I run this scripyt
[https://tvm.apache.org/docs/how_to/tune_with_autotvm/tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py](https://tvm.apache.org/docs/how_to/tune_with_autotvm/tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-
my target is apple m1
follow official guide, I successfully tuning my network with autotvm, however
before tuning, the network cost about 160ms, after tuning it only turns a
little fast, 130ms.
so I want to test if autoschedule could speed up my network. However , even run
the modfied offici
when I run atuotvm for my net, I met this warning , does anybody know how to
solve it
---
[Visit
Topic](https://discuss.tvm.apache.org/t/runtimewarning-iterating-over-a-tensor-might-cause-the-trace-to-be-incorrect/11779/1)
to resp
Here is a segment of a Relay graph imported from an ONNX model:
```relay
%73 = nn.batch_flatten(%72) /* ty=Tensor[(16, 1369), float32] */;
%74 = argmax(%73, axis=[1], keepdims=True) /* ty=Tensor[(16, 1), int32] */;
%75 = cast(%74, dtype="int64") /* ty=Tensor[(16, 1), int64] */;
...
%86
