如何从pytorch模块获取子模块序列？

麦队

对于pytorch模块，我想我可以使用.named_children，.named_modules等来获得子模块的列表。但是，我想这个列表不是按顺序给出的，对吧？一个例子：

In [19]: import transformers

In [20]: model = transformers.DistilBertForSequenceClassification.from_pretrained('distilb
    ...: ert-base-cased')

In [21]: [name for name, _ in model.named_children()]
Out[21]: ['distilbert', 'pre_classifier', 'classifier', 'dropout']

.named_children()上面模型中的顺序为distilbert，pre_classifier，classifier和dropout。但是，如果您检查代码，则很明显，这dropout发生在之前classifier。那么，如何获得这些子模块的顺序？

哈西特

在Pytorch中，print(model)或.named_children()等等的结果根据在__init__模型类中声明的顺序列出，例如

情况1

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)
        self.conv2_drop = nn.Dropout2d()

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, p=0.6)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

model = Model()
print(model)
[name for name, _ in model.named_children()]
# output
['conv1', 'conv2', 'fc1', 'fc2', 'conv2_drop']

情况二

在构造函数中更改了fc1和fc2层的顺序。

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.fc2 = nn.Linear(50, 10)
        self.fc1 = nn.Linear(320, 50)
        self.conv2_drop = nn.Dropout2d()

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, p=0.6)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

model = Model()
print(model)
[name for name, _ in model.named_children()]
# output
['conv1', 'conv2', 'fc2', 'fc1', 'conv2_drop']

这就是为什么在构造函数中声明classifier之前dropout将其打印出来的原因：

class DistilBertForSequenceClassification(DistilBertPreTrainedModel):
        ...
        self.distilbert = DistilBertModel(config)
        self.pre_classifier = nn.Linear(config.dim, config.dim)
        self.classifier = nn.Linear(config.dim, config.num_labels)
        self.dropout = nn.Dropout(config.seq_classif_dropout)

不过，您可以使用.modules()等来处理模型的子模块，但它们只会按在中声明的顺序列出__init__。如果只想基于forward方法打印结构，则可以尝试使用pytorch-summary。