tensorrt-cpp-api
tensorrt-cpp-api copied to clipboard
cyrusbehr
TensorRT C++ API Tutorial
Brief explanation: 1. **Modify Util namespace to EngineUtil**: Reduce the potential for name duplication. 2. **Move serializeEngineOptions() to EngineUtil namespace** 3. **Modify getDeviceNames() to getGpuDeviceNames() and move it to EngineUtil...
I have found that building this project in an Orin NX-based system runs into the OpenCV v4.5.4 from the JetPack 5.1.2 not being built with the CMake option -DOPENCV_EXTRA_MODULES_PATH=/modules. Therefore...
To reduce potential bugs and increase code quality, let's consider integrating [CodeRabbit.ai](https://coderabbit.ai/). Although I haven't used it extensively, it has provided valuable comments and suggestions in my experience. **Tasks:** -...
Hi, I've noticed that the library is updated frequently, which is great! However, without unit tests, it can be challenging to ensure that these updates don't break existing functionality. Adding...
I use scripts/build_opencv.sh to build opencv4.8, but i get some errors. ``` [100%] Linking CXX executable ../../bin/opencv_test_videostab [100%] Built target opencv_test_videostab In file included from /workspace/tensorrt-cpp-api-main/scripts/opencv-4.8.0/build/modules/python_bindings_generator/pyopencv_custom_headers.h:21, from /workspace/tensorrt-cpp-api-main/scripts/opencv-4.8.0/modules/python/src2/cv2.cpp:88: /workspace/tensorrt-cpp-api-main/scripts/opencv-4.8.0/modules/gapi/misc/python/python_bridge.hpp:85:27: error:...
Should be quite straightforward to add support for grayscale images. From my understanding, a small refactoring of `resizeKeepAspectRatioPadRightBottom` and `blobFromGpuMats` should be all that's needed.
When I tried to apply your code to MobileNetV3 inference, I discovered that your preprocessing transformation (mean subtraction and division by standard deviation) doesn't work correctly when these values are...
Hi， thanks for your excellent work, it really helps me in my work. But i have a question here. I modified your code to infer my model. I used FP16...
