Hi @areusch.
I have replicated the same step as in your last reply and I am using the latest
tvm repo. However, I am still getting the same error as above when using the
debug runtime. Could you please help me with this error?
RPCError: Traceback (most recent call last):
14: TVMFun
Thanks @areusch . I finally got this working.
However, right now I am giving the parameter using set_input(**params) to the
runtime. I tried using --link params while building, but then I get RPC session
timeout error @ mod.run()
---
[Visit
Topic](https://discuss.tvm.apache.org/t/measuri
@aakah18151 sorry for the delay. hm, it seems to me like you might be somehow
allocating too much memory for your device in the runtime. you could be
overwriting the stack when you set_input. unfortunately we don't have a good
way to detect this at the moment, though Zephyr should provide you
Hey @areusch It seems like I am unable to set the lowed model parameters in to
graph_mod, which is why I am getting this error. I am able to run this
sine_model https://tvm.apache.org/docs/tutorials/micro/micro_tflite.html using
similar steps but when passing the lowered parameters from my mo
@areusch
I tried to reduce the model size, however I am getting this error
> SessionTerminatedErrorTraceback (most recent call last)
> in
> 6
> 7 # Set the model parameters using the lowered parameters produced
> by `relay.build`.
> > 8 graph_mod
@aakah18151 `tests/micro/qemu/test_zephyr.py` should work on STM32f746xx board.
that should test sine_model.tflite. You can run it with:
`python tests/micro/qemu/test_zephyr.py --microtvm-platforms=stm32f746xx`
is this the tutorial you're trying?
---
[Visit
Topic](https://discuss.tvm.apa
Thanks @areusch . Unfortunately increasing the memory size did not work. The
other thing I tried is to replace my
/tvm/tests/micro/qemu/zephyr-runtime/src/main.c with the "main.c" from
blog-post eval which did not work either. Is there a working microTVM code
apart from sine model on the same
@aakah18151 we don't quite have good enough debugging for this right now for me
to be certain, but based on your stack trace and that it's inside
>` [bt] (6)
>/tvm_micro_with_debugger/tvm/build/libtvm.so(tvm::runtime::RPCClientSession::AllocDataSpace(DLContext,
> unsigned long, unsigned lon
@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)
> in
> 2 with tvm.micro.Session(binary=micro_binary, flasher=flashe
Thanks @areusch This works. :slight_smile:
---
[Visit
Topic](https://discuss.tvm.apache.org/t/measuring-utvm-inference-time/9064/4)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.apache.org/ema
Thanks @areusch. I tried your solution but getting this error.
>
> TypeError Traceback (most recent call last)
> in
> 1 from tvm.micro import session
> > 2 session.create_local_debug_runtime(graph,graph_mod,ses.context)
>
> ~/tvm_micro_with_debugger/t
11 matches
Mail list logo
