【深度学习】（十）卷积神经网络（上）

 先来看一下卷积神经网络的样子

 根据上面流程绘制脑图

目录

卷积

卷积计算

 一个卷积层输入输出不同代码

 输入输出通道相同代码

 下采样​编辑

 举例：对手写数字做卷积神经网络

要会求粉色框框数据​编辑

1、卷积

1）卷积计算

 2）一个卷积层输入输出不同代码

import torch
in_channels,out_channels=5,10
width,height=100,100#图像大小
kennel_size=3
batch_size = 1
input=torch.randn(batch_size,in_channels,width,height)
conv_layer=torch.nn.Conv2d(in_channels,out_channels,kernel_size=kennel_size)
output=conv_layer(input)
print(input.shape)
print(output.shape)
print(conv_layer.weight.shape)

结果torch.Size([1, 5, 100, 100])
torch.Size([1, 10, 98, 98])
torch.Size([10, 5, 3, 3])

 3）输入输出通道相同代码

若想输入输出的wh相同
则输入需要添加padding=kernel_size/2,
padding=1表示在输入的外圈增加一圈0

conv_layer=torch.nn.Conv2d(1,1,kernel_size=3,padding=1,bias=False)

import torch
input=[3,4,6,5,7,
       2,4,6,8,2,
       2,6,7,8,4,
       9,7,4,6,2,
       3,7,5,4,1,]
input=torch.Tensor(input).view(1,1,5,5)
conv_layer=torch.nn.Conv2d(1,1,kernel_size=3,padding=1,bias=False)
kernel = torch.Tensor([1,2,3,4,5,6,7,8,9]).view(1,1,3,3)
conv_layer.weight.data=kernel.data
output=conv_layer(input)
print(output)

结果

tensor([[[[ 91., 168., 224., 215., 127.],
          [122., 218., 295., 262., 149.],
          [197., 263., 282., 214., 122.],
          [196., 252., 253., 169.,  86.],
          [ 96., 112., 110.,  68.,  31.]]]], grad_fn=<ConvolutionBackward0>) 

 2、下采样

 1）举例：对手写数字做卷积神经网络

要会求粉色框框数据

 上图中分别卷积层1、池化层、卷积层2、池化层、全连接层

卷积层1self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)
卷积层2self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)
池化层self.pooling = torch.nn.MaxPool2d(2)

2）代码

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

# prepare dataset

batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])

train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)


# design model using class


class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)
        self.pooling = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(320, 10)

    def forward(self, x):
        # flatten data from (n,1,28,28) to (n, 784)
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = x.view(batch_size, -1)  # -1 此处自动算出的是320
        x = self.fc(x)

        return x


model = Net()

# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)


# training cycle forward, backward, update


def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
            running_loss = 0.0


def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print('accuracy on test set: %d %% ' % (100 * correct / total))


if __name__ == '__main__':
    for epoch in range(10):
         train(epoch)
         test()

。。。。。。
accuracy on test set: 98 % 
[7,   300] loss: 0.041
[7,   600] loss: 0.044
[7,   900] loss: 0.048
accuracy on test set: 98 % 
[8,   300] loss: 0.042
[8,   600] loss: 0.041
[8,   900] loss: 0.039
accuracy on test set: 98 % 
[9,   300] loss: 0.033
[9,   600] loss: 0.041
[9,   900] loss: 0.039
accuracy on test set: 98 % 
[10,   300] loss: 0.033
[10,   600] loss: 0.035
[10,   900] loss: 0.039
accuracy on test set: 98 % 

Process finished with exit code 0