[FRONTEND][ONNX] The onnx frontend cannot import ArgMin correctly: AssertionError: Axis is out of bounds

[coffezhou]

Expected behavior

The onnx frontend should import the model correctly.

Actual behavior

Traceback (most recent call last):
  File "/home/carla/Documents/test_tvm/0312/test_relax1.py", line 13, in <module>
    tvm_model = from_onnx(model, keep_params_in_input=True)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/carla/Documents/tvm/python/tvm/relax/frontend/onnx/onnx_frontend.py", line 3690, in from_onnx
    return g.from_onnx(graph, opset)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/carla/Documents/tvm/python/tvm/relax/frontend/onnx/onnx_frontend.py", line 3321, in from_onnx
    self._construct_nodes(graph)
  File "/home/carla/Documents/tvm/python/tvm/relax/frontend/onnx/onnx_frontend.py", line 3496, in _construct_nodes
    op = self._convert_operator(op_name, inputs, attr, self.opset)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/carla/Documents/tvm/python/tvm/relax/frontend/onnx/onnx_frontend.py", line 3596, in _convert_operator
    sym = op_function(self.bb, inputs, attrs, [self._nodes, self._params])
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/carla/Documents/tvm/python/tvm/relax/frontend/onnx/onnx_frontend.py", line 2688, in _impl_v12
    axis, keepdims = cls._check_attrs(data, attr)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/carla/Documents/tvm/python/tvm/relax/frontend/onnx/onnx_frontend.py", line 2669, in _check_attrs
    assert 0 <= axis < dims_num, "Axis is out of bounds"
           ^^^^^^^^^^^^^^^^^^^^
AssertionError: Axis is out of bounds

Environment

OS: Ubuntu 20.04
TVM: 0.20.dev0 (6e8c367)

Steps to reproduce

This bug can be reproduced by the following code with the model in the attachment. For the model, it can be correctly checked by onnx.checker.check_model. However, the onnx frontend cannot import it.

import tvm
from tvm import relax
from tvm.relax.frontend.onnx import from_onnx

import onnx

model_path = "model.onnx"
model = onnx.load(model_path)

onnx.checker.check_model(model, full_check=True)

tvm_model = from_onnx(model, keep_params_in_input=True)

model.zip

• needs-triage

cc @KJlaccHoeUM9l

[singh20anurag]

Identified the issue. Curious as to why the Expand logic was implemented this way. Filed a PR to fix here.