Tianxiaomo / pytorch-YOLOv4

PyTorch ,ONNX and TensorRT implementation of YOLOv4
Apache License 2.0
4.47k stars 1.49k forks source link

while building nvdsinfer_custom_impl_Yolo though make command , i get below error . Kindly assist #541

Open h9945394143 opened 2 years ago

h9945394143 commented 2 years ago

root@39026ff1831b:/app/sriharsha/pytorch-YOLOv4/DeepStream/nvdsinfer_custom_impl_Yolo# make g++ -c -o nvdsinfer_yolo_engine.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream-6.1/sources/includes -I/usr/local/cuda-11.6/include nvdsinfer_yolo_engine.cpp In file included from nvdsinfer_yolo_engine.cpp:25: yoloPlugins.h: In member function 'virtual nvinfer1::IPluginV2 YoloLayerV3PluginCreator::deserializePlugin(const char, const void, size_t)': yoloPlugins.h:122:56: error: invalid new-expression of abstract class type 'YoloLayerV3' 122 | return new YoloLayerV3(serialData, serialLength) ; | ^ yoloPlugins.h:50:7: note: because the following virtual functions are pure within 'YoloLayerV3': 50 | class YoloLayerV3 : public nvinfer1::IPluginV2 | ^~~ In file included from /usr/include/x86_64-linux-gnu/NvInferLegacyDims.h:53, from /usr/include/x86_64-linux-gnu/NvInfer.h:53, from /usr/include/x86_64-linux-gnu/NvCaffeParser.h:53, from /opt/nvidia/deepstream/deepstream-6.1/sources/includes/nvdsinfer_custom_impl.h:126, from nvdsinfer_yolo_engine.cpp:23: /usr/include/x86_64-linux-gnu/NvInferRuntimeCommon.h:606:21: note: 'virtual int32_t nvinfer1::IPluginV2::enqueue(int32_t, const void const, void const, void, cudaStream_t)' 606 | virtual int32_t enqueue(int32_t batchSize, void const const inputs, void const outputs, void* workspace, | ^~~ make: *** [Makefile:51: nvdsinfer_yolo_engine.o] Error 1 root@39026ff1831b:/app/sriharsha/pytorch-YOLOv4/DeepStream/nvdsinfer_custom_impl_Yolo#

PhiDCH commented 1 year ago

i have the same error when compile with cuda 11.7 in DeepStream 6.1