```
Traceback (most recent call last):
File "compile_onnx.py", line 147, in <module>
graph, lib, params=
tune_and_evaluate(tuning_option,mod,params,input_shape,target=target)
File "compile_onnx.py", line 96, in tune_and_evaluate
# tune_graph(mod["main"], data_shape, log_file, graph_opt_sch_file, False)
# turn graph
File "compile_onnx.py", line 80, in tune_graph
executor.benchmark_layout_transform(min_exec_num=2000)
File
"/home/qqai-cv/yexing/my_python/lib/python3.6/site-packages/tvm/autotvm/graph_tuner/base_graph_tuner.py",
line 431, in benchmark_layout_transform
self._iterate_layout_transform(_fetch_args_callback)
File
"/home/qqai-cv/yexing/my_python/lib/python3.6/site-packages/tvm/autotvm/graph_tuner/base_graph_tuner.py",
line 269, in _iterate_layout_transform
i_topi_op = in_node_entry["topi_op"][0]
KeyError: 'topi_op'
```
---
[Visit
Topic](https://discuss.tvm.ai/t/autotvm-tuning-fails-for-an-onnx-network-on-x86-cpu-in-tune-graph-keyerror-topi-op/6813/1)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ai/email/unsubscribe/2f3c4869fca5dd6d9f03d6000d62ea89b26397d788f288b9f33614ac5b9fac96).
