什么是Sequential?
"Sequential"是PyTorch中的一个模块,用于构建神经网络模型。它允许你按照顺序将不同的神经网络层组合在一起,形成一个网络模型。你可以把它想象成一个管道,数据从一个层流向另一个层,最终经过整个管道的处理得到输出。
简而言之,就是方便对数据进行处理,代码更加简洁。
通过搭建一个小的神经网络来对比使用Sequential前后,代码的变化:
未使用Sequential前:
import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
class My_Model(nn.Moudel):
def __init__(self):
super(My_Model, self).__init__()
// 开始对数据进行处理
self.conv1 = Conv2d(3, 32, 5, padding=2)
self.max_pool1 = MaxPool2d(2)
self.conv2 = Conv2d(32, 32, 5, padding=2)
self.max_pool2 = MaxPool2d(2)
self.conv3 = Conv2d(32, 64, 5, padding=2)
self.max_pool3 = MaxPool2d(2)
self.flatten = Flatten()
self.linear1 = Linear(1024, 64)
self.linear2 = Linear(64, 10)
def forward(self, x):
x = self.conv1(x)
x = self.max_pool1(x)
x = self.conv2(x)
x = self.max_pool2(x)
x = self.conv2(x)
x = self.max_pool3(x)
x = self.flatten()
x = self.linear1(x)
x = self.linear2(x)
return x
my_model = MyModel()
print(my_model)
使用Sequential后:
import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
class MyModel(nn.Module):
def __init__(self):
super(MyModel, self).__init__()
self.model1 = Sequential(
Conv2d(3, 32, 5, padding=2),
MaxPool2d(2),
Conv2d(32, 32, 5, padding=2),
MaxPool2d(2),
Conv2d(32, 64, 5, padding=2),
MaxPool2d(2),
Flatten(),
Linear(1024, 64),
Linear(64, 10)
)
def forward(self, x):
x = self.model1(x)
return x
my_module = MyModel()
print(my_module)
input = torch.ones((64, 3, 32, 32))
output = my_module(input)
print(output.shape)
通过两张图片的对比可以看出来,结果是一样的,但是使用Sequential以后,代码明显更加简洁;