bug: Given model is not a onnx.ModelProto.

[sarmientoj24]

Describe the bug

Receiving this error that my model is not an onnx.ModelProto

❯ bentoml serve image_classification_onnx:svc --reload
/home/user/workspace/ws/models/test_image_classification.onnx
2022-10-26T15:42:39+0800 [INFO] [cli] Using the default model signature for onnx ({'run': {'batchable': False}}) for model image_classification_onnx.
Traceback (most recent call last):
  File "/home/user/anaconda3/envs/yolov5/bin/bentoml", line 8, in <module>
    sys.exit(cli())
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/click/core.py", line 1128, in __call__
    return self.main(*args, **kwargs)
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/click/core.py", line 1053, in main
    rv = self.invoke(ctx)
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/click/core.py", line 1659, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/click/core.py", line 1395, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/click/core.py", line 754, in invoke
    return __callback(*args, **kwargs)
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/bentoml_cli/utils.py", line 256, in wrapper
    return func(*args, **kwargs)
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/bentoml_cli/utils.py", line 230, in wrapper
    return_value = func(*args, **kwargs)
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/bentoml_cli/utils.py", line 191, in wrapper
    return func(*args, **kwargs)
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/bentoml_cli/serve.py", line 217, in serve
    ssl_ciphers=ssl_ciphers,
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/simple_di/__init__.py", line 139, in _
    return func(*_inject_args(bind.args), **_inject_kwargs(bind.kwargs))
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/bentoml/serve.py", line 192, in serve_http_development
    svc = load(bento_identifier, working_dir=working_dir)
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/bentoml/_internal/service/loader.py", line 351, in load
    standalone_load=standalone_load,
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/simple_di/__init__.py", line 139, in _
    return func(*_inject_args(bind.args), **_inject_kwargs(bind.kwargs))
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/bentoml/_internal/service/loader.py", line 137, in import_service
    module = importlib.import_module(module_name, package=working_dir)
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1006, in _gcd_import
  File "<frozen importlib._bootstrap>", line 983, in _find_and_load
  File "<frozen importlib._bootstrap>", line 967, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 677, in _load_unlocked
  File "<frozen importlib._bootstrap_external>", line 728, in exec_module
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "/home/user/workspace/ws/scripts/deploy/image_classification_onnx.py", line 32, in <module>
    bentoml.onnx.save_model(f"{BENTO_MODEL}", model_path)
  File "/home/user/anaconda3/envs/yolov5/lib/python3.7/site-packages/bentoml/_internal/frameworks/onnx.py", line 299, in save_model
    raise TypeError(f"Given model ({model}) is not a onnx.ModelProto.")
TypeError: Given model (/home/user/workspace/ws/models/test_image_classification.onnx) is not a onnx.ModelProto.

Netron app

To reproduce

No response

Expected behavior

No response

Environment

bentoml: 1.0.7 environment: Ubuntu 20.04

[sarmientoj24]

[frostming]

bentoml.onnx.save_model(f"{BENTO_MODEL}", model_path)

So what is a model_path? From the naming it looks like a path, then it is incorrect.