B站--刘二大人《PyTorch深度学习实践》完结合集 10.卷积神经网络(基础篇)
PPT 链接:网盘 提取码:cxe4
目录
1.基础知识
1.全连接网络
- 全连接层
前几节中用到的线性层,称为全连接层
线性层中的每一个输入节点都会参与到下一层任何一个输出节点的计算中
- 将全连接层连接在一起构成全连接网络
2.卷积神经网络基本构成![](https://i-blog.csdnimg.cn/blog_migrate/d29ee506a9e4d33a77a1d90d10d5d867.png)
- 卷积神经网络由特征提取器(feature extraction)、分类(classification)构成
- feature extraction :特征提取器,由下采样层和卷积层共同构成,对图像进行卷积运算
- classification: 由全连接层将输出转换成概率
3.图像
卷积神经网络中使用RGB图像,输入通道为3,输出通道等于卷积核的个数
单通道操作过程如图所示:
- 多通道
每个通道分别与kernel进行卷积运算,然后结果进行相加
- n*w*h--->m*w*h
卷积层代码示例:
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])
4.常见权重
- padding=1
代码示例:
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)
2.stride= 2 步长
代码示例:
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)
3.max pooling layer
- 2x2的max pooling layer 默认步长stride=2
- 找最大值,拼成新的矩阵
-
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) #步长stride也默认等于2 output = maxpooling_layer(input) print(output)
5.简单实现卷积神经网络
代码示例:
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()
参考链接:
pytorch 深度学习实践 第10讲 卷积神经网络(基础篇)_pytorch神经网络学习实践_会游泳的小雁的博客-CSDN博客