At first, many thanks for your answer.
Unfortunately, the experiment environment of mine is more like ‘offline’, which means I could not use RPC or any other remote ways. The core idea of what I want to achieve is to create ARM-used .so files and build a ARM-used executable program of an inference model. So the third way is not much appropriate.
Let me give you a brief summary that what I’ve done.
(In x86, target machine is x86)
- Got the checkpoint files after training my own Mxnet model.
(1.1 Executed the makefile of TVM and NNVM to get shared libraries which would be used)
- Loaded the checkpoint files to create shared library, json and params files as get_started.py in nnvm
- Loaded these so, json and params to a cc file as cpp_deploy.cc described in tvm, and generated a executable program (with libtvm_runtime.so) by using gcc
(in x86, target machine is arm)
While in 1.1, I could not get shared libraries as mentioned above because error occurred during make in tvm while I changed the llvm-config in config.mk and edited CXX in Makefile as the cross-compiler. I’ve tried several times, but still struggled in this step. Could you tell me any details about how to edit config.mk and Makefile in tvm for creating ARM-used shared libraries and json and params files?