这是刘二大人系列课程笔记的 最后一个笔记了，介绍的是 BasicCNN 和 AdvancedCNN ，我做图像，所以后面的RNN我可能暂时不会花时间去了解了；
写在前面：
1. Basic CNN
完整代码：
#!usr/bin/env python
# -*- coding:utf-8 _*-
"""
@author: 24_nemo
@file: 10_CNN_handType.py
@time: 2022/04/12
@desc:
"""
import torch
in_channel, out_channel = 5, 10
width, height = 100, 100
kernel_size = 3
batch_size = 1
input = torch.randn(batch_size,
in_channel,
width,
height)
conv_layer = torch.nn.Conv2d(in_channel,
out_channel,
kernel_size=kernel_size)
output = conv_layer(input)
print(input.shape)
print(output.shape)
print(conv_layer.weight.shape)
运行结果（截图时仍在运行）：
2. Advanced CNN
写在前面：
- 这是刘老师课程的最后一讲，RNN与我关系不大我也没看；
- 课程中讲了
GoogLeNet和ResNet两个网络的基本情况和简单的代码实现，在这里记录一下：
GoogLeNet的完整代码：
# advanced CNN
import torch
from torch import nn, optim
import torch.nn.functional as F
from torchvision import datasets # dataset 引用位置
from torch.utils.data import DataLoader # DataLoader 引用位置
from torchvision import transforms
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 InceptionA(torch.nn.Module):
def __init__(self, in_channels):
super(InceptionA, self).__init__()
self.branch1x1 = nn.Conv2d(in_channels, 16, kernel_size=1) # 乘号用字母x代替;
self.branch5x5_1 = nn.Conv2d(in_channels, 16, kernel_size=1)
self.branch5x5_2 = nn.Conv2d(16, 24, kernel_size=5, padding=2)
self.branch3x3_1 = nn.Conv2d(in_channels, 16, kernel_size=1) # 第一个卷积核都是1x1，这个东西是减少操作数的，为了加速运算
self.branch3x3_2 = nn.Conv2d(16, 24, kernel_size=3, padding=1)
self.branch3x3_3 = nn.Conv2d(24, 24, kernel_size=3, padding=1)
self.branch_pool = nn.Conv2d(in_channels, 24,
kernel_size=1) # branch 这个词儿，在S2D引用的laina的代码里见过，一个是upper——branch，一个是bottom——branch；
def forward(self, x):
branch1x1 = self.branch1x1(x)
branch5x5 = self.branch5x5_1(x)
branch5x5 = self.branch5x5_2(branch5x5)
branch3x3 = self.branch3x3_1(x)
branch3x3 = self.branch3x3_2(branch3x3)
branch3x3 = self.branch3x3_3(branch3x3)
branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
branch_pool = self.branch_pool(branch_pool)
output = [branch1x1, branch5x5, branch3x3, branch_pool]
return torch.cat(output, dim=1)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
self.conv2 = nn.Conv2d(88, 20, kernel_size=5)
self.incep1 = InceptionA(in_channels=10)
self.incep2 = InceptionA(in_channels=20)
self.mp = nn.MaxPool2d(2)
self.fc = nn.Linear(1408, 10)
def forward(self, x):
in_size = x.size(0)
x = F.relu(self.mp(self.conv1(x)))
x = self.incep1(x)
x = F.relu(self.mp(self.conv2(x)))
x = self.incep2(x)
x = x.view(in_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(10):
train(epoch)
test()
运行结果（截图时仍在运行）：
ResNet的完整代码：
# ResNet
import torch
from torch import nn, optim
from torchvision import datasets
from torch.utils.data import DataLoader
from torchvision import transforms
import torch.nn.functional as F
batch_size = 64
transforms = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081))])
train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transforms)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist', train=True, download=True, transform=transforms)
test_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
class ResidualBlock(nn.Module):
def __init__(self, channels):
super(ResidualBlock, self).__init__()
self.channels = channels
self.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
def forward(self, x):
y = F.relu(self.conv1(x))
y = self.conv2(y)
return F.relu(x + y)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 16, kernel_size=5)
self.conv2 = nn.Conv2d(16, 32, kernel_size=5)
self.mp = nn.MaxPool2d(2)
self.rbloch1 = ResidualBlock(16)
self.rbloch2 = ResidualBlock(32)
self.fc = nn.Linear(512, 10)
def forward(self, x):
in_size = x.size(0)
x = self.mp(F.relu(self.conv1(x)))
x = self.rbloch1(x)
x = self.mp(F.relu(self.conv2(x)))
x = self.rbloch2(x)
x = x.view(in_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_size + 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()
运行结果（截图时仍在运行）：
|
