You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, I am trying to follow the guide to install the r2inference library on a jetson nano. For my backend, I am using TensorRT which your documentation said is already included on the Jetson Nano with Jetpack 4.3 which I currently have installed. When I run the ninja build command I get the following error.
ninja: Entering directory build'
[57/95] Compiling C++ object tests/unit/r2i/tensorrt/engine.p/engine.cc.o
FAILED: tests/unit/r2i/tensorrt/engine.p/engine.cc.o
c++ -Itests/unit/r2i/tensorrt/engine.p -Itests/unit/r2i/tensorrt -I../tests/unit/r2i/tensorrt -I. -I.. -I/usr/local/cuda-10.2/targets/aarch64-linux/include -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -fdiagnostics-color=always -D_FILE_OFFSET_BITS=64 -Wall -Winvalid-pch -Wnon-virtual-dtor -std=c++11 -g -pthread -MD -MQ tests/unit/r2i/tensorrt/engine.p/engine.cc.o -MF tests/unit/r2i/tensorrt/engine.p/engine.cc.o.d -o tests/unit/r2i/tensorrt/engine.p/engine.cc.o -c ../tests/unit/r2i/tensorrt/engine.cc
In file included from ../tests/unit/r2i/tensorrt/engine.cc:26:0:
../tests/unit/r2i/tensorrt/mockcudaengine.cc:97:18: error: cannot declare field ‘nvinfer1::{anonymous}::MockExecutionContext::cuda_engine’ to be of abstract type ‘nvinfer1::{anonymous}::MockCudaEngine’
MockCudaEngine cuda_engine;
^~~~~~~~~~~
../tests/unit/r2i/tensorrt/mockcudaengine.cc:22:7: note: because the following virtual functions are pure within ‘nvinfer1::{anonymous}::MockCudaEngine’:
class MockCudaEngine : public ICudaEngine {
^~~~~~~~~~~~~~
In file included from /usr/include/aarch64-linux-gnu/NvInfer.h:53:0,
from ../r2i/tensorrt/model.h:17,
from ../r2i/tensorrt/engine.h:18,
from ../tests/unit/r2i/tensorrt/engine.cc:13:
/usr/include/aarch64-linux-gnu/NvInferRuntime.h:1539:18: note: virtual bool nvinfer1::ICudaEngine::hasImplicitBatchDimension() const
virtual bool hasImplicitBatchDimension() const TRTNOEXCEPT = 0;
^~~~~~~~~~~~~~~~~~~~~~~~~
../tests/unit/r2i/tensorrt/engine.cc: In member function ‘virtual void TEST_GROUP_CppUTestGroupTensorRTEngine::setup()’:
../tests/unit/r2i/tensorrt/engine.cc:91:29: error: invalid new-expression of abstract class type ‘nvinfer1::{anonymous}::MockCudaEngine’
nvinfer1::MockCudaEngine,
^~~~~~~~~~~~~~
[59/95] Compiling C++ object tests/unit/r2i/tensorrt/frameworkfactory.p/frameworkfactory.cc.o
ninja: build stopped: subcommand failed.`
Any ideas on how to fix this issue. If i understood the error I could attempt to troubleshoot but not exactly sure what's wrong.
The text was updated successfully, but these errors were encountered:
Hello, I am trying to follow the guide to install the r2inference library on a jetson nano. For my backend, I am using TensorRT which your documentation said is already included on the Jetson Nano with Jetpack 4.3 which I currently have installed. When I run the ninja build command I get the following error.
ninja: Entering directory
build'[57/95] Compiling C++ object tests/unit/r2i/tensorrt/engine.p/engine.cc.o
FAILED: tests/unit/r2i/tensorrt/engine.p/engine.cc.o
c++ -Itests/unit/r2i/tensorrt/engine.p -Itests/unit/r2i/tensorrt -I../tests/unit/r2i/tensorrt -I. -I.. -I/usr/local/cuda-10.2/targets/aarch64-linux/include -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -fdiagnostics-color=always -D_FILE_OFFSET_BITS=64 -Wall -Winvalid-pch -Wnon-virtual-dtor -std=c++11 -g -pthread -MD -MQ tests/unit/r2i/tensorrt/engine.p/engine.cc.o -MF tests/unit/r2i/tensorrt/engine.p/engine.cc.o.d -o tests/unit/r2i/tensorrt/engine.p/engine.cc.o -c ../tests/unit/r2i/tensorrt/engine.cc
In file included from ../tests/unit/r2i/tensorrt/engine.cc:26:0:
../tests/unit/r2i/tensorrt/mockcudaengine.cc:97:18: error: cannot declare field ‘nvinfer1::{anonymous}::MockExecutionContext::cuda_engine’ to be of abstract type ‘nvinfer1::{anonymous}::MockCudaEngine’
MockCudaEngine cuda_engine;
^~~~~~~~~~~
../tests/unit/r2i/tensorrt/mockcudaengine.cc:22:7: note: because the following virtual functions are pure within ‘nvinfer1::{anonymous}::MockCudaEngine’:
class MockCudaEngine : public ICudaEngine {
^~~~~~~~~~~~~~
In file included from /usr/include/aarch64-linux-gnu/NvInfer.h:53:0,
from ../r2i/tensorrt/model.h:17,
from ../r2i/tensorrt/engine.h:18,
from ../tests/unit/r2i/tensorrt/engine.cc:13:
/usr/include/aarch64-linux-gnu/NvInferRuntime.h:1539:18: note: virtual bool nvinfer1::ICudaEngine::hasImplicitBatchDimension() const
virtual bool hasImplicitBatchDimension() const TRTNOEXCEPT = 0;
^~~~~~~~~~~~~~~~~~~~~~~~~
../tests/unit/r2i/tensorrt/engine.cc: In member function ‘virtual void TEST_GROUP_CppUTestGroupTensorRTEngine::setup()’:
../tests/unit/r2i/tensorrt/engine.cc:91:29: error: invalid new-expression of abstract class type ‘nvinfer1::{anonymous}::MockCudaEngine’
nvinfer1::MockCudaEngine,
^~~~~~~~~~~~~~
[59/95] Compiling C++ object tests/unit/r2i/tensorrt/frameworkfactory.p/frameworkfactory.cc.o
ninja: build stopped: subcommand failed.`
Any ideas on how to fix this issue. If i understood the error I could attempt to troubleshoot but not exactly sure what's wrong.
The text was updated successfully, but these errors were encountered: