Make -j Error - nvonnxparser_static.dir/ModelImporter.cpp.o

[bangoga]

Description

Environment

TensorRT Version: 1.8.1+cu111 ONNX-TensorRT Version / Branch: ONNX-TensorRT 8.0 Release/ Master Branch GPU Type: Unkown Nvidia Driver Version: 11.0 CUDA Version: 11.0 CUDNN Version: 8.1 Operating System + Version: Aws deep learning. ubuntu Python Version (if applicable): 3.8 Baremetal or Container (if container which image + tag): docker nvcr.io/nvidia/tensorrt:21.05-py3

Steps To Reproduce

• git clone repo onnxtensor && cd onnxtensor
• git submodule init
• git submodule update
• Add toonnx_utils.hpp :

#include <stdexcept>
#include <limits>

Running make -j

ERROR Itself

.
.
.
/onnxtensor/builtin_op_importers.cpp:5129:12: error: ‘class nvinfer1::IResizeLayer’ has no member named ‘setCoordinateTransformation’
 5129 |     layer->setCoordinateTransformation(transformation);
      |            ^~~~~~~~~~~~~~~~~~~~~~~~~~~
/onnxtensor/builtin_op_importers.cpp:5130:12: error: ‘class nvinfer1::IResizeLayer’ has no member named ‘setNearestRounding’
 5130 |     layer->setNearestRounding(roundMode);
      |            ^~~~~~~~~~~~~~~~~~
make[2]: *** [CMakeFiles/nvonnxparser_static.dir/build.make:76: CMakeFiles/nvonnxparser_static.dir/ModelImporter.cpp.o] Error 1
make[2]: *** [CMakeFiles/nvonnxparser_static.dir/build.make:89: CMakeFiles/nvonnxparser_static.dir/builtin_op_importers.cpp.o] Error 1
make[1]: *** [CMakeFiles/Makefile2:150: CMakeFiles/nvonnxparser_static.dir/all] Error 2
make: *** [Makefile:152: all] Error 2

I'm unable to see where the resolution is going to be? Any advice would be really helpful.

[kevinch-nv]

The 21.05 container has an older version of TensorRT (7.2) that's not compatible with the code on the master branch (that's meant for TRT 8.0). You can use a later container image or checkout the 7.2.1 branch and build.