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?
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。
本文收集自互联网,转载请注明来源。
如有侵权,请联系 [email protected] 删除。
我来说两句