I tried to go through the example from the TVM website: Example I could compile and run the example on my local machine and it works fine. Then, I would like to compile a new model for NVIDIA Jetson TX2 using the following command:
On my local machine:
tvmc compile --target "llvm -device=arm_cpu -mtriple=aarch64-linux-gnu -mattr=+neon" --output resnet50-v2-7-tvm-tx2.tar resnet50-v2-7.onnx
and run the new model on the Jetson board with the following command:
tvmc run --inputs imagenet_cat.npz --output predictions.npz resnet50-v2-7-tvm-tx2.tar
However, I get the following error:
TVMError:
An error occurred during the execution of TVM.
For more information, please see: Handle TVM Errors — tvm 0.9.dev0 documentation
Check failed: (lib_handle_ != nullptr) is false: Failed to load dynamic shared library /tmp/tmp28aau05_/mod.so /tmp/tmp28aau05_/mod.so: invalid ELF header
I tried to make sure about the “–target” attribute using “GCC - v” and here is the result:
Target: aarch64-linux-gnu
Configured with: …/src/configure -v --with-pkgversion=‘Ubuntu/Linaro 7.5.0-3ubuntu1~18.04’ --with-bugurl=file:///usr/share/doc/gcc-7/README.Bugs --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --prefix=/usr --with-gcc-major-version-only --program-suffix=-7 --program-prefix=aarch64-linux-gnu- --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --libdir=/usr/lib --enable-nls --enable-bootstrap --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --with-default-libstdcxx-abi=new --enable-gnu-unique-object --disable-libquadmath --disable-libquadmath-support --enable-plugin --enable-default-pie --with-system-zlib --enable-multiarch --enable-fix-cortex-a53-843419 --disable-werror --enable-checking=release --build=aarch64-linux-gnu --host=aarch64-linux-gnu --target=aarch64-linux-gnu
gcc version 7.5.0 (Ubuntu/Linaro 7.5.0-3ubuntu1~18.04)
Does anyone know what is the problem? Why I am not able to run the model on the Arm CPU?
Thank you