由 getattr 引起的有趣错误

Question

我尝试同时训练 8 个具有相同结构的 CNN 模型。在批量训练模型后，我需要同步其他 7 个模型中特征提取层的权重。

这是模型：

class GNet(nn.Module):
    def __init__(self, dim_output, dropout=0.5):
        super(GNet, self).__init__()
        self.out_dim = dim_output
        # Load the pretrained AlexNet model
        alexnet = models.alexnet(pretrained=True)

        self.pre_filtering = nn.Sequential(
            alexnet.features[:4]
        )

        # Set requires_grad to False for all parameters in the pre_filtering network
        for param in self.pre_filtering.parameters():
            param.requires_grad = False

        # construct the feature extractor
        # every intermediate feature will be fed to the feature extractor

        # res: 25 x 25
        self.feat_ex1 = nn.Conv2d(192, 128, kernel_size=3, stride=1)

        # res: 25 x 25
        self.feat_ex2 = nn.Sequential(
            nn.BatchNorm2d(128),
            nn.Dropout(p=dropout),
            nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1)
        )

        # res: 25 x 25
        self.feat_ex3 = nn.Sequential(
            nn.BatchNorm2d(128),
            nn.Dropout(p=dropout),
            nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1)
        )

        # res: 13 x 13
        self.feat_ex4 = nn.Sequential(
            nn.MaxPool2d(kernel_size=3, stride=2, padding=1),
            nn.BatchNorm2d(128),
            nn.Dropout(p=dropout),
            nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1)
        )

        # res: 13 x 13
        self.feat_ex5 = nn.Sequential(
            nn.BatchNorm2d(128),
            nn.Dropout(p=dropout),
            nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1)
        )

        # res: 13 x 13
        self.feat_ex6 = nn.Sequential(
            nn.BatchNorm2d(128),
            nn.Dropout(p=dropout),
            nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1)
        )

        # res: 13 x 13
        self.feat_ex7 = nn.Sequential(
            nn.BatchNorm2d(128),
            nn.Dropout(p=dropout),
            nn.Conv2d(128, 64, kernel_size=3, stride=1, padding=1)
        )

        # define the flexible pooling field of each layer
        # use a full convolution layer here to perform flexible pooling
        self.fpf13 = nn.Conv2d(in_channels=448, out_channels=448, kernel_size=13, groups=448)
        self.fpf25 = nn.Conv2d(in_channels=384, out_channels=384, kernel_size=25, groups=384)
        self.linears = {}
        for i in range(self.out_dim):
            self.linears[f'linear_{i+1}'] = nn.Linear(832, 1)

        self.LogTanh = LogTanh()
        self.flatten = nn.Flatten()

这是同步权重的功能：

def sync_weights(models, current_sub, sync_seqs):
    for sub in range(1, 9):
        if sub != current_sub:
            # Synchronize the specified layers
            with torch.no_grad():
                for seq_name in sync_seqs:
                    reference_layer = getattr(models[current_sub], seq_name)[2]
                    layer = getattr(models[sub], seq_name)[2]
                    layer.weight.data = reference_layer.weight.data.clone()
                    if layer.bias is not None:
                        layer.bias.data = reference_layer.bias.data.clone()

然后出现错误：

'Conv2d' object is not iterable

这意味着 getattr() 返回一个 Conv2D 对象。 但如果我删除[2]：

def sync_weights(models, current_sub, sync_seqs):
    for sub in range(1, 9):
        if sub != current_sub:
            # Synchronize the specified layers
            with torch.no_grad():
                for seq_name in sync_seqs:
                    reference_layer = getattr(models[current_sub], seq_name)
                    layer = getattr(models[sub], seq_name)
                    layer.weight.data = reference_layer.weight.data.clone()
                    if layer.bias is not None:
                        layer.bias.data = reference_layer.bias.data.clone()

我收到另一个错误：

'Sequential' object has no attribute 'weight'

这意味着 getattr() 返回一个 Sequential。但之前它返回一个 Conv2D 对象。 有人对这个有了解吗？ 供您参考，sync_weights 中传递的sync_seqs 参数是：

sync_seqs = [
    'feat_ex1',
    'feat_ex2',
    'feat_ex3',
    'feat_ex4',
    'feat_ex5',
    'feat_ex6',
    'feat_ex7'
]

Answer 1

在这两种情况下，

getattr

都会返回一个

Sequential

，而它又包含一堆对象。在第二种情况下，您直接将

Sequential

分配给变量，因此

reference_layer

最终包含

Sequential

。

但是，在第一种情况下，您并没有执行直接分配。您将获取

Sequential

对象，然后使用

[2]

对其进行索引。这意味着

reference_value

包含

Sequential

中的第三项，这是一个

Conv2d

对象。

举一个更简单的例子。假设我有一个

ListContainer

类，除了保存列表之外什么也不做。然后，我可以按如下方式重新创建您的示例，其中

test1

对应于您的第一个测试用例，反之亦然：

class ListContainer:
    def __init__(self, list_items):
        self.list_items = list_items

letters = ["a", "b", "c"]
container = ListContainer(letters)

test1 = getattr(container, "list_items")[0]
test2 = getattr(container, "list_items")

print(type(test1)) # <class 'str'>
print(type(test2)) # <class 'list'>

在这两个测试中，

getattr

本身都返回一个列表 - 但在第二个测试中，我们在获得该列表后对其进行一些操作，因此 test2 最终成为一个字符串。