tkDNN
tkDNN copied to clipboard
Deep neural network library and toolkit to do high performace inference on NVIDIA jetson platforms
When building docker base image (from `docker/Dockerfile.base`), cmake was failing with the following: ```bash CMake Error at CMakeLists.txt:91 (find_package): By not providing "Findyaml-cpp.cmake" in CMAKE_MODULE_PATH this project has asked CMake...
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...
This pull requests fixes the issues mentioned in [287](https://github.com/ceccocats/tkDNN/issues/287) and moves to __declspec(dllexport) and __declspec(dllimport) on a as needed basis (symbol wise per header) instead of using CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS in the...
Loading YAML: yolo4_fp32.rt terminate called after throwing an instance of 'YAML::ParserException'what(): yaml-cpp: error at line 1, column 8: unknown escape character:Aborted (core dumped) Could you please tell me why?
Hi! I'm a bit confused, you show metrics for yolo 608 on the jetson nano, however I'm not able to serialize it with only 4GB of ram. Can you point...
root@621c511df0aa951571b070ee:~/tkDNN/build# ./demo csresnext50-panet-spp_fp16.rt ../demo/yolo_test.mp4 y Loading YAML: csresnext50-panet-spp_fp16.rt terminate called after throwing an instance of 'YAML::ParserException' what(): yaml-cpp: error at line 1, column 8: unknown escape character: Aborted (core dumped)...
I was been using tkdnn with tensort6/cuda10.0 for a while and everything works fine. Recently I upgrade the gpu card from 2070 to A4000, so a upgrade of all related...
when I make tkDNN in jetson nano, I met unexpected error message as below: kibum@kibum-desktop:~/tkDNN/build$ make CMake Warning (dev) at CMakeLists.txt:21: Syntax Warning in cmake code at column 30 Argument...
CV 4.5.0 + CUDA, jetpack 4.5.1. Low performance of models like yolo4, yolo4x (lower than in the original darcnet), performance of tiny models is correct. Also, when I try to...