[Bug]: Exception "object is not initialized" when using OpenVINO with torch.nn.functional.max_pool1d

[Thrsu]

OpenVINO Version

2024.0.0-14509-34caeefd078-releases/2024/0

Operating System

Ubuntu 18.04 (LTS)

Device used for inference

CPU

Framework

PyTorch

Model used

Given in the following script

Issue description

When attempting to compile and execute a PyTorch model containing torch.nn.functional.max_pool1d using OpenVINO, an exception is raised with the message "object is not initialized." This occurs during the inference step when calling the compile_model.

Step-by-step reproduction

1. Execute the following script, which reproduces the issue:

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


def compile_torch(model, input_data):
    ov_model = ov.convert_model(model, example_input=input_data)
    ir_path = f"temp_OVIR.xml"
    ov.save_model(ov_model, ir_path, compress_to_fp16=False)
    core = ov.Core()
    model = core.read_model(ir_path)

    compiled_model = core.compile_model(model=model, device_name="CPU")
    output_key = compiled_model.output(0)
    result = compiled_model(input_data)[output_key]
    return result

input_data = torch.randn([1, 2, 9], dtype=torch.float32)

class max_pool1d(Module):
    def forward(self, *args):
        return torch.nn.functional.max_pool1d(args[0],16,stride=2,padding=4,dilation=1,return_indices=False,ceil_mode=True,)

torch_model = max_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
res_ov = compile_torch(trace, input_data)
np.testing.assert_allclose(torch_outputs, res_ov, rtol=1e-3, atol=1e-3)

Relevant log output

RuntimeError: Exception from src/inference/src/cpp/infer_request.cpp:223:
object is not initialized

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]

@Thrsu This problem seem to be caused by CPU plugin. IR that was generated seems correct and GPU can infer it. Reassigning this to CPU team

[yuxu42]

@tiger100256-hu Could you please take a look? Thanks!