Thanks @areusch. I tried your solution but getting this error.
>
> TypeError Traceback (most recent call last)
> <ipython-input-10-f1a6572353c7> in <module>
> 1 from tvm.micro import session
> ----> 2 session.create_local_debug_runtime(graph,graph_mod,ses.context)
>
> ~/tvm_micro_with_debugger/tvm/python/tvm/micro/session.py in
> create_local_debug_runtime(graph_json_str, mod, ctx, dump_root)
> 243 fcreate = get_global_func("tvm.graph_runtime_debug.create")
> 244 return debug_runtime.GraphModuleDebug(
> --> 245 fcreate(graph_json_str, mod, lookup_remote_linked_param,
> *device_type_id),
> 246 [ctx],
> 247 graph_json_str,
>
> ~/tvm_micro_with_debugger/tvm/python/tvm/_ffi/_ctypes/packed_func.py in
> __call__(self, *args)
> 221 """
> 222 temp_args = []
> --> 223 values, tcodes, num_args = _make_tvm_args(args, temp_args)
> 224 ret_val = TVMValue()
> 225 ret_tcode = ctypes.c_int()
>
> ~/tvm_micro_with_debugger/tvm/python/tvm/_ffi/_ctypes/packed_func.py in
> _make_tvm_args(args, temp_args)
> 186 temp_args.append(arg)
> 187 else:
> --> 188 raise TypeError("Don't know how to handle type %s" %
> type(arg))
> 189 return values, type_codes, num_args
> 190
>
> TypeError: Don't know how to handle type <class
> 'tvm.contrib.graph_runtime.GraphModule'>
USE MICRO AND GRAPH DEBUGGER is on in config.cmake while building TVM.
Any suggestions?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/measuring-utvm-inference-time/9064/3)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.apache.org/email/unsubscribe/47dfe6ec6c7e1fa3bc258e4b004fd80742c584fa19c8f044cf5882ad099cedad).
