PonyMaY
PonyMaY
(1) If global parallelization is not performed, can we substitute the tracker model(KLT) seperately like replacing the detect model from SSD to YOLOv4？ (2) I means: Can we reuse the...
Thank you for your prompt and enthusiastic response! (1) We want to seperate the detection and tracking. Will KLT running in parallel with detecting be better than seperated? For example,...
> I need to know your target hardware. We use Jetson NX.
>Let me know if you make any progress on conversion to TensorRT. Hi Alexis! Is the conversion of FairMOT's DLA34 backbone version(ONNX -> TRT) helpful?
Hi Alexis, sorry for being late to reply you. I have managed to convert FairMOT's YOLOv5 backbone version to TensorRT. Please check it from the download link below. [https://pan.baidu.com/s/14ucwaxZtfoj53Hre1ueJ7A](url) Password:6yct...
> @PonyMaY Thanks. I cannot access your link. Can you share your ONNX model and your TensorRT conversion script if possible? Did you use any plugins? Sorry for making trouble...
@zengjie617789 Sorry to bother you, it seems that you have managed to achieve the final `fairmot.trt` successfully. I have some troubles like this `[E] Could not load plugin library: ./build/DCNv2PluginDyn.so,...
@zengjie617789 Thank you for your prompt reply to me! Sorry to bother you again. I did success to achieve the ONNX model(file sIze is 75MB, is it correct?) And the...
@wting861006 @liu-mengyang 两位好，时隔数月不知您还是否有这个项目的记录，我按照您的方法再cuda10.2上运行了这个项目，也得到了fairmot的onnx模型，但是在转trt模型时，一致遇到`[04/08/2022-10:58:24] [E] Could not load plugin library: ./build/DCNv2PluginDyn.so, due to: libtorch.so: cannot open shared object file: No such file or directory`这样的错误，但是我能确保自己conda环境中的torch/lib目录下时有`libtorch.so`的，并且编译成功也在build目录下生成了`DCNv2Plugin.so`库。不知您们是否还留有当时的运行记录，或者能解答一下我的困惑，感谢您！
@liu-mengyang 作者您好，最近我又尝试使用tensorrt:21.02-py3版本的NGC TensorRT Docker容器运行该项目。并且得到了无错误产生的plugin编译信息。编译信息如下： ``` cd build; make make[1]: Entering directory '/home/trt-fairmot/TensorRT_ONNX_impl/build' g++ -g -DEBUG -std=c++17 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -fPIC -MD -MP -I../include -isystem /usr/local/cuda/include -isystem /usr/local/tensorrt7.2-cuda11.1/include -isystem /usr/local/lib/python3.8/dist-packages/torch/include...