[GitHub] [tvm] Lyken17 edited a comment on pull request #8633: [Runtime] Add graph_executor get_input_index API.

[GitBox <gi...@apache.org>]

Lyken17 edited a comment on pull request #8633:
URL: https://github.com/apache/tvm/pull/8633#issuecomment-901834168


   Hi there,
   
   It seems this commit introduces bugs when tunning models on raspberry pis. When I follow the example on [auto-scheduler-tune-network-arm](https://tvm.apache.org/docs/tutorials/auto_scheduler/tune_network_arm.html#sphx-glr-tutorials-auto-scheduler-tune-network-arm-py), I got following errors 
   
   ```
   Upload...
   Traceback (most recent call last):
     File "pi_bench/tune_mbv2.py", line 143, in <module>
       tune_and_evaluate()
     File "pi_bench/tune_mbv2.py", line 126, in tune_and_evaluate
       module = graph_executor.GraphModule(rlib["default"](dev))
     File "/home/ligeng/Workspace/tvm/python/tvm/contrib/graph_executor.py", line 160, in __init__
       self._get_input_index = module["get_input_index"]
     File "/home/ligeng/Workspace/tvm/python/tvm/runtime/module.py", line 107, in __getitem__
       return self.get_function(name)
     File "/home/ligeng/Workspace/tvm/python/tvm/runtime/module.py", line 91, in get_function
       raise AttributeError("Module has no function '%s'" % name)
   AttributeError: Module has no function 'get_input_index'
   ```
   
   After I comment the 160th line in `graph_executor`, the tutorial runs without problem.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org