神经网络--搭建小实战和Seq的使用

搭建神经网络演示下图处理过程

计算padding需要使用的公式

import torch

from torch import nn
from torch.nn import Conv2d, MaxPool2d, Linear
from torch.nn.modules.flatten import Flatten


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

        # 新建一个卷积层  Inputs 3@32×32  inchannel:3 outchaanel: 32 kernel:5×5
        # Convolution 5×5 kernel
        #32*2*padding-4-1 = 27+2*padding = 31  -->  padding = 2
        self.conv1 = Conv2d(3, 32, 5, padding=2)

        #最大池化
        #Max-pooling 2×2 kernel
        self.maxpool1 = MaxPool2d(2)

        #卷积
        #Convolution 5×5 kernel
        self.conv2 = Conv2d(32, 32, 5, padding=2)

        #最大池化
        #Max-pooling 2×2 kernel
        self.maxpool2 = MaxPool2d(2)

        # 卷积
        # Convolution 5×5 kernel
        self.conv3 = Conv2d(32, 64, 5, padding=2)

        #最大池化
        #Max-pooling 2×2 kernel
        self.maxpool3 = MaxPool2d(2)

        #flatten展平
        #Feature maps 64@4×4
        #64×4×4 = 1024
        self.flatten = Flatten()

        #线性层：每个神经元与上一层所有神经元相连
        #hidden units 64
        self.linear1 = Linear(1024, 64)

        #Outputs 10
        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

test1 = Test()
#输入一个一维图像
#torch.ones()输入的都是1
#batch_size:64  3通道  32×32
input = torch.ones((64, 3, 32, 32))
output = test1(input)
print(output.shape)

结果：

torch.Size([64, 10])

Sequential 是一个时序容器。Modules 会以他们传入的顺序被添加到容器中。在神经网络搭建的过程中如果使用 Sequential，代码更简洁。
tensorboard显示计算图的具体信息

from torch import nn
from torch.nn import Conv2d, MaxPool2d, Linear, Sequential
from torch.nn.modules import Flatten
from torch.utils.tensorboard import SummaryWriter

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

test1 = Test()
input = torch.ones((64, 3, 32, 32))
output = test1(input)

writer = SummaryWriter("logs_seq")
writer.add_graph(test1, input)
writer.close()

terminal中输入

tensorboard --logdir="logs_seq" --port=6007

结果：

Test(
  (conv1): Conv2d(3, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (maxpool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (maxpool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv3): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (maxpool3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (flatten): Flatten(start_dim=1, end_dim=-1)
  (linear1): Linear(in_features=1024, out_features=64, bias=True)
  (linear2): Linear(in_features=64, out_features=10, bias=True)
)
torch.Size([64, 10])