视频中所涉及的代码如下：
- basic_cnn.py 一个简单的卷积层
- padding.py 卷积层参数——padding填充
- stride.py 参数——步长
- maxpooling.py 下采样——最大池化
- cnn.py 一个简单的卷积神经网络
- cnn_job.py 作业——修改网络结构
1. basic_cnn.py 一个简单的卷积层
示范卷积层所做的工作
import torch
in_channels, out_channels = 5, 10
width, height = 100, 100
kernel_size = 3
batch_size = 1
# 生成一个服从正态分布的随机数 4维张量
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)
# 输出结果：
# torch.Size([1, 5, 100, 100])
# torch.Size([1, 10, 98, 98])
# torch.Size([10, 5, 3, 3])
print(output)2. padding.py 卷积层参数——padding填充
在原图像周围填充0，使输出与输入图像的高度和宽度一样
import torch
input = [3, 4, 6, 5, 7,
2, 4, 6, 8, 2,
1, 6, 7, 8, 4,
9, 7, 4, 6, 2,
3, 7, 5, 4, 1]
# (1, 1, 5, 5)——>(batch, channel, width, height)
input = torch.Tensor(input).view(1, 1, 5, 5)
conv_layer = torch.nn.Conv2d(1, 1, kernel_size=3, padding=1, bias=False)
# (1, 1, 3, 3)——>(output, input, kernel_width, kernel_height)
kernel = torch.Tensor([1, 2, 3, 4, 5, 6, 7, 8, 9]).view(1, 1, 3, 3)
# 卷积层权重初始化
conv_layer.weight.data = kernel.data
output = conv_layer(input)
print(output)3. stride.py 参数——步长
卷积核移动的速度
import torch
input = [3, 4, 6, 5, 7,
2, 4, 6, 8, 2,
1, 6, 7, 8, 4,
9, 7, 4, 6, 2,
3, 7, 5, 4, 1]
# (1, 1, 5, 5)——>(batch, channel, width, height)
input = torch.Tensor(input).view(1, 1, 5, 5)
conv_layer = torch.nn.Conv2d(1, 1, kernel_size=3, stride=2, bias=False)
# (1, 1, 3, 3)——>(output, input, kernel_width, kernel_height)
kernel = torch.Tensor([1, 2, 3, 4, 5, 6, 7, 8, 9]).view(1, 1, 3, 3)
# 卷积层权重初始化
conv_layer.weight.data = kernel.data
output = conv_layer(input)
print(output)4. maxpooling.py 下采样——最大池化
取一个池化窗口中权重最大的值保存下来
import torch
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)
# 步长stride也默认等于2
maxpooling_layer = torch.nn.MaxPool2d(kernel_size=2)
output = maxpooling_layer(input)
print(output)5. cnn.py 一个简单的卷积神经网络
使用的mnist数据集进行训练和测试，与第9将中的代码一样，只需要更换模型定义
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
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,
# 指定数据用transform来处理
transform=transform)
train_loader = DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_dataset = datasets.MNIST(root='../dataset/mnist',
train=False,
download=True,
transform=transform)
test_loader = DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
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):
# x的第0维就是batch_size
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()
# 将模型迁移到GPU上运行，cuda:0表示第0块显卡
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(torch.cuda.is_available())
model.to(device)
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
# 将训练和测试过程分别封装在两个函数当中
def train(epoch):
running_loss = 0
for batch_idx, data in enumerate(train_loader, 0):
inputs, target = data
# 将要计算的张量也迁移到GPU上——输入和输出
inputs, target = inputs.to(device), target.to(device)
optimizer.zero_grad()
# 前馈 反馈 更新
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
accuracy = []
def test():
correct = 0
total = 0
with torch.no_grad():
for data in test_loader:
images, labels = data
# 测试中的张量也迁移到GPU上
images, labels = images.to(device), labels.to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, dim=1)
total += labels.size(0)
# ？？怎么比较的相等
# print(predicted)
# print(labels)
# print('predicted == labels', predicted == labels)
# 两个张量比较，得出的是其中相等的元素的个数（即一个批次中预测正确的个数）
correct += (predicted == labels).sum().item()
# print('correct______', correct)
print('Accuracy on test set: %d %%' % (100 * correct / total))
accuracy.append(100 * correct / total)
if __name__ == '__main__':
for epoch in range(10):
train(epoch)
test()
print(accuracy)
plt.plot(range(10), accuracy)
plt.xlabel("epoch")
plt.ylabel("Accuracy")
plt.show()结果：
6. cnn_job.py 作业——修改网络结构
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
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,
# 指定数据用transform来处理
transform=transform)
train_loader = DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_dataset = datasets.MNIST(root='../dataset/mnist',
train=False,
download=True,
transform=transform)
test_loader = DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
# 模型修改如下（随便改的）
self.conv1 = torch.nn.Conv2d(1, 16, kernel_size=5)
self.conv2 = torch.nn.Conv2d(16, 32, kernel_size=5)
self.conv3 = torch.nn.Conv2d(32, 64, kernel_size=3)
self.pooling = torch.nn.MaxPool2d(2)
self.fc1 = torch.nn.Linear(64, 32)
self.fc2 = torch.nn.Linear(32, 10)
def forward(self, x):
# x的第0维就是batch_size
batch_size = x.size(0)
x = self.pooling(F.relu((self.conv1(x))))
x = self.pooling(F.relu((self.conv2(x))))
x = self.pooling(F.relu((self.conv3(x))))
x = x.view(batch_size, -1)
x = F.relu(self.fc1(x))
x = self.fc2(x)
return x
model = Net()
# 将模型迁移到GPU上运行，cuda:0表示第0块显卡
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(torch.cuda.is_available())
model.to(device)
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
# 将训练和测试过程分别封装在两个函数当中
def train(epoch):
running_loss = 0
for batch_idx, data in enumerate(train_loader, 0):
inputs, target = data
# 将要计算的张量也迁移到GPU上——输入和输出
inputs, target = inputs.to(device), target.to(device)
optimizer.zero_grad()
# 前馈 反馈 更新
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
accuracy = []
def test():
correct = 0
total = 0
with torch.no_grad():
for data in test_loader:
images, labels = data
# 测试中的张量也迁移到GPU上
images, labels = images.to(device), labels.to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, dim=1)
total += labels.size(0)
# ？？怎么比较的相等
# print(predicted)
# print(labels)
# print('predicted == labels', predicted == labels)
# 两个张量比较，得出的是其中相等的元素的个数（即一个批次中预测正确的个数）
correct += (predicted == labels).sum().item()
# print('correct______', correct)
print('Accuracy on test set: %d %%' % (100 * correct / total))
accuracy.append(100 * correct / total)
if __name__ == '__main__':
for epoch in range(10):
train(epoch)
test()
print(accuracy)
plt.plot(range(10), accuracy)
plt.xlabel("epoch")
plt.ylabel("Accuracy")
plt.show()结果：
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
