深度学习：UserWarning: The parameter ‘pretrained‘ is deprecated since 0.13..解决办法

深度学习：UserWarning: The parameter ‘pretrained’ is deprecated since 0.13 and may be removed in the future, please use ‘weights’ instead. 解决办法

1 报错警告：

pytorch版本：0.14.1
在利用pytorch中的预训练模型时，如resnet18

import torchvision.models as models
pretrained_model = models.resnet18(pretrained=True)

会提示警告：

UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  f"The parameter '{pretrained_param}' is deprecated since 0.13 and may be removed in the future, "

看出给出的原因是在0.13版本后，开始使用weights参数。

2 处理方法：

接下来为处理这个问题的方法，不同的预训练模型方法适用 以model.resnet18()为例

• 首先点击models.resnet18()函数，进入函数内部，可以看到如下内容

  @handle_legacy_interface(weights=("pretrained", ResNet18_Weights.IMAGENET1K_V1))
def resnet18(*, weights: Optional[ResNet18_Weights] = None, progress: bool = True, **kwargs: Any) -> ResNet:
    """ResNet-18 from `Deep Residual Learning for Image Recognition `__.

    Args:
        weights (:class:`~torchvision.models.ResNet18_Weights`, optional): The
            pretrained weights to use. See
            :class:`~torchvision.models.ResNet18_Weights` below for
            more details, and possible values. By default, no pre-trained
            weights are used.
        progress (bool, optional): If True, displays a progress bar of the
            download to stderr. Default is True.
        **kwargs: parameters passed to the ``torchvision.models.resnet.ResNet``
            base class. Please refer to the `source code
            `_
            for more details about this class.

    .. autoclass:: torchvision.models.ResNet18_Weights
        :members:
    """
    weights = ResNet18_Weights.verify(weights)

    return _resnet(BasicBlock, [2, 2, 2, 2], weights, progress, **kwargs)

• 首先看到第一行weights=("pretrained", ResNet18_Weights.IMAGENET1K_V1)，所以这个还是可以用的，相当于利用了ResNet18_Weights.IMAGENET1K_V1参数。然后看第二行的这个weights函数接受的ResNet18_Weights,再次进入内部，可以看到如下：

class ResNet18_Weights(WeightsEnum):
    IMAGENET1K_V1 = Weights(
        url="https://download.pytorch.org/models/resnet18-f37072fd.pth",
        transforms=partial(ImageClassification, crop_size=224),
        meta={
            **_COMMON_META,
            "num_params": 11689512,
            "recipe": "https://github.com/pytorch/vision/tree/main/references/classification#resnet",
            "_metrics": {
                "ImageNet-1K": {
                    "acc@1": 69.758,
                    "acc@5": 89.078,
                }
            },
            "_docs": """These weights reproduce closely the results of the paper using a simple training recipe.""",
        },
    )
    DEFAULT = IMAGENET1K_V1

这个是选择的参数，其他的预训练模型可以有多个版本，如下面ResNet50_Weights, 可以根据自己需求选择需要的。

• 上面的函数已经给出了调用方法Args: weights (:class:~torchvision.models.ResNet18_Weights, optional)
  所以直接

pretrained_model = models.resnet18(models.ResNet18_Weights.IMAGENET1K_V1)

也可以

pretrained_model = models.resnet18(models.ResNet18_Weights.DEFAULT)

这两个是一样的。

3.总结

在版本更新之后可能会有些变化，有些函数调用方式的变化可以直接通过函数内部查看然后修改，重点是修改思路解决相同类似的问题。