coffezhou opened a new issue, #17877:
URL: https://github.com/apache/tvm/issues/17877
### Expected behavior
The onnx frontend should import the model correctly.
### Actual behavior
When importing the onnx model, tvm crashes as follows:
```c
Traceback (most recent call last):
File "/home/carla/Documents/test/test.py", line 189, in <module>
main()
File "/home/carla/Documents/test/test.py", line 178, in main
check_correctness(onnx_model)
File "/home/carla/Documents/test/test.py", line 104, in check_correctness
tvm_model = from_onnx(model, opset=opset, 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 1164, in _impl_v1
const_dtype = x.struct_info.dtype
^
UnboundLocalError: cannot access local variable 'x' where it is not
associated with a value
[13:05:02] /home/carla/Documents/tvm/src/relax/ir/block_builder.cc:64:
Warning: BlockBuilder destroyed with remaining blocks!
```
The FastGelu code in the onnx frontend is as follows. The inputs[1]
represents the bias, while bias is optional. So, if the statement "if
inputs[1]" is false, the variable ''x' is not defined.
### Environment
OS: Ubuntu 20.04
TVM: 0.21.dev0(c00f52a70)
### Steps to reproduce
This bug can be reproduced by the following code with the model in the
attachment. As shown in the code, the model can be executed by onnxruntime.
```python
import sys
import numpy as np
import onnx
import onnxruntime
import tvm
from tvm import relax
from tvm.relax.frontend.onnx import from_onnx
import pickle
def main():
onnx_model = onnx.load("a344.onnx")
with open("inputs.pkl", "rb") as fp:
inputs = pickle.load(fp)
try:
ort_session = onnxruntime.InferenceSession(
onnx_model.SerializeToString(),
providers=["CPUExecutionProvider"]
)
ort_output = ort_session.run([], inputs)
except Exception as e:
print(e)
sys.exit(1)
# Convert the onnx model into relax through the onnx importer.
tvm_model = from_onnx(onnx_model, keep_params_in_input=True)
if __name__ == "__main__":
main()
```
[testcase.zip](https://github.com/user-attachments/files/19845512/testcase.zip)
### Triage
* 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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
