无法使用 CoreML 工具将 MobileNet V2 PyTorch 转换为 mlmodel

Question

我想使用 coremltools 将 PyTorch MobileNet V2 预训练模型转换为 .mlmodel。这是我的代码：

    import torchvision
    import torch
    import coremltools as ct

    # Load a pre-trained version of MobileNetV2
    torch_model = torchvision.models.mobilenet_v2(pretrained=True)
    # Set the model in evaluation mode.
    torch_model.eval()

    # Trace the model with random data.
    example_input = torch.rand(1, 3, 224, 224) 
    traced_model = torch.jit.trace(torch_model, example_input)
    out = traced_model(example_input)

    # Using image_input in the inputs parameter:
    # Convert to Core ML using the Unified Conversion API.
    model = ct.convert(
        traced_model,
        inputs=[ct.TensorType(shape=example_input.shape)]
     )

    # Save the converted model.
    model.save("mobilenet_v2.mlmodel")

它在 Google Colab 上运行良好，但是当我运行在我的本地计算机 (MacBook) 上运行时，出现以下错误

Converting Frontend ==> MIL Ops: 100%|▉| 390/391 [00:00<00:00, 647.56
Running MIL Common passes:   0%|         | 0/34 [00:00<?, ? passes/s]anaconda3/lib/python3.8/site-packages/coremltools/converters/mil/mil/passes/name_sanitization_utils.py:101: UserWarning: Input, 'input.1', of the source model, has been renamed to 'input_1' in the Core ML model.
  warnings.warn(msg.format(var.name, new_name))
anaconda3/lib/python3.8/site-packages/coremltools/converters/mil/mil/passes/name_sanitization_utils.py:129: UserWarning: Output, '830', of the source model, has been renamed to 'var_830' in the Core ML model.
  warnings.warn(msg.format(var.name, new_name))
Running MIL Common passes: 100%|█| 34/34 [00:00<00:00, 41.87 passes/s
Running MIL Clean up passes: 100%|█| 9/9 [00:00<00:00, 80.15 passes/s
Translating MIL ==> NeuralNetwork Ops: 100%|█| 495/495 [00:00<00:00, 
Traceback (most recent call last):
  File "convert_models.py", line 24, in <module>
    model = ct.convert(
  File "anaconda3/lib/python3.8/site-packages/coremltools/converters/_converters_entry.py", line 352, in convert
    mlmodel = mil_convert(
  File "anaconda3/lib/python3.8/site-packages/coremltools/converters/mil/converter.py", line 183, in mil_convert
    return _mil_convert(model, convert_from, convert_to, ConverterRegistry, MLModel, compute_units, **kwargs)
  File "anaconda3/lib/python3.8/site-packages/coremltools/converters/mil/converter.py", line 231, in _mil_convert
    return modelClass(proto,
  File "anaconda3/lib/python3.8/site-packages/coremltools/models/model.py", line 346, in __init__
    self.__proxy__, self._spec, self._framework_error = _get_proxy_and_spec(
  File "anaconda3/lib/python3.8/site-packages/coremltools/models/model.py", line 123, in _get_proxy_and_spec
    specification = _load_spec(filename)
  File "/anaconda3/lib/python3.8/site-packages/coremltools/models/utils.py", line 210, in load_spec
    raise Exception(
Exception: Unable to load libmodelpackage. Cannot make save spec.

我正在使用以下版本的库：

torchvision: '0.9.0'
手电筒：'1.8.0'
coremltools: '5.2.0'

Answer 1

我通过将 macOS 从 10.14.6 Mojave 更新到 11.5.2 MacOS Big Sur 解决了这个问题。从我创建的 Github issue 中，他们向我解释说我以前的 MacOS 版本不支持 coremltools 版本“5.2”。因此，通过更新您的 macOS 它应该可以正常工作。

无法使用 CoreML 工具将 MobileNet V2 PyTorch 转换为 mlmodel

Couldn't convert MobileNet V2 PyTorch to mlmodel using CoreML tools

pytorch

coremltools

mlmodel

mobilenet