PyTorch深度学习实践（十）卷积神经网络（基础篇）

1.卷积（Convolution）以后，通道数C（channels）改变，图像宽度W（width），高度H（height）可变可不变，但是下采样（Subsampling）/或者（pooling）以后，C不变，W和H改变，因为下采样的目的就是减少参数量。

用3个卷积核（3*3*3）和3个通道（RGB）下的张量（3*5*5）做卷积之后得到一个张量（1*3*3）如果你想得到一个m个通道的输出张量，只需要用m个（3*3*3）的卷积核和输入张量做卷积，最后再把它们按照顺序拼接起来。

2.张量的一些概念

 3.一个卷积神经网络的基本机构主要包括两个方面，特征提取（Feature Extraction）和分类（Classification）

 然后是代码实现了一个卷积层，并给他一个输入来检测性能

import torch
in_channels, out_channels = 5,10
width, height = 100, 100
kernel_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=kernel_size)

output = conv_layer(input)

print(input.shape)
print(output.shape)
print(conv_layer.weight.shape)

 结果如图所示

输入的是一个5通道的，大小100*100的图像，输出是一个10通道的，大小98*98的图像 ，卷积层权重的形状是，输出是10通道的，输入是5通道，然后卷积核大小是3*3，它与输入图像是没关系的，但是如果你放入一个6通道的输入图像进去，他就会报错（因为输入通道已经定义好了是5）

4.padding：本质就是在图像的最外面添加一圈0，比如一个5*5的图像，共25个格子，padding=1时，就是在外面加一圈0，最后就变成一个7*7的图像，共49个格子

 另一个小代码：

import torch
input = [3,4,6,5,7,       #定义输入图像
         2,4,6,8,2,
         1,6,7,8,4,
         9,7,4,6,2,
         3,7,5,4,1]
input = torch.Tensor(input). view(1,1,5,5) #4个参数分别为Batch_size,channels,width,height
                                           #把输入变成这样一个张量
conv_layer = torch.nn. Conv2d(1,1, kernel_size=3, padding=1, bias=False)
                          #构建一个卷积层，输入输出都是一个通道

kernel = torch. Tensor([1,2,3,4,5,6,7,8,9]).view(1,1,3,3)
                    #构建卷积核，并用view改变形状，输出，输入通道数都是1，宽和高也都是3
conv_layer.weight.data = kernel.data
                #把卷积核的data赋值给卷积层，相当于给卷积层初始化
output = conv_layer(input)
print(output)

 然后实现结果如图：

 5.stride：卷积核移动的步长，常见的都是1

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
import matplotlib.pyplot as plt
 
# 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
        # print("x.shape",x.shape)
        x = self.fc(x)
 
        return x
 
 
model = Net()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
 
# 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
        inputs, target = inputs.to(device), target.to(device)
        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
            images, labels = images.to(device), labels.to(device)
            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))
    return correct/total
 
 
if __name__ == '__main__':
    epoch_list = []
    acc_list = []
    
    for epoch in range(10):
        train(epoch)
        acc = test()
        epoch_list.append(epoch)
        acc_list.append(acc)
    
    plt.plot(epoch_list,acc_list)
    plt.ylabel('accuracy')
    plt.xlabel('epoch')
    plt.grid()
    plt.show()