[GitHub] [tvm] Thrsu opened a new issue, #15270: [Bug][Realy] Lacking support for parameter dilations in LPPool leads to crash

["Thrsu (via GitHub)" <gi...@apache.org>]

Thrsu opened a new issue, #15270:
URL: https://github.com/apache/tvm/issues/15270

   According to the [official ONNX operators documentation](https://github.com/onnx/onnx/blob/main/docs/Operators.md#LPPool), dilations is one of the attributes of the LPPool operator.
   However, currently, Relay does not support dilations as an attribute yet, which may result in a program crash.
   
   ### Actual behavior
   The crash message is as below:
   ```
   Traceback (most recent call last):
     ......
       irmod, params = relay.frontend.from_onnx(model, shape_dict, opset=18)
     File "/workplace/software/tvm/tvm_/python/tvm/relay/frontend/onnx.py", line 7346, in from_onnx
       mod, params = g.from_onnx(graph, opset)
     File "/workplace/software/tvm/tvm_/python/tvm/relay/frontend/onnx.py", line 6963, in from_onnx
       self._construct_nodes(graph)
     File "/workplace/software/tvm/tvm_/python/tvm/relay/frontend/onnx.py", line 7078, in _construct_nodes
       op = self._convert_operator(op_name, inputs, attr, self.opset)
     File "/workplace/software/tvm/tvm_/python/tvm/relay/frontend/onnx.py", line 7204, in _convert_operator
       sym = convert_map[op_name](inputs, attrs, self._params)
     File "/workplace/software/tvm/tvm_/python/tvm/relay/frontend/onnx.py", line 2024, in _impl_v1
       out = AttrCvt(
     File "/workplace/software/tvm/tvm_/python/tvm/relay/frontend/common.py", line 453, in __call__
       return get_relay_op(op_name)(*inputs, **new_attrs)
   TypeError: avg_pool2d() got an unexpected keyword argument 'dilations'
   ```
   
   ### Environment
   
   TVM version: 0.13.dev0
   ONNX version: 1.14.0
   
   ### Steps to reproduce
   You can download the [onnx model](https://drive.google.com/file/d/1PwH80SsyDAFsgUQWh89JWHt4c33s8CzZ/view?usp=sharing) and use the script below to load it
   ```
   import onnx
   import tvm
   import tvm.relay as relay
   
   shape_dict = {'x': [1, 1, 4, 4]}
   irmod, params = relay.frontend.from_onnx(model, shape_dict, opset=18)
   ```
   
   ### Triage
   * relay:op
   * frontend:onnx
   * needs-triage
   


-- 
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.apache.org

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