说明 0、前一部分叫做Feature Extraction，后一部分叫做classification
1、每一个卷积核它的通道数量要求和输入通道是一样的。这种卷积核的总数有多少个和你输出通道的数量是一样的。
2、卷积(convolution)后，C(Channels)变，W(width)和H(Height)可变可不变，取决于是否padding。subsampling(或pooling)后，C不变，W和H变。
3、卷积层：保留图像的空间信息。
4、卷积层要求输入输出是四维张量(B,C,W,H)，全连接层的输入与输出都是二维张量(B,Input_feature)。
传送门 PyTorch的nn.Linear（）详解
5、卷积(线性变换)，激活函数(非线性变换)，池化；这个过程若干次后，view打平，进入全连接层~
1. 卷积操作
import torch
# 定义输入、输出通道
in_channels, out_channels = 5, 10
# 定义图像尺寸
width, height = 100, 100
# 定义卷积核的大小，下式表示大小为3*3的正方形，同时，卷积核的通道数与输入图像的通道数一致，均为5
kernel_size = 3
# 定义一次输入图像的数量
batch_size = 1input = torch.randn(batch_size,in_channels,width,height)# out_channels 决定了卷积核的数量, 即一共有10个3*3*5的卷积核
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)输出：
torch.Size([1, 5, 100, 100])
torch.Size([1, 10, 98, 98])
torch.Size([10, 5, 3, 3])
有时，我们希望获得与原图像相同大小的卷积后的图像，这时需要属性padding，默认为0
conv_layer_with_padding = torch.nn.Conv2d(in_channels,out_channels,padding=1,kernel_size = kernel_size)
output_with_padding = conv_layer_with_padding(input)
print(output_with_padding.shape)
输出：
torch.Size([1, 10, 100, 100])
还有时，我们希望再次降低网络的大小，以降低运算量。此时引入卷积核移动步长stride的概念，默认为1
conv_layer_with_stride = torch.nn.Conv2d(in_channels,out_channels,stride=2,kernel_size=kernel_size)output_with_stride = conv_layer_with_stride(input)
print(output_with_stride.shape)
输出：
torch.Size([1, 10, 49, 49])
2. 下采样
下采样与卷积无本质区别，不同的在于目的。下采样的目的是将数据维度再次减少。
最常用的下采样手段是Max Pooling 最大池化。
input = [3,4,6,5,2,4,6,8,1,6,7,8,9,7,4,6,
]
input = torch.Tensor(input).view(1,1,4,4)
maxpooling_layer = torch.nn.MaxPool2d(kernel_size=2)
# 注意，我们将kernel_size设为2，此时stride默认也为2output = maxpooling_layer(input)
print(output)输出：
tensor([[[[4., 8.],[9., 8.]]]])
3. 卷积神经基础代码
代码说明：
1、torch.nn.Conv2d(1,10,kernel_size=3,stride=2,bias=False)
1是指输入的Channel，灰色图像是1维的；10是指输出的Channel，也可以说第一个卷积层需要10个卷积核；kernel_size=3,卷积核大小是3x3；stride=2进行卷积运算时的步长，默认为1；bias=False卷积运算是否需要偏置bias，默认为False。padding = 0，卷积操作是否补0。
2、self.fc = torch.nn.Linear(320, 10)，这个320获取的方式，可以通过x = x.view(batch_size, -1)
# print(x.shape)可得到(64,320)，64指的是batch，320就是指要进行全连接操作时，输入的特征维度。
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 datasetbatch_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 classclass 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 xmodel = 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 = 0.0for batch_idx, data in enumerate(train_loader, 0):inputs, target = datainputs, 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 = 0.0def test():correct = 0total = 0with torch.no_grad():for data in test_loader:images, labels = dataimages, 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 / totalif __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.show()
