Measuring uTVM inference time

@areusch I am trying to run a different tflite model from the tutorial given by @tgall_foo . I am getting error while running.

> RPCError                                  Traceback (most recent call last)
> <ipython-input-55-f4fd2e93ed4c> in <module>
>       2 with tvm.micro.Session(binary=micro_binary, flasher=flasher) as session:
>       3     graph_mod = tvm.micro.create_local_graph_runtime(
> ----> 4         graph, session.get_system_lib(), session.context
>       5     )
>       6 
> 
> ~/tvm_micro_with_debugger/tvm/python/tvm/micro/session.py in create_local_graph_runtime(graph_json_str, mod, ctx)
>     214     fcreate = get_global_func("tvm.graph_runtime.create")
>     215     return graph_runtime.GraphModule(
> --> 216         fcreate(graph_json_str, mod, lookup_remote_linked_param, *device_type_id)
>     217     )
>     218 
> 
> ~/tvm_micro_with_debugger/tvm/python/tvm/_ffi/_ctypes/packed_func.py in __call__(self, *args)
>     235             != 0
>     236         ):
> --> 237             raise get_last_ffi_error()
>     238         _ = temp_args
>     239         _ = args
> 
> RPCError: Traceback (most recent call last):
>   [bt] (8) /tvm_micro_with_debugger/tvm/build/libtvm.so(tvm::runtime::NDArray::Empty(std::vector<long, std::allocator<long> >, DLDataType, DLContext)+0x1ff) [0x7f7abd9752bf]
>   [bt] (7) /tvm_micro_with_debugger/tvm/build/libtvm.so(tvm::runtime::RPCDeviceAPI::AllocDataSpace(DLContext, unsigned long, unsigned long, DLDataType)+0x53a) [0x7f7abd9a93aa]
>   [bt] (6) /tvm_micro_with_debugger/tvm/build/libtvm.so(tvm::runtime::RPCClientSession::AllocDataSpace(DLContext, unsigned long, unsigned long, DLDataType)+0x2b7) [0x7f7abd9b11b7]
>   [bt] (5) /tvm_micro_with_debugger/tvm/build/libtvm.so(+0x126f1f0) [0x7f7abd9ad1f0]
>   [bt] (4) /tvm_micro_with_debugger/tvm/build/libtvm.so(tvm::runtime::RPCEndpoint::HandleUntilReturnEvent(bool, std::function<void (tvm::runtime::TVMArgs)>)+0x243) [0x7f7abd9ace33]
>   [bt] (3) /tvm_micro_with_debugger/tvm/build/libtvm.so(tvm::runtime::RPCEndpoint::EventHandler::HandleNextEvent(bool, bool, std::function<void (tvm::runtime::TVMArgs)>)+0xc6) [0x7f7abd9b69d6]
>   [bt] (2) /tvm_micro_with_debugger/tvm/build/libtvm.so(tvm::runtime::RPCEndpoint::EventHandler::HandleProcessPacket(std::function<void (tvm::runtime::TVMArgs)>)+0x126) [0x7f7abd9b67c6]
>   [bt] (1) /tvm_micro_with_debugger/tvm/build/libtvm.so(tvm::runtime::RPCEndpoint::EventHandler::HandleReturn(tvm::runtime::RPCCode, std::function<void (tvm::runtime::TVMArgs)>)+0x13f) [0x7f7abd9b5bef]
>   [bt] (0) /tvm_micro_with_debugger/tvm/build/libtvm.so(+0x126cec2) [0x7f7abd9aaec2]
>   File "/tvm_micro_with_debugger/tvm/src/runtime/rpc/rpc_endpoint.cc", line 378
> RPCError: Error caught from RPC call:

How to fix this. In general is there anything special that need to be done to run some other model using uTVM apart from the standard sine_model.