博客

建立了模型对象后直接打印模型就会输出它的比较完整的层

net = Net()

print(net)

net模型还没有使用sequential结构

from torch import nn
from torch.nn import functional as F
from torchvision import models


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()

        self.fc1 = nn.Linear(28 * 28, 256)
        self.fc2 = nn.Linear(256, 64)
        self.fc3 = nn.Linear(64, 10)

    def forward(self, x):
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)

        return x

print('net--------------------------')
net = Net()
print(net)

print('vgg--------------------------')
vgg = models.vgg19(pretrained=True).features
print(vgg)

model._modules.items()

可以遍历输出每一层

from torch import nn
from torch.nn import functional as F
from torchvision import models


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()

        self.fc1 = nn.Linear(28 * 28, 256)
        self.fc2 = nn.Linear(256, 64)
        self.fc3 = nn.Linear(64, 10)

    def forward(self, x):
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)

        return x


net = Net()
vgg = models.vgg19(pretrained=True).features


print('net--------------------------')
for i in net._modules.items():
    print(i)

print()

print('vgg--------------------------')
for i in vgg._modules.items():
    print(i)

model.modules() & model.children()

modules()与children()都是返回网络模型里的组成元素，但是children()返回的是最外层的元素，modules()返回的是所有的元素，包括不同级别的子元素。

用list举例就是

model.modules()

from torch import nn
from torch.nn import functional as F
from torchvision import models


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()

        self.fc1 = nn.Linear(28 * 28, 256)
        self.fc2 = nn.Linear(256, 64)
        self.fc3 = nn.Linear(64, 10)

    def forward(self, x):
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)

        return x


net = Net()
vgg = models.vgg19(pretrained=True).features


print('net--------------------------')
for i in net.modules():
    print(i)

print()

print('vgg--------------------------')
for i in vgg.modules():
    print(i)

model.children()

from torch import nn
from torch.nn import functional as F
from torchvision import models


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()

        self.fc1 = nn.Linear(28 * 28, 256)
        self.fc2 = nn.Linear(256, 64)
        self.fc3 = nn.Linear(64, 10)

    def forward(self, x):
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)

        return x


net = Net()
vgg = models.vgg19(pretrained=True).features


print('net--------------------------')
for i in net.children():
    print(i)

print()

print('vgg--------------------------')
for i in vgg.children():
    print(i)

在这里和model.modules()的结果是一样的

它们的区别展现在例如网络结构有嵌套的时候

class Net4(torch.nn.Module):
    def __init__(self):
        super(Net4, self).__init__()
        self.conv = torch.nn.Sequential(
            OrderedDict(
                [
                    ("conv1", torch.nn.Conv2d(3, 32, 3, 1, 1)),
                    ("relu1", torch.nn.ReLU()),
                    ("pool1", torch.nn.MaxPool2d(2))
                ]
            ))

        self.dense = torch.nn.Sequential(
            OrderedDict([
                ("dense1", torch.nn.Linear(32 * 3 * 3, 128)),
                ("relu2", torch.nn.ReLU()),
                ("dense2", torch.nn.Linear(128, 10))
            ])
        )

    def forward(self, x):
        conv_out = self.conv1(x)
        res = conv_out.view(conv_out.size(0), -1)
        out = self.dense(res)
        return out


print("Method 4:")
model4 = Net4()
# modules方法将整个模型的所有构成（包括包装层Sequential、单独的层、自定义层等）由浅入深依次遍历出来，直到最深处的单层
for i in model4.modules():
    print(i)
    print('==============================')
print('=============华丽分割线=================')
# named_modules()同上，但是返回的每一个元素是一个元组，第一个元素是名称，第二个元素才是层对象本身。
for i in model4.named_modules():
    print(i)
    print('==============================')
'''
离模型最近即最浅处，就是模型本身
Net4(
  (conv): Sequential(
    (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (relu1): ReLU()
    (pool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (dense): Sequential(
    (dense1): Linear(in_features=288, out_features=128, bias=True)
    (relu2): ReLU()
    (dense2): Linear(in_features=128, out_features=10, bias=True)
  )
)
==============================
由浅入深，到模型的属性
Sequential(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU()
  (pool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
==============================
由浅入深，再到模型的属性的内部
Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
==============================
由浅入深，再到模型的属性的内部，依次将这个属性遍历结束
ReLU()
==============================
MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
由浅入深，再到模型的属性的内部，依次将这个属性遍历结束，再遍历另个属性
==============================
Sequential(
  (dense1): Linear(in_features=288, out_features=128, bias=True)
  (relu2): ReLU()
  (dense2): Linear(in_features=128, out_features=10, bias=True)
)
==============================
Linear(in_features=288, out_features=128, bias=True)
==============================
ReLU()
==============================
Linear(in_features=128, out_features=10, bias=True)
==============================
=============华丽分割线=================
('', Net4(
  (conv): Sequential(
    (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (relu1): ReLU()
    (pool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (dense): Sequential(
    (dense1): Linear(in_features=288, out_features=128, bias=True)
    (relu2): ReLU()
    (dense2): Linear(in_features=128, out_features=10, bias=True)
  )
))
==============================
('conv', Sequential(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (relu1): ReLU()
  (pool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
))
==============================
('conv.conv1', Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)))
==============================
('conv.relu1', ReLU())
==============================
('conv.pool1', MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False))
==============================
('dense', Sequential(
  (dense1): Linear(in_features=288, out_features=128, bias=True)
  (relu2): ReLU()
  (dense2): Linear(in_features=128, out_features=10, bias=True)
))
==============================
('dense.dense1', Linear(in_features=288, out_features=128, bias=True))
==============================
('dense.relu2', ReLU())
==============================
('dense.dense2', Linear(in_features=128, out_features=10, bias=True))
==============================
'''