CNN原理图
Feature Extraction 为特征提取层负责提取C1，S1，C2，S2的特征作为一个向量
Classifiction 为分类器，将得到的向量进行全连接
一般有RGB三种通道，C*W*H
卷积过程，是数字与数字的相乘，并不是矩阵乘法
每一个核都要配备一个通道，若通道有3个，则有3个核；若通道有5个，则有5个核；相应的如果想要有m个输出通道，则需要有m个核。即：卷积核通道数=输入通道数，卷积核个数=输出通道数
import torch in_channels, out_channels = 5, 10 # 输入通道为5，输出为10 width, height = 100, 100 # 图像大小为100*100 kernel_size = 3 # 卷积核大小 batch_size = 1 # 小批量 input = torch.randn(batch_size, in_channels, width, height) #B,N,W,H conv_layer = torch.nn.Conv2d(in_channels, out_channels, kernel_size=kernel_size) # 输入通道数，输出通道数，卷积核大小3*3 output = conv_layer(input) print(input.shape) print(output.shape) print(conv_layer.weight.shape)
torch.Size([1, 5, 100, 100]) #5个通道，图像大小为100*100
torch.Size([1, 10, 98, 98]) # 输出变成10个通道，图像大小为98*98
torch.Size([10, 5, 3, 3]) #10为输出通道，5为输入通道，3*3为kernel大小
输入图像与卷积核进行卷积---padding相关代码
import torch
input = [3,4,5,6,7,
2,4,6,8,2,
1,6,7,8,4,
1,2,5,9,8,
5,2,1,8,9]
input = torch.Tensor(input).view(1, 1, 5, 5) # B,C,W,H
conv_layer = torch.nn.Conv2d(1, 1,kernel_size=3, padding=1, bias=False) # 输入输出通道为1，不需要偏执量
kernel = torch.Tensor([1,2,3,4,5,6,7,8,9]).view(1,1,3,3) # 构造卷积核，输出输入为1，大小为3*3
conv_layer.weight.data = kernel.data
output = conv_layer(input)
print(output)
输入图像与卷积核进行卷积---stride相关代码
import torch
input = [3,4,5,6,7,
2,4,6,8,2,
1,6,7,8,4,
1,2,5,9,8,
5,2,1,8,9]
input = torch.Tensor(input).view(1, 1, 5, 5) # B,C,W,H
conv_layer = torch.nn.Conv2d(1, 1,kernel_size=3, stride=2, bias=False) # 输入输出通道为1，不需要偏执量
kernel = torch.Tensor([1,2,3,4,5,6,7,8,9]).view(1,1,3,3) # 构造卷积核，输出输入为1，大小为3*3
conv_layer.weight.data = kernel.data
output = conv_layer(input)
print(output)
最大池化层，将4*4的分为4部分，取出每一部分的最大值
一个简易的神经网络模型
关于kernel大小计算：（28-24）+1=5，
(12-5)+1=8,
池化层大小直接对卷积层的大小除以2
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
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)
# class Net(torch.nn.Module):
# def __init__(self):
# super(Net, self).__init__()
# self.l1 = torch.nn.Linear(784, 512)
# self.l2 = torch.nn.Linear(512, 216)
# self.l3 = torch.nn.Linear(216, 128)
# self.l4 = torch.nn.Linear(128, 64)
# self.l5 = torch.nn.Linear(64, 10)
# def forward(self, x):
# x = x.view(-1, 784)
# x = F.relu(self.l1(x))
# x = F.relu(self.l2(x))
# x = F.relu(self.l3(x))
# x = F.relu(self.l4(x))
# return self.l5(x)
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
# 定义两个卷积层
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)
x = self.fc(x)
return x
model = Net()
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
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(3):
train(epoch)
test()
