[Bug]: Failed to create convolution_backward_data::primitive_desc

[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

For the given PyTorch model in the following script, OpenVINO will crash at core.compile_model. Crash message is showns below.

Step-by-step reproduction

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)
    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.randint(1, 10, [1, 2, 4, 5], dtype=torch.int64)
weight = torch.randint(1, 10, [2, 2, 2, 3], dtype=torch.int64)
bias = torch.randint(1, 10, [4], dtype=torch.int64)


class conv_transpose2d(Module):
    def forward(self, *args):
        return torch.nn.functional.conv_transpose2d(args[0], weight, bias, groups=2)

torch_model = conv_transpose2d().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

Traceback (most recent call last):
  File "test.py", line 35, in <module>
    res_ov = compile_torch(trace, input_data)
  File "test.py", line 14, in compile_torch
    compiled_model = core.compile_model(model=model, device_name='CPU')
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\runtime\ie_api.py", line 543, in compile_model
    super().compile_model(model, device_name, {} if config is None else config),
Exception from src/inference/src/core.cpp:113:
[ GENERAL_ERROR ]  AssertionError !getSupportedPrimitiveDescriptors().empty()Supported primitive descriptors list is empty for node: aten::_convolution/GroupConvolutionBackpropData type: Deconvolution

>>>>>>>>>>>>>>>>>>>Bug Info:   AssertionError !getSupportedPrimitiveDescriptors.emptySupported primitive descriptors list is empty for node: aten::_convolution/GroupConvolutionBackpropData type: Deconvolution

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.

[dmitry-gorokhov]

@jikechao Thank you for reporting the issue.
There is a bug on CPU plugin level. We will take a look.

[github-actions]

This issue will be closed in a week because of 9 months of no activity.

[github-actions]

This issue was closed because it has been stalled for 9 months with no activity.