这里拿实现vgg16模型来举例
下图为vgg16模型的网络图谱
这个是计算padding的解题思路,当然也可以口算
第一种形式:
import torch
from torch import nn
from torch.nn import Conv2d,MaxPool2d,Flatten,Linear
from torch.utils.tensorboard import SummaryWriter
#相对繁琐的一种方式:
class qiqi(nn.Module):
def __init__(self):
super(qiqi, self).__init__()
self.conv1=Conv2d(3,32,5,padding=2)#padding可以根据公式算出来
self.maxpool1=MaxPool2d(2)
self.conv2=Conv2d(32,32,5,padding=2)
self.maxpool2=MaxPool2d(2)
self.conv3=Conv2d(32,64,5,padding=2)
self.maxpool3=MaxPool2d(2)
self.flatten=Flatten()
self.linear1=Linear(1024,64)#1024是池化后展平的大小,算不出来可以print一下就知道了
self.linear2=Linear(64,10)
def forward(self,x):
x=self.conv1(x)
x=self.maxpool1(x)
x=self.conv2(x)
x=self.maxpool2(x)
x=self.conv3(x)
x=self.maxpool3(x)
x=self.flatten(x)
x=self.linear1(x)
x=self.linear2(x)
return x
#验证神经网络是否正确
qq=qiqi()
print(qq)
input = torch.ones((64,3,32,32))#64张3通道32*32的单位1矩阵
output=qq(input)
print(output.shape)
第二种使用Sequencital:
import torch
from torch import nn
from torch.nn import Conv2d,MaxPool2d,Flatten,Linear,Sequential#这边要引入一下
from torch.utils.tensorboard import SummaryWriter
#相对繁琐的一种方式:
class qiqi(nn.Module):
def __init__(self):
super(qiqi, self).__init__()
self.model1 = Sequential(
Conv2d(3, 32, 5, padding=2), #注意有逗号
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
qq=qiqi()
print(qq)
input = torch.ones((64,3,32,32))#64张3通道32*32的单位1矩阵
output=qq(input)
writer = SummaryWriter("nn_seq(vgg16)")
writer.add_graph(qq,input)
writer.close()
tensorboard中打开所示:
可以看到每一层的关系和参数