onnx: step = 1 is currently not supported

1. 在yolov5s的pytorch模型转换onnx模型时报如下错误:

RuntimeError: step!=1 is currently not supported
原因主要是低版本的opset不支持切片操作导致的;

把模型转换的代码改成如下所示即可,即使用版本11以上的opset:

torch.onnx.export(model, img, "xxx.onnx", verbose=True,opset_version=11,export_params=True)

我这个onnx不支持这个参数;

解决方法是:

class OnnxExportApiArgs:
    """
    configuration for torch onnx export api invocation
    """

    def __init__(self, opset_version: int = 11, input_names: List[str] = ['inpout'], output_names: List[str] =  ['output']):
        """
        Refer torch documentation https://pytorch.org/docs/1.7.1/onnx.html?highlight=onnx%20export#torch.onnx.export
        :param opset_version: onnx opset version to use to export the model
        :param input_names:  names to assign to the input nodes of the onnx graph, in order
        :param output_names: names to assign to the output nodes of the graph, in order
        """
        self.opset_version = opset_version
        self.input_names = input_names
        self.output_names = output_names

    @property
    def kwargs(self):
        """
        formats all override options into kwarg format to appended to onnx export call
        """
        return {'opset_version': self.opset_version,
                'input_names': self.input_names,
                'output_names': self.output_names}

调用:

if onnx_export_args is None:
    onnx_export_args = OnnxExportApiArgs()

torch.onnx.export(model, dummy_input, temp_file, enable_onnx_checker=False,**onnx_export_args.kwargs)


2. 解决该问题后可能会继续出现如下错误:

RuntimeError: Exporting the operator silu to ONNX opset version 11 is not supported. Please open a bug to request ONNX export support for the missing operator.
这是因为onnx与pytorch一些方法不兼容导致的,onnx不支持silu,把激活函数换一种写法即可。

解决方法如下:

pytorch的激活函数源码位置:X:\anaconda3\envs\python3.7\Lib\sitepackages\torch\nn\modules\activation.py(此处结合自己的anaconda实际安装位置来更改)。

修改成如下:

class SiLU(Module):
 
    __constants__ = ['inplace']
    inplace: bool
 
    def __init__(self, inplace: bool = False):
        super(SiLU, self).__init__()
        self.inplace = inplace
 
    def forward(self, input: Tensor) -> Tensor:
        # ------------------------------------- #
        # 把F.silu替换掉,修改后如下
        return input * torch.sigmoid(input)
 
        #原来的代码
        #return F.silu(input, inplace=self.inplace)


————————————————
版权声明:本文为CSDN博主「小码乔」的原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处链接及本声明。
原文链接:https://blog.csdn.net/weixin_37889356/article/details/121671974

猜你喜欢

转载自blog.csdn.net/jacke121/article/details/126615988