《PyTorch深度学习实践8》——卷积神经网络-基础篇（Basic-Convolution Neural Network）
目录
-
- 一、卷积层
-
- 1.卷积层理解
- 2.卷积层参数
- 二、池化层
- 三、MNIST分类
-
- 1.网络结构
- 2.CPU版本
- 3.GPU版本
一、卷积层
1.卷积层理解
假如我们有一张图像，RGB三通道，我们对每个通道都用一个卷积核，就可以得到三个通道的特征图，之后我们可以将这三个特征图进行简单叠加，就可以得到一张特征图。如下所示：
我们也可以这样表示：
也就是说，我们有一张 n ∗ 5 ∗ 5 n*5*5 n∗5∗5的图像，可以用一个 n ∗ 3 ∗ 3 n*3*3 n∗3∗3的卷积核，得到一张 1 ∗ 3 ∗ 3 1*3*3 1∗3∗3的特征图像：
假如我们有 n ∗ w i d t h i n ∗ h e i g h t i n n*width_{in}*height_{in} n∗widthin∗heightin的图像，我们可以使用m个卷积核，得到m张特征图像，之后我们可以对这m张特征图像进行串联，就可以得到 m ∗ w i d t h o u t ∗ h e i g h t o u t m*width_{out}*height_{out} m∗widthout∗heightout的图像。而此时这个卷积核可以是4维张量，为 m ∗ n ∗ k e r n e l _ s i z e w i d t h ∗ k e r n e l _ s i z e h e i g h t m*n*kernel\_size_{width}*kernel\_size_{height} m∗n∗kernel_sizewidth∗kernel_sizeheight
这段程序是torch.nn.Conv2d的简单用法：
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)
2.卷积层参数
padding=1是对输入边界外1层填充0（ 5 ∗ 5 — > 7 ∗ 7 5*5—>7*7 5∗5—>7∗7），然后可以得到输出也是 5 ∗ 5 5*5 5∗5
stride=2表示卷积过程每次移动步长为2
这段程序对上述结果进行验证：
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]
input = torch.Tensor(input).view(1, 1, 5, 5)
# padding
conv_layer1 = torch.nn.Conv2d(1, 1, kernel_size=3, padding=1, bias= False)
kernel = torch.Tensor([1,2,3,4,5,6,7,8,9]).view(1, 1, 3, 3)
conv_layer1.weight.data = kernel.data
output1 = conv_layer1(input)
print("output1：",output1)
# stride
conv_layer2 = torch.nn.Conv2d(1, 1, kernel_size=3, stride=2, bias= False)
kernel = torch.Tensor([1,2,3,4,5,6,7,8,9]).view(1, 1, 3, 3)
conv_layer2.weight.data = kernel.data
output2 = conv_layer2(input)
print("output2：",output2)
二、池化层
Max Pooling Layer：
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)
maxpooling_layer = torch.nn.MaxPool2d(kernel_size=2)
output = maxpooling_layer(input)
print(output)
三、MNIST分类
1.网络结构
2.CPU版本
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
# prepare dataset
batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
train_dataset = datasets.MNIST(root='', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='', 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 = self.pooling(F.relu(self.conv1(x)))
x = self.pooling(F.relu(self.conv2(x)))
x = x.view(batch_size, -1) # -1 此处自动算出的是320
x = self.fc(x)
return x
model = Net()
# 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
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: %.2f %% ' % (100 * correct / total))
if __name__ == '__main__':
for epoch in range(10):
train(epoch)
test()
3.GPU版本
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='', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='', 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") # 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: %.2f %% ' % (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.show()
部分结果：
可视化：
本文为系列文章：
| 上一篇 | 《Pytorch深度学习实践》目录 | 下一篇 |
|---|---|---|
| MNIST数据集多分类（Softmax Classifier） | 资料 | 卷积神经网络-高级篇（Advanced-Convolution Neural Network） |