赞
踩
第一章 python训练线性模型实战
第二章 python训练决策树模型实战
第三章 python训练神经网络模型实战
第四章 python训练支持向量机模型实战
第五章 python训练贝叶斯分类器模型实战
第六章 python训练集成学习模型实战
第七章 python训练聚类模型实战
第八章 python训练KNN模型实战
第九章 python训练CNN模型实战
第十章 python训练RNN模型实战
......(会一直更新)
目录
训练CNN模型的步骤如下:
可以在各种网站上下载图像数据集,例如 CIFAR10 和 ImageNet。以使用的 CIFAR10 数据集为例,具体步骤如下:
- 安装 torchvision 库:使用以下命令安装 torchvision 库。
- ``` python
- !pip install torchvision
- ```
如果你使用的是 conda,可以使用以下命令来安装 torchvision 库。
- ``` python
- !conda install torchvision -c pytorch
- ```
- 加载数据集:使用以下代码来加载 CIFAR10 数据集。
- ``` python
-
- import torch
-
- import torchvision.datasets as datasets
-
-
-
- # 加载数据集
-
- train_data = datasets.CIFAR10(root='./data', train=True, download=True)
-
- test_data = datasets.CIFAR10(root='./data', train=False, download=True)
-
-
-
- # 将数据转换为 PyTorch 的张量格式
-
- train_data = torch.utils.data.DataLoader(train_data, batch_size=64, shuffle=True)
-
- test_data = torch.utils.data.DataLoader(test_data, batch_size=64, shuffle=True)
-
- ```
在本例中,我们定义了一个包含三个卷积层和两个全连接层的 CNN 模型,以处理 3 通道的 32x32 图像。
-
- ``` python
-
- import torch.nn as nn
-
-
-
- class Net(nn.Module):
-
- def __init__(self):
-
- super(Net, self).__init__()
-
-
-
- # 定义卷积层
-
- self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1)
-
- self.conv2 = nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1)
-
- self.conv3 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
-
-
-
- # 定义全连接层
-
- self.fc1 = nn.Linear(64 * 4 * 4, 500)
-
- self.fc2 = nn.Linear(500, 10)
-
-
-
- def forward(self, x):
-
-
-
- # 卷积层
-
- x = self.conv1(x)
-
- x = nn.functional.relu(x)
-
- x = nn.functional.max_pool2d(x, 2)
-
-
-
- x = self.conv2(x)
-
- x = nn.functional.relu(x)
-
- x = nn.functional.max_pool2d(x, 2)
-
-
-
- x = self.conv3(x)
-
- x = nn.functional.relu(x)
-
- x = nn.functional.max_pool2d(x, 2)
-
-
-
- # 全连接层
-
- x = x.view(-1, 64 * 4 * 4)
-
- x = self.fc1(x)
-
- x = nn.functional.relu(x)
-
- x = self.fc2(x)
-
-
-
- return x
-
-
-
- # 创建模型实例
-
- model = Net()
-
- ```
训练 CNN 模型的代码如下所示:
-
- ``` python
-
- import torch.optim as optim
-
-
-
- # 定义优化器和损失函数
-
- criterion = nn.CrossEntropyLoss()
-
- optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)
-
-
-
- # 训练模型
-
- for epoch in range(10): # 训练 10 次
-
- running_loss = 0.0
-
- for i, data in enumerate(train_data, 0):
-
- # 获取输入
-
- inputs, labels = data
-
-
-
- # 梯度清零
-
- optimizer.zero_grad()
-
-
-
- # 前向传播,反向传播,优化器更新参数
-
- outputs = model(inputs)
-
- loss = criterion(outputs, labels)
-
- loss.backward()
-
- optimizer.step()
-
-
-
- # 输出统计信息
-
- running_loss += loss.item()
-
- if i % 100 == 99:
-
- print('[%d, %5d] loss: %.3f' %
-
- (epoch + 1, i + 1, running_loss / 100))
-
- running_loss = 0.0
-
- print('Finished Training')
-
- ```
对测试集进行推理并计算准确率。
-
- ``` python
-
- correct = 0
-
- total = 0
-
- with torch.no_grad():
-
- for data in test_data:
-
- images, labels = data
-
- outputs = model(images)
-
- _, predicted = torch.max(outputs.data, 1)
-
- total += labels.size(0)
-
- correct += (predicted == labels).sum().item()
-
-
-
- print('Accuracy of the network on the 10000 test images: %d %%' % (
-
- 100 * correct / total))
-
- ```
-
- ``` python
-
- import torch
-
- import torch.nn as nn
-
- import torch.optim as optim
-
- import torchvision.datasets as datasets
-
-
-
- # 加载数据集
-
- train_data = datasets.CIFAR10(root='./data', train=True, download=True)
-
- test_data = datasets.CIFAR10(root='./data', train=False, download=True)
-
-
-
- # 将数据转换为 PyTorch 的张量格式
-
- train_data = torch.utils.data.DataLoader(train_data, batch_size=64, shuffle=True)
-
- test_data = torch.utils.data.DataLoader(test_data, batch_size=64, shuffle=True)
-
-
-
- # 定义 CNN 模型
-
- class Net(nn.Module):
-
- def __init__(self):
-
- super(Net, self).__init__()
-
-
-
- # 定义卷积层
-
- self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1)
-
- self.conv2 = nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1)
-
- self.conv3 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
-
-
-
- # 定义全连接层
-
- self.fc1 = nn.Linear(64 * 4 * 4, 500)
-
- self.fc2 = nn.Linear(500, 10)
-
-
-
- def forward(self, x):
-
-
-
- # 卷积层
-
- x = self.conv1(x)
-
- x = nn.functional.relu(x)
-
- x = nn.functional.max_pool2d(x, 2)
-
-
-
- x = self.conv2(x)
-
- x = nn.functional.relu(x)
-
- x = nn.functional.max_pool2d(x, 2)
-
-
-
- x = self.conv3(x)
-
- x = nn.functional.relu(x)
-
- x = nn.functional.max_pool2d(x, 2)
-
-
-
- # 全连接层
-
- x = x.view(-1, 64 * 4 * 4)
-
- x = self.fc1(x)
-
- x = nn.functional.relu(x)
-
- x = self.fc2(x)
-
-
-
- return x
-
-
-
- # 创建模型实例
-
- model = Net()
-
-
-
- # 定义优化器和损失函数
-
- criterion = nn.CrossEntropyLoss()
-
- optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)
-
-
-
- # 训练模型
-
- for epoch in range(10): # 训练 10 次
-
- running_loss = 0.0
-
- for i, data in enumerate(train_data, 0):
-
- # 获取输入
-
- inputs, labels = data
-
-
-
- # 梯度清零
-
- optimizer.zero_grad()
-
-
-
- # 前向传播,反向传播,优化器更新参数
-
- outputs = model(inputs)
-
- loss = criterion(outputs, labels)
-
- loss.backward()
-
- optimizer.step()
-
-
-
- # 输出统计信息
-
- running_loss += loss.item()
-
- if i % 100 == 99:
-
- print('[%d, %5d] loss: %.3f' %
-
- (epoch + 1, i + 1, running_loss / 100))
-
- running_loss = 0.0
-
- print('Finished Training')
-
-
-
- # 测试模型
-
- correct = 0
-
- total = 0
-
- with torch.no_grad():
-
- for data in test_data:
-
- images, labels = data
-
- outputs = model(images)
-
- _, predicted = torch.max(outputs.data, 1)
-
- total += labels.size(0)
-
- correct += (predicted == labels).sum().item()
-
-
-
- print('Accuracy of the network on the 10000 test images: %d %%' % (
-
- 100 * correct / total))
-
- ```
[[1](https://www.python.org/)]
[[2](https://zhuanlan.zhihu.com/p/344562609)]
大家觉得有帮助的话还请大家给个收藏关注鼓励一下,有什么问题评论区留言,看到会恢复哒~
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。