mosheliv / tensortrt-yolo-python-api Goto Github PK
View Code? Open in Web Editor NEWPython api for tensorrt implementation of yolov2
Python api for tensorrt implementation of yolov2
Hi @mosheliv,
Look like the step no 6 for the link is wrong for deepstream_reference_apps/yolo/apps/trt-yolo/CMakeFiles/trt-yolo-app.dir/flags.make, should it deepstream_reference_apps/yolo/apps/trt-yolo/build/CMakeFiles/trt-yolo-app.dir/flags.make ?
Hi @mosheliv,
In step 9 cd apps/trt-yolo/lib. in my case, there is lib folder. It exist in apps/trt-yolo/build/lib or https://github.com/NVIDIA-AI-IOT/deepstream_reference_apps/tree/master/yolo/lib . so which lib did you mean?
you can change readme from
export YOLO_ROOT=pwd/deepstream_reference_apps/yolo
to
export YOLO_ROOT=$PWD/deepstream_reference_apps/yolo
How can I use cuda 10.2 instead of cuda 10.0 ?
cmake -D CMAKE_BUILD_TYPE=Release -D CUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda ..
-- The CXX compiler identification is GNU 7.5.0
-- Check for working CXX compiler: /usr/bin/c++
-- Check for working CXX compiler: /usr/bin/c++ -- works
-- Detecting CXX compiler ABI info
-- Detecting CXX compiler ABI info - done
-- Detecting CXX compile features
-- Detecting CXX compile features - done
-- Looking for C++ include pthread.h
-- Looking for C++ include pthread.h - found
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Failed
-- Looking for pthread_create in pthreads
-- Looking for pthread_create in pthreads - not found
-- Looking for pthread_create in pthread
-- Looking for pthread_create in pthread - found
-- Found Threads: TRUE
CMake Error at /usr/share/cmake-3.16/Modules/FindPackageHandleStandardArgs.cmake:146 (message):
Could NOT find CUDA: Found unsuitable version "10.2", but required is exact
version "10.0" (found /usr/local/cuda)
Call Stack (most recent call first):
/usr/share/cmake-3.16/Modules/FindPackageHandleStandardArgs.cmake:391 (_FPHSA_FAILURE_MESSAGE)
/usr/share/cmake-3.16/Modules/FindCUDA.cmake:1104 (find_package_handle_standard_args)
CMakeLists.txt:36 (find_package)
-- Configuring incomplete, errors occurred!
See also "/opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream_reference_apps/yolo/apps/trt-yolo/build/CMakeFiles/CMakeOutput.log".
See also "/opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream_reference_apps/yolo/apps/trt-yolo/build/CMakeFiles/CMakeError.log".
Hi, I was wondering if there is an example on how to use it. I'd like to extract the data (class name,location) of each detection.
Thanks for your help.
I have compiled opencv from source and still it's not finding the path, anyone please ?
after running this: make && sudo make install
Scanning dependencies of target yolo-lib
[ 15%] Building CXX object lib/CMakeFiles/yolo-lib.dir/calibrator.cpp.o
In file included from /home/admin1/deepstream_reference_apps/yolo/lib/ds_image.h:28:0,
from /home/admin1/deepstream_reference_apps/yolo/lib/calibrator.h:29,
from /home/admin1/deepstream_reference_apps/yolo/lib/calibrator.cpp:26:
/home/admin1/deepstream_reference_apps/yolo/lib/trt_utils.h:31:10: fatal error: opencv/cv.h: No such file or directory
#include <opencv/cv.h>
^~~~~~~~~~~~~
compilation terminated.
make[2]: *** [lib/CMakeFiles/yolo-lib.dir/build.make:70: lib/CMakeFiles/yolo-lib.dir/calibrator.cpp.o] Error 1
make[1]: *** [CMakeFiles/Makefile2:123: lib/CMakeFiles/yolo-lib.dir/all] Error 2
make: *** [Makefile:130: all] Error 2
I think they updated the deepstream reference apps repo there is no directory called "yolo" in it.
I've got this error :
jetson-nano@jetsonnano-desktop:~/deepstream_reference_apps/yolo/apps/trt-yolo/build$ cmake -D CMAKE_BUILD_TYPE=Release ..
-- Found TensorRT headers at /usr/include/aarch64-linux-gnu
-- Found TensorRT libs at /usr/lib/aarch64-linux-gnu/libnvinfer.so;/usr/lib/aarch64-linux-gnu/libnvinfer_plugin.so
CMake Error at CMakeLists.txt:73 (add_subdirectory):
add_subdirectory given source
"/home/jetson-nano/deepstream_reference_apps/yolo/apps/../../lib" which is
not an existing directory.
Please help me figure this out.
hi mosh,
thanks for creating this awesome wrapper. i am having the following trouble running it though:
Traceback (most recent call last):
File "t.py", line 7, in
lib=CDLL('./libyolo.so')
File "/usr/lib/python3.6/ctypes/init.py", line 348, in init
self._handle = _dlopen(self._name, mode)
OSError: ./libyolo.so: undefined symbol: _ZN2cv7putTextERKNS_17_InputOutputArrayERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEENS_6Point_IiEEidNS_7Scalar_IdEEiib
do you have an idea of what could e the cause.
i am also wondering if it could run on a video?
thanks
Basically I am trying to load 2 different tiny-yolov3 models to memory and do inference depending on the situation. However, when I try to load 2 different yolo models in the same python script, library messes up the memory locations and fails.
Any help would be appreciated. I will post if I come up with a solution
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.