0 with conda, do i have to install pytorch from source code to the newest version of pytorch?

[hanabi7]

my gcc version is correct

[Johnqczhang]

i install pytorch=1.1.0 with conda, do i have to install pytorch from source code to the newest version of pytorch?

I'm not sure if it works if you install the latest version of pytorch from source code. Using pytorch-1.1.0 installed from conda and gcc-4.9.2 really works for me. Have you tried solution in this issue?

[SriRamGovardhanam]

Hello
i have checked your guide perfectly
I am facing OS Error issue

Traceback (most recent call last): File "DensePose/detectron/tests/test_zero_even_op.py", line 117, in <module> c2_utils.import_custom_ops() File "/home/sriram/DensePose/detectron/utils/c2.py", line 40, in import_custom_ops dyndep.InitOpsLibrary(custom_ops_lib) File "/home/sriram/anaconda2/lib/python2.7/site-packages/caffe2/python/dyndep.py", line 35, in InitOpsLibrary _init_impl(name) File "/home/sriram/anaconda2/lib/python2.7/site-packages/caffe2/python/dyndep.py", line 48, in _init_impl ctypes.CDLL(path) File "/home/sriram/anaconda2/lib/python2.7/ctypes/__init__.py", line 366, in __init__ self._handle = _dlopen(self._name, mode) OSError: /home/sriram/DensePose/build/libcaffe2_detectron_custom_ops_gpu.so: undefined symbol: _ZN6caffe219CPUOperatorRegistryB5cxx11Ev
Tried to install gcc-4.9.2 and ended up facing error for so may possible times, also when i ran using colab, there they just installed gcc-4.9.1 but default gcc is 7.5.0

so i just skipped test_zero_even_op.py and tried to run in infer mode , even there i faced some errors like

RuntimeError: [enforce fail at context_gpu.cu:415] error == cudaSuccess. 2 vs 0. Error at: /opt/conda/conda-bld/pytorch_1549617926868/work/caffe2/core/context_gpu.cu:415: out of memory
please check this thread [https://github.com/facebookresearch/DensePose/issues/269]

i was trying from the last 7days , it is really painful
please help me out.