[Bug]: Expected numpy type or openvino.runtime.Type, got <class 'NoneType'>.

[jikechao]

OpenVINO Version

2023.1.0-12185-9e6b00e51cd-releases/2023/1

Operating System

Ubuntu 18.04 (LTS)

Device used for inference

CPU

Framework

PyTorch

Model used

No response

Issue description

OpenVINO converts PyTorch model will crash when input_data is torch.int16.
It triggered an assertion error and reported "Got incorrect format of input types. Expected numpy type or openvino.runtime.Type, got <class 'NoneType'>."

As a comparison, torch.int8 and torch.int32 can be identified and the model can be converted into OV IR correctly.

Step-by-step reproduction

import torch
import openvino as ov

torch_model = torch.nn.ReLU6(inplace=False,).eval()

input_data = torch.randint(1, 100, [10, 15, 2], dtype=torch.int16)  # only torch.int16 can trigger this crash.
trace = torch.jit.trace(torch_model, input_data)
trace = torch.jit.freeze(trace)
input_shapes = input_data.shape
print(input_shapes)

ov_model = ov.convert_model(trace, example_input=input_data)
ir_path = f"_temp_model/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]

Relevant log output

Traceback (most recent call last):
  File "test_demo.py", line 12, 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 76, in moc_pipeline
    argv.placeholder_shapes, argv.placeholder_data_types = convert_params_lists_to_dicts(
  File "C:\software\conda\envs\torch\lib\site-packages\openvino\tools\ovc\moc_frontend\extractor.py", line 407, in convert_params_lists_to_dicts
    assert isinstance(node_type, (type, np.dtype, Type)), "Got incorrect format of input types. " \
AssertionError: Got incorrect format of input types. Expected numpy type or openvino.runtime.Type, got <class 'NoneType'>.

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 very much for your findings. This issue was caused because int16 was omitted from dictionary.

[jikechao]

@mvafin Thanks for your PR.