marcoslucianops / DeepStream-Yolo

NVIDIA DeepStream SDK 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models
MIT License
1.39k stars 344 forks source link

’CUDA=10.2 make - C nvdsinder_ Custom_ Impl_ Yolo 'has been run,but no engine file #426

Open ghty11468 opened 10 months ago

ghty11468 commented 10 months ago

’CUDA=10.2 make - C nvdsinder Custom Impl_ Yolo 'has been run, and the compilation process seems to have been compiled, but it seems that no engine file has been generated. The following is the compilation process:

jetson@yahboom:~/DeepStream-Yolo-master$ CUDA_VER=10.2 make -C nvdsinfer_custom_impl_Yolo make: Entering directory '/home/jetson/DeepStream-Yolo-master/nvdsinfer_custom_impl_Yolo' g++ -c -o utils.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include utils.cpp g++ -c -o yolo.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include yolo.cpp yolo.cpp: In member function ‘nvinfer1::ICudaEngine Yolo::createEngine(nvinfer1::IBuilder, nvinfer1::IBuilderConfig)’: yolo.cpp:207:83: warning: ‘nvinfer1::ICudaEngine nvinfer1::IBuilder::buildEngineWithConfig(nvinfer1::INetworkDefinition&, nvinfer1::IBuilderConfig&)’ is deprecated [-Wdeprecated-declarations] nvinfer1::ICudaEngine engine = builder->buildEngineWithConfig(network, config); ^ In file included from /usr/include/aarch64-linux-gnu/NvOnnxParser.h:26:0, from yolo.cpp:26: /usr/include/aarch64-linux-gnu/NvInfer.h:8642:43: note: declared here TRT_DEPRECATED nvinfer1::ICudaEngine buildEngineWithConfig( ^~~~~ g++ -c -o nvdsinfer_yolo_engine.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include nvdsinfer_yolo_engine.cpp g++ -c -o nvdsinitinputlayers_Yolo.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include nvdsinitinputlayers_Yolo.cpp g++ -c -o nvdsparsebbox_Yolo.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include nvdsparsebbox_Yolo.cpp g++ -c -o yoloPlugins.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include yoloPlugins.cpp g++ -c -o layers/convolutional_layer.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include layers/convolutional_layer.cpp g++ -c -o layers/route_layer.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include layers/route_layer.cpp g++ -c -o layers/shortcut_layer.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include layers/shortcut_layer.cpp g++ -c -o layers/pooling_layer.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include layers/pooling_layer.cpp g++ -c -o layers/reorg_layer.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include layers/reorg_layer.cpp g++ -c -o layers/batchnorm_layer.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include layers/batchnorm_layer.cpp g++ -c -o layers/activation_layer.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include layers/activation_layer.cpp g++ -c -o layers/channels_layer.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include layers/channels_layer.cpp g++ -c -o layers/sam_layer.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include layers/sam_layer.cpp g++ -c -o layers/deconvolutional_layer.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include layers/deconvolutional_layer.cpp g++ -c -o layers/upsample_layer.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include layers/upsample_layer.cpp g++ -c -o layers/implicit_layer.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include layers/implicit_layer.cpp /usr/local/cuda-10.2/bin/nvcc -c -o yoloForward_v2.o --compiler-options '-fPIC' -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include yoloForward_v2.cu /usr/local/cuda-10.2/bin/nvcc -c -o yoloForward.o --compiler-options '-fPIC' -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include yoloForward.cu /usr/local/cuda-10.2/bin/nvcc -c -o yoloForward_nc.o --compiler-options '-fPIC' -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include yoloForward_nc.cu /usr/local/cuda-10.2/bin/nvcc -c -o nvdsparsebbox_Yolo_cuda.o --compiler-options '-fPIC' -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-10.2/include nvdsparsebbox_Yolo_cuda.cu g++ -o libnvdsinfer_custom_impl_Yolo.so utils.o yolo.o nvdsinfer_yolo_engine.o nvdsinitinputlayers_Yolo.o nvdsparsebbox_Yolo.o yoloPlugins.o layers/convolutional_layer.o layers/route_layer.o layers/shortcut_layer.o layers/pooling_layer.o layers/reorg_layer.o layers/batchnorm_layer.o layers/activation_layer.o layers/channels_layer.o layers/sam_layer.o layers/deconvolutional_layer.o layers/upsample_layer.o layers/implicit_layer.o yoloForward_v2.o yoloForward.o yoloForward_nc.o nvdsparsebbox_Yolo_cuda.o -shared -Wl,--start-group -lnvinfer_plugin -lnvinfer -lnvparsers -lnvonnxparser -L/usr/local/cuda-10.2/lib64 -lcudart -lcublas -lstdc++fs -Wl,--end-group make: Leaving directory '/home/jetson/DeepStream-Yolo-master/nvdsinfer_custom_impl_Yolo'

I earnestly request the author's help in answering. Thank you.

marcoslucianops commented 10 months ago

The engine is created when you run the deepstream-app command for the model you are running.

ghty11468 commented 10 months ago

引擎是在为正在运行的模型运行命令时创建的。deepstream-app

Thank you for your answer. I have also learned this content. But what happened when I encountered this error after running the command?

e22606c9b19d4baaa93c727f0e2063f

marcoslucianops commented 10 months ago

Which Jetson board are you using?

ghty11468 commented 10 months ago

您使用的是哪种 Jetson 板?

Yes, I'm using a Jetson nano

marcoslucianops commented 10 months ago

Can you debug the deepstream-app using gdb?

ghty11468 commented 10 months ago

Can you debug the deepstream-app using gdb?

Sorry, I can't do the operation you mentioned

marcoslucianops commented 10 months ago

The commands are

gdb deepstream-app

and

run -c deepstream_app_config.txt
marcoslucianops commented 10 months ago

To get the output

where
ghty11468 commented 10 months ago

To get the output

where

ad80b17d200f5d54c7f8f9692c5e5ff 75533d48f9876a9200a5c37cd8936ed

marcoslucianops commented 10 months ago

Which model are you trying to run?

ghty11468 commented 10 months ago

Which model are you trying to run?

I am using the YOLOv5S model. If this command is successfully run, will an engine file be generated?

marcoslucianops commented 10 months ago

Yes, but I don't know why you're getting this error. Maybe something wrong in the board enviroment or exported model.

ghty11468 commented 10 months ago

Yes, but I don't know why you're getting this error. Maybe something wrong in the board enviroment or exported model.

Thank you. Do you still have any previous version of the code package? I am using the one that utilizes cfg and wts files

marcoslucianops commented 10 months ago

You can get it in the old commits, but I recommend you to use the new files (with ONNX export) because it's more optimized now.

ghty11468 commented 10 months ago

You can get it in the old commits, but I recommend you to use the new files (with ONNX export) because it's more optimized now.

Thank you. May I ask where the old commits you mentioned is? Sorry, I couldn't find it

marcoslucianops commented 10 months ago

https://github.com/marcoslucianops/DeepStream-Yolo/tree/e652ef4e394fbcee0b8b8652c4630802bec4eab3

This is the last commit that uses the wts and cfg files.

ghty11468 commented 10 months ago

https://github.com/marcoslucianops/DeepStream-Yolo/tree/e652ef4e394fbcee0b8b8652c4630802bec4eab3

这是使用 wts 和 cfg 文件的最后一次提交。

Thank you very much, thank you for the patient answer above

ghty11468 commented 10 months ago

https://github.com/marcoslucianops/DeepStream-Yolo/tree/e652ef4e394fbcee0b8b8652c4630802bec4eab3

这是使用 wts 和 cfg 文件的最后一次提交。

Thank you very much. My problem has been resolved, just download the project file again. Perhaps the previous project code file was damaged