pytorch(一)一个简单的CNN搭建

网络组成：卷积、激活、池化、BN、dropout、全连接层等。各层作用。

需要设定某些网络层的相关参数inchannel,outchannel,kernel_size、padding、stride等。

若输入数据维度为W*W   kernelsize： F×F     stride：S          padding： P

可以得出卷积层输出的特征图尺寸计算：N = (W − F + 2P )/S+1

nn.MaxPool2d()函数中，参数ceil_mode默认为False表示向下取整，如果等于True，向上取整

池化层输出计算公式：dilation默认为1，如果不设置stride则默认为kernelsize大小。来源

例子：

假设输入：3*448*448

经过5次卷积要获得256*14*14 feature map（fp）

最简单方法是卷积层stride与padding都为1，核为3；池化层核为2，stride为2。

import torch.nn as nn
import torch
import numpy as np
import torch.nn.functional as F

class myNet(nn.Module):
    def __init__(self):
        super(myNet, self).__init__()
        self.conv1=nn.Conv2d(3,32,3,1,1)
        self.conv2 = nn.Conv2d(32, 64, 3,1,1)
        self.conv3 = nn.Conv2d(64, 128, 3,1,1)
        self.conv4 = nn.Conv2d(128, 128, 3,1,1)
        self.conv5 = nn.Conv2d(128, 256, 3,1,1)
        self.linear1=nn.Linear(256*14*14,4096)
        self.linear2=nn.Linear(4096,4096)
        self.linear3=nn.Linear(4096,10)

    def forward(self,x):
        x = F.max_pool2d(F.relu(self.conv1(x)),(2,2))
        x = F.max_pool2d(F.relu(self.conv2(x)), (2, 2))
        x = F.max_pool2d(F.relu(self.conv3(x)), (2, 2))
        x = F.max_pool2d(F.relu(self.conv4(x)), (2, 2))
        x = F.max_pool2d(F.relu(self.conv5(x)), (2, 2))
        print(x.size())
        x = x.view(x.size()[0], -1)
        x = self.linear1(x)
        print(x.shape)
        x = self.linear2(x)
        print(x.shape)
        x = self.linear3(x)

        return x



inputs=torch.randn(1,3,448,448)
model=myNet()
#打印各层网络参数信息
print(model)
print(model(inputs).shape)



"""
输出信息：
myNet(
  (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (conv2): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (conv3): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (conv4): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (conv5): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (linear1): Linear(in_features=50176, out_features=4096, bias=True)
  (linear2): Linear(in_features=4096, out_features=4096, bias=True)
  (linear3): Linear(in_features=4096, out_features=10, bias=True)
)
torch.Size([1, 256, 14, 14])
torch.Size([1, 4096])
torch.Size([1, 4096])
torch.Size([1, 10])


"""

待续。。。