[Bug]: Argument element types do not match (input arg element type: i64, arg_pad element type: f32)

[jikechao]

OpenVINO Version

openvino-nightly 2023.2.0.dev20231101

Operating System

Ubuntu 18.04 (LTS)

Device used for inference

CPU

Framework

PyTorch

Model used

Given in the following script

Issue description

If the input type of avg_pool1d operator is set as 'torch.int64', PyTorch can run well. However, when converting the model to OpenVINO, it crashed. The crash message is shown below.

Step-by-step reproduction

import torch
from torch.nn import Module
import openvino as ov


class avg_pool1d(Module):
    def forward(self, *args):
        return torch.nn.functional.avg_pool1d(args[0], kernel_size=2)


input_data = torch.randint(1, 10, [1, 2, 3], dtype=torch.int64)
torch_model = avg_pool1d().float().eval()
torch_outputs = torch_model(input_data).cpu().numpy()

trace = torch.jit.trace(torch_model, input_data)
trace = torch.jit.freeze(trace)

input_shapes = input_data.shape
ov_model = ov.convert_model(trace, example_input=input_data)

Relevant log output

Traceback (most recent call last):
  File "test.py", line 19, in <module>
    ov_model = ov.convert_model(trace, example_input=input_data)
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\convert.py", line 101, in convert_model
    ov_model, _ = _convert(cli_parser, params, True)
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\convert_impl.py", line 524, in _convert
    raise e
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\convert_impl.py", line 476, in _convert
    ov_model = driver(argv, {"conversion_parameters": non_default_params})
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\convert_impl.py", line 226, in driver
    ov_model = moc_emit_ir(prepare_ir(argv), argv)
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\convert_impl.py", line 172, in prepare_ir
    ov_model = moc_pipeline(argv, moc_front_end)
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\moc_frontend\pipeline.py", line 247, in moc_pipeline
    ov_model = moc_front_end.convert(input_model)
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\frontend\frontend.py", line 18, in convert
    converted_model = super().convert(model)
openvino._pyopenvino.OpConversionFailure: Check 'is_conversion_successful' failed at src/frontends/pytorch/src/frontend.cpp:140:
FrontEnd API failed with OpConversionFailure:
Model wasn't fully converted. Failed operations detailed log:
-- aten::avg_pool1d with a message:
Exception happened during conversion of operation aten::avg_pool1d with schema aten::avg_pool1d(Tensor self, int[1] kernel_size, int[1] stride=[], int[1] padding=[0], bool ceil_mode=False, bool count_include_pad=True) -> Tensor
Check 'element::Type::merge(result_et, result_et, arg_pad_element_type)' failed at src/core/src/op/util/pad_base.cpp:80:
While validating node 'opset1::Pad Pad_18 (1[0]:i64[?,?,?], aten::avg_pool1d/Concat[0]:i32[3], aten::avg_pool1d/Concat[0]:i32[3], aten::avg_pool1d/Constant[0]:f32[]) -> (dynamic[...])' with friendly_name 'Pad_18':
Argument element types do not match (input arg element type: i64, arg_pad element type: f32).

Summary:
-- Conversion is failed for: aten::avg_pool1d

Issue submission checklist

• I'm reporting an issue. It's not a question.
• I checked the problem with the documentation, FAQ, open issues, Stack Overflow, etc., and have not found a solution.
• There is reproducer code and related data files such as images, videos, models, etc.

[mvafin]

Thank you for the ticket. PR #21139 should fix the issue.