ioHelper.cpp:66:5: error: ‘onnx’ has not been declared

[Tramac]

When I complied the example from the posts/TensorRT-introduction, I got the following error:

ioHelper.cpp: In function ‘std::ostream& nvinfer1::operator<<(std::ostream&, nvinfer1::ILogger::Severity)’:
ioHelper.cpp:52:12: warning: enumeration value ‘kVERBOSE’ not handled in switch [-Wswitch]
     switch (severity)
            ^
ioHelper.cpp: In function ‘size_t nvinfer1::readTensorProto(const string&, float*)’:
ioHelper.cpp:66:5: error: ‘onnx’ has not been declared
     onnx::TensorProto tensorProto;
     ^~~~
ioHelper.cpp:67:10: error: ‘tensorProto’ was not declared in this scope
     if (!tensorProto.ParseFromString(data))
          ^~~~~~~~~~~
ioHelper.cpp:67:10: note: suggested alternative: ‘readTensorProto’
     if (!tensorProto.ParseFromString(data))
          ^~~~~~~~~~~
          readTensorProto
In file included from /home/opt/compiler/gcc-8.2/gcc-8.2/include/c++/8.2.0/cassert:44,
                 from /home/work/protobuf/src/google/protobuf/extension_set.h:42,
                 from /home/work/onnx-tensorrt/build/third_party/onnx/onnx/onnx_onnx2trt_onnx-ml.pb.h:33,
                 from /home/work/onnx-tensorrt/build/third_party/onnx/onnx/onnx-ml.pb.h:2,
                 from /home/work/onnx-tensorrt/third_party/onnx/onnx/onnx_pb.h:50,
                 from ioHelper.cpp:32:
ioHelper.cpp:70:12: error: ‘tensorProto’ was not declared in this scope
     assert(tensorProto.has_raw_data());
            ^~~~~~~~~~~
ioHelper.cpp:70:12: note: suggested alternative: ‘readTensorProto’
make: *** [<builtin>: ioHelper.o] Error 1

I have installed onnx-tensorrt and TensorRT successfully, why can't find onnx?

The ioHelper.cpp is same as it.

Many appreciate if got any reply!

@harrism @angererc @nsakharnykh

[mk-nvidia]

@Tramac you're missing the onnx library. pip install onnx should install it for you. For more details see https://github.com/onnx/onnx#installation

[Tramac]

@mk-nvidia Thanks for your reply!
pip list is as follows:

Package           Version
----------------- --------
appdirs           1.4.4
dataclasses       0.8
decorator         5.0.9
graphsurgeon      0.4.1
Mako              1.1.4
MarkupSafe        2.0.1
numpy             1.19.5
onnx              1.9.0
onnx-tensorrt     0.1.0
pip               21.1.2
protobuf          3.17.3
pycuda            2020.1
pytools           2021.2.7
setuptools        57.0.0
six               1.16.0
tensorrt          7.0.0.11
torch             1.4.0
typing-extensions 3.10.0.0
uff               0.6.5
wheel             0.36.2

where the onnx, onnx-tensorrt and tensorrt have been installed successfully.

[harrism]

@mk-nvidia yeah this definitely isn't just a library installation problem. The errors are in one of the files in the present repo, saying onnx is not declared, so I suspect a header has changed between versions.

[Tramac]

@harrism how can I fix this problem, I have no idea about it.
Looking forward to reply!

[Tramac]

@harrism The new error:

ioHelper.o: In function `nvinfer1::readTensorProto(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, float*)':
ioHelper.cpp:(.text+0x16b): undefined reference to `onnx::TensorProto::TensorProto()'
ioHelper.cpp:(.text+0x184): undefined reference to `google::protobuf::MessageLite::ParseFromString(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)'
ioHelper.cpp:(.text+0x27b): undefined reference to `onnx::TensorProto::~TensorProto()'
ioHelper.cpp:(.text+0x2b0): undefined reference to `onnx::TensorProto::~TensorProto()'
collect2: error: ld returned 1 exit status
make: *** [<builtin>: simpleOnnx_1] Error 1

where Makefile as follows:

CXXFLAGS=-std=c++11 -DONNX_ML=1 -Wall -I$(CUDA_INSTALL_DIR)/include -I$(TENSORRT_LIBRARY_DIR)/include
LDFLAGS=-L$(CUDA_INSTALL_DIR)/lib64 -L$(CUDA_INSTALL_DIR)/lib64/stubs -L/usr/local/lib
LDLIBS=-Wl,--start-group -L$(ONNX_TENSORRT_DIR)/build/third_party/onnx -L$(PROTOBUF_DIR) -lnvonnxparser -lnvinfer -lcudart_static -lonnx -lonnx_proto -lprotobuf -lstdc++ -lm -lrt -ldl -lpthread -Wl,--end-group

HEADERS=${wildcard *.h}
TARGET_SRCS=$(wildcard simpleOnnx*.cpp)
TARGET_OBJS=${TARGET_SRCS:.cpp=.o}
TARGETS=${TARGET_OBJS:.o=}

This error is same as #34 , but it hasn't been resolved yet.

[harrism]

@harrism

I don't know, or I would have already told you. :) This is why I asked @mk-nvidia for help.

[Tramac]

@harrism Thanks for your reply, I will try to change a version. Update again if it is resolved.