monday-leo / yolov5_tensorrt_win10 Goto Github PK

其他环境我都bao持一致，我想用VS2019，这个要怎么修改呢

windows下使用mark分支下的CMakeLists.txt进行FP16量化编译成功，但是INT8量化报错：
错误 LNK2019 无法解析的外部符号 "public: __cdecl Int8EntropyCalibrator2::Int8EntropyCalibrator2(int,int,int,char const *,char const *,char const *,bool)" (??0Int8EntropyCalibrator2@@qeaa@HHHPEBD00_N@Z)，函数 "class nvinfer1::ICudaEngine * __cdecl build_engine(unsigned int,class nvinfer1::IBuilder *,class nvinfer1::IBuilderConfig *,enum nvinfer1::DataType,float &,float &,class std::basic_string<char,struct std::char_traits,class std::allocator > &)" (?build_engine@@YAPEAVICudaEngine@nvinfer1@@IPEAVIBuilder@2@PEAVIBuilderConfig@2@W4DataType@2@AEAM3AEAV?$basic_string@DU?$char_traits@D@std@@v?$allocator@D@2@@std@@@z)

您好，
请问需要支持最新的官网的 yolov5 版本，请问需要怎么修改呢？

这个报错原因是什么呢

linux下，头文件dirent.h报错找不到windows.h，请问怎么解决呢？

CUDA11.5
TensorRT 8.2.5.1
编译后使用Yolov5.exe可以直接调用best.engine进行推理，
编译成Yolov5.dll，python3.11 CDLL提示
FileNotFoundError: Could not find module 'C:\Users\zhuzi\Documents\yolov5\build\Release\yolov5.dll' (or one of its dependencies). Try using the full path with constructor syntax.

设置winmod=1提示
OSError: exception: access violation reading 0x0000000000000008

Performing C SOURCE FILE Test CMAKE_HAVE_LIBC_PTHREAD failed with the following output:
Change Dir: D:/2/Yolov5_Tensorrt_Win10-master/build/CMakeFiles/CMakeScratch/TryCompile-1qpn13

Run Build Command(s):E:/vs/MSBuild/Current/Bin/amd64/MSBuild.exe cmTC_0bcb0.vcxproj /p:Configuration=Debug /p:Platform=x64 /p:VisualStudioVersion=17.0 /v:m && MSBuild version 17.3.1+2badb37d1 for .NET Framework
用于 x64 的 Microsoft (R) C/C++ 优化编译器 19.33.31630 版
src.c
版权所有(C) Microsoft Corporation。保留所有权利。
cl /c /Zi /W3 /WX- /diagnostics:column /Od /Ob0 /D _MBCS /D WIN32 /D _WINDOWS /D CMAKE_HAVE_LIBC_PTHREAD /D "CMAKE_INTDIR="Debug"" /Gm- /RTC1 /MDd /GS /fp:precise /Zc:wchar_t /Zc:forScope /Zc:inline /Fo"cmTC_0bcb0.dir\Debug\" /Fd"cmTC_0bcb0.dir\Debug\vc143.pdb" /external:W3 /Gd /TC /errorReport:queue "D:\2\Yolov5_Tensorrt_Win10-master\build\CMakeFiles\CMakeScratch\TryCompile-1qpn13\src.c"
D:\2\Yolov5_Tensorrt_Win10-master\build\CMakeFiles\CMakeScratch\TryCompile-1qpn13\src.c(1,10): fatal error C1083: 无法打开包括文件: “pthread.h”: No such file or directory [D:\2\Yolov5_Tensorrt_Win10-master\build\CMakeFiles\CMakeScratch\TryCompile-1qpn13\cmTC_0bcb0.vcxproj]

首先非常感谢作者提供的步骤，非常详细！！！
奇怪的是编译可以输出yolov5.dll，但是通过LoadLibrary不能加载成功，通过导出函数查看工具，可以正常看到yolov5.dll的导出函数，看起来像是dll被损坏了一样？可以100%确定yolov5.dll文件是存在的。

可以在linux下使用吗

前面wts模型文件是我自己准备的，yoolar.h里对应的改了，release.exe文件也有了，
就是运行转换的时候，loading后就开始报错，
这什么kernel weights 为0，啥意思？

E:\PycharmProject\Yolov5_Tensorrt_Win10-master\build\Release>yolov5 -s mybest.wts myberry.engine s
[12/07/2023-15:50:41] [W] [TRT] The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag whenever possible.
Loading weights: mybest.wts
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: [scaleLayer.h::nvinfer1::ScaleLayer::setScale::23] Error Code 3: API Usage Error (Parameter check failed at: scaleLayer.h::nvinfer1::ScaleLayer::setScale::23, condition: scale.count > 0
)
[12/07/2023-15:50:42] [E] [TRT] 3: [scaleLayer.h::nvinfer1::ScaleLayer::setShift::24] Error Code 3: API Usage Error (Parameter check failed at: scaleLayer.h::nvinfer1::ScaleLayer::setShift::24, condition: shift.count > 0
)
[12/07/2023-15:50:42] [E] [TRT] 3: [scaleLayer.h::nvinfer1::ScaleLayer::setPower::25] Error Code 3: API Usage Error (Parameter check failed at: scaleLayer.h::nvinfer1::ScaleLayer::setPower::25, condition: power.count > 0
)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: [scaleLayer.h::nvinfer1::ScaleLayer::setScale::23] Error Code 3: API Usage Error (Parameter check failed at: scaleLayer.h::nvinfer1::ScaleLayer::setScale::23, condition: scale.count > 0
)
[12/07/2023-15:50:42] [E] [TRT] 3: [scaleLayer.h::nvinfer1::ScaleLayer::setShift::24] Error Code 3: API Usage Error (Parameter check failed at: scaleLayer.h::nvinfer1::ScaleLayer::setShift::24, condition: shift.count > 0
)
[12/07/2023-15:50:42] [E] [TRT] 3: [scaleLayer.h::nvinfer1::ScaleLayer::setPower::25] Error Code 3: API Usage Error (Parameter check failed at: scaleLayer.h::nvinfer1::ScaleLayer::setPower::25, condition: power.count > 0
)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: [scaleLayer.h::nvinfer1::ScaleLayer::setScale::23] Error Code 3: API Usage Error (Parameter check failed at: scaleLayer.h::nvinfer1::ScaleLayer::setScale::23, condition: scale.count > 0
)
[12/07/2023-15:50:42] [E] [TRT] 3: [scaleLayer.h::nvinfer1::ScaleLayer::setShift::24] Error Code 3: API Usage Error (Parameter check failed at: scaleLayer.h::nvinfer1::ScaleLayer::setShift::24, condition: shift.count > 0
)
[12/07/2023-15:50:42] [E] [TRT] 3: [scaleLayer.h::nvinfer1::ScaleLayer::setPower::25] Error Code 3: API Usage Error (Parameter check failed at: scaleLayer.h::nvinfer1::ScaleLayer::setPower::25, condition: power.count > 0
)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: [scaleLayer.h::nvinfer1::ScaleLayer::setScale::23] Error Code 3: API Usage Error (Parameter check failed at: scaleLayer.h::nvinfer1::ScaleLayer::setScale::23, condition: scale.count > 0
)
[12/07/2023-15:50:42] [E] [TRT] 3: [scaleLayer.h::nvinfer1::ScaleLayer::setShift::24] Error Code 3: API Usage Error (Parameter check failed at: scaleLayer.h::nvinfer1::ScaleLayer::setShift::24, condition: shift.count > 0
)
[12/07/2023-15:50:42] [E] [TRT] 3: [scaleLayer.h::nvinfer1::ScaleLayer::setPower::25] Error Code 3: API Usage Error (Parameter check failed at: scaleLayer.h::nvinfer1::ScaleLayer::setPower::25, condition: power.count > 0
)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: (Unnamed Layer* 0) [Convolution]:kernel weights has count 0 but 3456 was expected
[12/07/2023-15:50:42] [E] [TRT] 4: (Unnamed Layer* 0) [Convolution]: count of 0 weights in kernel, but kernel dimensions (6,6) with 3 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 3 * 66 * 32 / 1 = 3456
[12/07/2023-15:50:42] [E] [TRT] 4: [convolutionNode.cpp::nvinfer1::builder::ConvolutionNode::computeOutputExtents::58] Error Code 4: Internal Error ((Unnamed Layer 0) [Convolution]: number of kernel weights does not match tensor dimensions)
[12/07/2023-15:50:42] [E] [TRT] 3: [network.cpp::nvinfer1::Network::addResize::1358] Error Code 3: API Usage Error (Parameter check failed at: network.cpp::nvinfer1::Network::addResize::1358, condition: input.getDimensions().nbDims > 0

我使用这个engine 模型，精度有点不准，请问怎么调成fp32精度