ceccocats
commented
2 years ago tkDNN require opencv compled with dnn module, but is only for that Int8batchStream file. If you cant install opencv with dnn module just comment these lines: https://github.com/ceccocats/tkDNN/blob/d4f7b4ad8b21f1af78e1bada3e0368c0c1304ad9/src/Int8BatchStream.cpp#L4 https://github.com/ceccocats/tkDNN/blob/d4f7b4ad8b21f1af78e1bada3e0368c0c1304ad9/src/Int8BatchStream.cpp#L129 https://github.com/ceccocats/tkDNN/blob/d4f7b4ad8b21f1af78e1bada3e0368c0c1304ad9/src/Int8BatchStream.cpp#L130
of course int8 will not work
I am trying to run this on Google Colab, however cmake returns this error: -- CUDA Architecture: -arch=sm_75 -- CUDA Version: 11.1 -- CUDA Path: /usr/local/cuda -- CUDA Libararies: /usr/local/cuda/lib64/libcudart_static.a;Threads::Threads;dl;/usr/lib/x86_64-linux-gnu/librt.so -- CUDA Performance Primitives: /usr/local/cuda/lib64/libnppc.so;/usr/local/cuda/lib64/libnppial.so;/usr/local/cuda/lib64/libnppicc.so;;/usr/local/cuda/lib64/libnppidei.so;/usr/local/cuda/lib64/libnppif.so;/usr/local/cuda/lib64/libnppig.so;/usr/local/cuda/lib64/libnppim.so;/usr/local/cuda/lib64/libnppist.so;/usr/local/cuda/lib64/libnppisu.so;/usr/local/cuda/lib64/libnppitc.so;/usr/local/cuda/lib64/libnpps.so -- Found CUDNN: /usr/lib/x86_64-linux-gnu/libcudnn.so -- Found CUDNN include: /usr/include -- Found NVINFER: /usr/lib/x86_64-linux-gnu/libnvinfer.so -- Found NVINFER include: /usr/include/x86_64-linux-gnu Eigen DIR: /usr/include/eigen3 install dir:/usr/local -- Configuring done -- Generating done -- Build files have been written to: /content/tkdnn/build Consolidate compiler generated dependencies of target kernels [ 21%] Built target kernels Consolidate compiler generated dependencies of target tkDNN [ 21%] Building CXX object CMakeFiles/tkDNN.dir/src/Int8BatchStream.cpp.o /content/tkdnn/src/Int8BatchStream.cpp:4:10: fatal error: opencv2/dnn/dnn.hpp: No such file or directory
include <opencv2/dnn/dnn.hpp>
compilation terminated. CMakeFiles/tkDNN.dir/build.make:215: recipe for target 'CMakeFiles/tkDNN.dir/src/Int8BatchStream.cpp.o' failed make[2]: [CMakeFiles/tkDNN.dir/src/Int8BatchStream.cpp.o] Error 1 CMakeFiles/Makefile2:214: recipe for target 'CMakeFiles/tkDNN.dir/all' failed make[1]: [CMakeFiles/tkDNN.dir/all] Error 2 Makefile:135: recipe for target 'all' failed make: *** [all] Error 2
I have installed tensorrt using pip: !pip install --upgrade --index-url https://pypi.ngc.nvidia.com nvidia-tensorrt==8.2.5.1 and it seems to install correctly: import tensorrt as trt trt.version returns: 8.2.5.1 Could you provide a guide on running this on Google Colab? Seems like I am missing something in installation.