如何从pytorch模块中获取子模块的序列？

Question

对于pytorch 模块，我想我可以使用.named_children、.named_modules等来获取子模块的列表。不过，我想名单不是按顺序排列的，对吧？举个例子：

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']

给出了.named_children()在上述模型中的阶数为蒸馏器、pre_classifier、分类器和退出。但是，如果检查代码，很明显，dropout发生在classifier之前。那么，如何获得这些子模块的顺序呢？

Answer 1

在Pytorch中，print(model)或.named_children()等的结果是根据它们在模型类的__init__中声明的顺序列出的。

案例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']

案例2

更改构造函数中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的classifier在dropout之前打印的原因：

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)

尽管如此，您可以使用.modules()等来处理模型的子模块，但是它们只会按照在__init__中声明的顺序列出。如果只想打印基于forward方法的结构，可以尝试使用火把-摘要。