可以使用以下3种方式构建模型：
1，继承nn.Module基类构建自定义模型。
2，使用nn.Sequential按层顺序构建模型。
3，继承nn.Module基类构建模型并辅助应用模型容器进行封装(nn.Sequential,nn.ModuleList,nn.ModuleDict)。
其中 第1种方式最为常见，第2种方式最简单，第3种方式最为灵活也较为复杂。
推荐使用第1种方式构建模型。
import torch
from torch import nn
from torchkeras import summary以下是继承nn.Module基类构建自定义模型的一个范例。模型中的用到的层一般在__init__函数中定义，然后在forward方法中定义模型的正向传播逻辑。
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3)
self.pool1 = nn.MaxPool2d(kernel_size = 2,stride = 2)
self.conv2 = nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5)
self.pool2 = nn.MaxPool2d(kernel_size = 2,stride = 2)
self.dropout = nn.Dropout2d(p = 0.1)
self.adaptive_pool = nn.AdaptiveMaxPool2d((1,1))
self.flatten = nn.Flatten()
self.linear1 = nn.Linear(64,32)
self.relu = nn.ReLU()
self.linear2 = nn.Linear(32,1)
self.sigmoid = nn.Sigmoid()
def forward(self,x):
x = self.conv1(x)
x = self.pool1(x)
x = self.conv2(x)
x = self.pool2(x)
x = self.dropout(x)
x = self.adaptive_pool(x)
x = self.flatten(x)
x = self.linear1(x)
x = self.relu(x)
x = self.linear2(x)
y = self.sigmoid(x)
return y
net = Net()
print(net)Net(
(conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1))
(pool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(conv2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1))
(pool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(dropout): Dropout2d(p=0.1, inplace=False)
(adaptive_pool): AdaptiveMaxPool2d(output_size=(1, 1))
(flatten): Flatten()
(linear1): Linear(in_features=64, out_features=32, bias=True)
(relu): ReLU()
(linear2): Linear(in_features=32, out_features=1, bias=True)
(sigmoid): Sigmoid()
)
summary(net,input_shape= (3,32,32))----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 32, 30, 30] 896
MaxPool2d-2 [-1, 32, 15, 15] 0
Conv2d-3 [-1, 64, 11, 11] 51,264
MaxPool2d-4 [-1, 64, 5, 5] 0
Dropout2d-5 [-1, 64, 5, 5] 0
AdaptiveMaxPool2d-6 [-1, 64, 1, 1] 0
Flatten-7 [-1, 64] 0
Linear-8 [-1, 32] 2,080
ReLU-9 [-1, 32] 0
Linear-10 [-1, 1] 33
Sigmoid-11 [-1, 1] 0
================================================================
Total params: 54,273
Trainable params: 54,273
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.011719
Forward/backward pass size (MB): 0.359634
Params size (MB): 0.207035
Estimated Total Size (MB): 0.578388
----------------------------------------------------------------
使用nn.Sequential按层顺序构建模型无需定义forward方法。仅仅适合于简单的模型。
以下是使用nn.Sequential搭建模型的一些等价方法。
1，利用add_module方法
net = nn.Sequential()
net.add_module("conv1",nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3))
net.add_module("pool1",nn.MaxPool2d(kernel_size = 2,stride = 2))
net.add_module("conv2",nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5))
net.add_module("pool2",nn.MaxPool2d(kernel_size = 2,stride = 2))
net.add_module("dropout",nn.Dropout2d(p = 0.1))
net.add_module("adaptive_pool",nn.AdaptiveMaxPool2d((1,1)))
net.add_module("flatten",nn.Flatten())
net.add_module("linear1",nn.Linear(64,32))
net.add_module("relu",nn.ReLU())
net.add_module("linear2",nn.Linear(32,1))
net.add_module("sigmoid",nn.Sigmoid())
print(net)Sequential(
(conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1))
(pool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(conv2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1))
(pool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(dropout): Dropout2d(p=0.1, inplace=False)
(adaptive_pool): AdaptiveMaxPool2d(output_size=(1, 1))
(flatten): Flatten()
(linear1): Linear(in_features=64, out_features=32, bias=True)
(relu): ReLU()
(linear2): Linear(in_features=32, out_features=1, bias=True)
(sigmoid): Sigmoid()
)
2，利用变长参数
这种方式构建时不能给每个层指定名称。
net = nn.Sequential(
nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3),
nn.MaxPool2d(kernel_size = 2,stride = 2),
nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5),
nn.MaxPool2d(kernel_size = 2,stride = 2),
nn.Dropout2d(p = 0.1),
nn.AdaptiveMaxPool2d((1,1)),
nn.Flatten(),
nn.Linear(64,32),
nn.ReLU(),
nn.Linear(32,1),
nn.Sigmoid()
)
print(net)Sequential(
(0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1))
(1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1))
(3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(4): Dropout2d(p=0.1, inplace=False)
(5): AdaptiveMaxPool2d(output_size=(1, 1))
(6): Flatten()
(7): Linear(in_features=64, out_features=32, bias=True)
(8): ReLU()
(9): Linear(in_features=32, out_features=1, bias=True)
(10): Sigmoid()
)
3，利用OrderedDict
from collections import OrderedDict
net = nn.Sequential(OrderedDict(
[("conv1",nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3)),
("pool1",nn.MaxPool2d(kernel_size = 2,stride = 2)),
("conv2",nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5)),
("pool2",nn.MaxPool2d(kernel_size = 2,stride = 2)),
("dropout",nn.Dropout2d(p = 0.1)),
("adaptive_pool",nn.AdaptiveMaxPool2d((1,1))),
("flatten",nn.Flatten()),
("linear1",nn.Linear(64,32)),
("relu",nn.ReLU()),
("linear2",nn.Linear(32,1)),
("sigmoid",nn.Sigmoid())
])
)
print(net)Sequential(
(conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1))
(pool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(conv2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1))
(pool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(dropout): Dropout2d(p=0.1, inplace=False)
(adaptive_pool): AdaptiveMaxPool2d(output_size=(1, 1))
(flatten): Flatten()
(linear1): Linear(in_features=64, out_features=32, bias=True)
(relu): ReLU()
(linear2): Linear(in_features=32, out_features=1, bias=True)
(sigmoid): Sigmoid()
)
summary(net,input_shape= (3,32,32))----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 32, 30, 30] 896
MaxPool2d-2 [-1, 32, 15, 15] 0
Conv2d-3 [-1, 64, 11, 11] 51,264
MaxPool2d-4 [-1, 64, 5, 5] 0
Dropout2d-5 [-1, 64, 5, 5] 0
AdaptiveMaxPool2d-6 [-1, 64, 1, 1] 0
Flatten-7 [-1, 64] 0
Linear-8 [-1, 32] 2,080
ReLU-9 [-1, 32] 0
Linear-10 [-1, 1] 33
Sigmoid-11 [-1, 1] 0
================================================================
Total params: 54,273
Trainable params: 54,273
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.011719
Forward/backward pass size (MB): 0.359634
Params size (MB): 0.207035
Estimated Total Size (MB): 0.578388
----------------------------------------------------------------
当模型的结构比较复杂时，我们可以应用模型容器(nn.Sequential,nn.ModuleList,nn.ModuleDict)对模型的部分结构进行封装。
这样做会让模型整体更加有层次感，有时候也能减少代码量。
注意，在下面的范例中我们每次仅仅使用一种模型容器，但实际上这些模型容器的使用是非常灵活的，可以在一个模型中任意组合任意嵌套使用。
1，nn.Sequential作为模型容器
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv = nn.Sequential(
nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3),
nn.MaxPool2d(kernel_size = 2,stride = 2),
nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5),
nn.MaxPool2d(kernel_size = 2,stride = 2),
nn.Dropout2d(p = 0.1),
nn.AdaptiveMaxPool2d((1,1))
)
self.dense = nn.Sequential(
nn.Flatten(),
nn.Linear(64,32),
nn.ReLU(),
nn.Linear(32,1),
nn.Sigmoid()
)
def forward(self,x):
x = self.conv(x)
y = self.dense(x)
return y
net = Net()
print(net)Net(
(conv): Sequential(
(0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1))
(1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1))
(3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(4): Dropout2d(p=0.1, inplace=False)
(5): AdaptiveMaxPool2d(output_size=(1, 1))
)
(dense): Sequential(
(0): Flatten()
(1): Linear(in_features=64, out_features=32, bias=True)
(2): ReLU()
(3): Linear(in_features=32, out_features=1, bias=True)
(4): Sigmoid()
)
)
2，nn.ModuleList作为模型容器
注意下面中的ModuleList不能用Python中的列表代替。
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.layers = nn.ModuleList([
nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3),
nn.MaxPool2d(kernel_size = 2,stride = 2),
nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5),
nn.MaxPool2d(kernel_size = 2,stride = 2),
nn.Dropout2d(p = 0.1),
nn.AdaptiveMaxPool2d((1,1)),
nn.Flatten(),
nn.Linear(64,32),
nn.ReLU(),
nn.Linear(32,1),
nn.Sigmoid()]
)
def forward(self,x):
for layer in self.layers:
x = layer(x)
return x
net = Net()
print(net)Net(
(layers): ModuleList(
(0): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1))
(1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1))
(3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(4): Dropout2d(p=0.1, inplace=False)
(5): AdaptiveMaxPool2d(output_size=(1, 1))
(6): Flatten()
(7): Linear(in_features=64, out_features=32, bias=True)
(8): ReLU()
(9): Linear(in_features=32, out_features=1, bias=True)
(10): Sigmoid()
)
)
summary(net,input_shape= (3,32,32))----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 32, 30, 30] 896
MaxPool2d-2 [-1, 32, 15, 15] 0
Conv2d-3 [-1, 64, 11, 11] 51,264
MaxPool2d-4 [-1, 64, 5, 5] 0
Dropout2d-5 [-1, 64, 5, 5] 0
AdaptiveMaxPool2d-6 [-1, 64, 1, 1] 0
Flatten-7 [-1, 64] 0
Linear-8 [-1, 32] 2,080
ReLU-9 [-1, 32] 0
Linear-10 [-1, 1] 33
Sigmoid-11 [-1, 1] 0
================================================================
Total params: 54,273
Trainable params: 54,273
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.011719
Forward/backward pass size (MB): 0.359634
Params size (MB): 0.207035
Estimated Total Size (MB): 0.578388
----------------------------------------------------------------
3，nn.ModuleDict作为模型容器
注意下面中的ModuleDict不能用Python中的字典代替。
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.layers_dict = nn.ModuleDict({"conv1":nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3),
"pool": nn.MaxPool2d(kernel_size = 2,stride = 2),
"conv2":nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5),
"dropout": nn.Dropout2d(p = 0.1),
"adaptive":nn.AdaptiveMaxPool2d((1,1)),
"flatten": nn.Flatten(),
"linear1": nn.Linear(64,32),
"relu":nn.ReLU(),
"linear2": nn.Linear(32,1),
"sigmoid": nn.Sigmoid()
})
def forward(self,x):
layers = ["conv1","pool","conv2","pool","dropout","adaptive",
"flatten","linear1","relu","linear2","sigmoid"]
for layer in layers:
x = self.layers_dict[layer](x)
return x
net = Net()
print(net)Net(
(layers_dict): ModuleDict(
(adaptive): AdaptiveMaxPool2d(output_size=(1, 1))
(conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1))
(conv2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1))
(dropout): Dropout2d(p=0.1, inplace=False)
(flatten): Flatten()
(linear1): Linear(in_features=64, out_features=32, bias=True)
(linear2): Linear(in_features=32, out_features=1, bias=True)
(pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(relu): ReLU()
(sigmoid): Sigmoid()
)
)
summary(net,input_shape= (3,32,32))----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 32, 30, 30] 896
MaxPool2d-2 [-1, 32, 15, 15] 0
Conv2d-3 [-1, 64, 11, 11] 51,264
MaxPool2d-4 [-1, 64, 5, 5] 0
Dropout2d-5 [-1, 64, 5, 5] 0
AdaptiveMaxPool2d-6 [-1, 64, 1, 1] 0
Flatten-7 [-1, 64] 0
Linear-8 [-1, 32] 2,080
ReLU-9 [-1, 32] 0
Linear-10 [-1, 1] 33
Sigmoid-11 [-1, 1] 0
================================================================
Total params: 54,273
Trainable params: 54,273
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.011719
Forward/backward pass size (MB): 0.359634
Params size (MB): 0.207035
Estimated Total Size (MB): 0.578388
----------------------------------------------------------------
如果对本书内容理解上有需要进一步和作者交流的地方，欢迎在公众号"Python与算法之美"下留言。作者时间和精力有限，会酌情予以回复。
也可以在公众号后台回复关键字：加群，加入读者交流群和大家讨论。
