python

关注公众号 jb51net

关闭
首页 > 脚本专栏 > python > PyTorch torch.nn模块

PyTorch中torch.nn模块的实现

作者：pumpkin84514

torch.nn是PyTorch中用于构建神经网络的核心模块,包括多种组件,每个组件都有其特定的原理和使用场景,本文就来详细的介绍一下如何使用,感兴趣的可以了解一下

torch.nn 是 PyTorch 中专门用于构建和训练神经网络的模块。它的整体架构分为几个主要部分，每部分的原理、要点和使用场景如下：

1. nn.Module

原理和要点：nn.Module 是所有神经网络组件的基类。任何神经网络模型都应该继承 nn.Module，并实现其 forward 方法。

使用场景：用于定义和管理神经网络模型，包括层、损失函数和自定义的前向传播逻辑。

主要 API 和使用场景：

import torch
import torch.nn as nn

class MyModel(nn.Module):
    def __init__(self):
        super(MyModel, self).__init__()
        self.linear = nn.Linear(10, 1)
    
    def forward(self, x):
        return self.linear(x)

model = MyModel()
print(model)

2. Layers（层）

2.1 nn.Linear（全连接层）

linear = nn.Linear(10, 5)
input = torch.randn(1, 10)
output = linear(input)
print(output)

2.2 nn.Conv2d（二维卷积层）

conv = nn.Conv2d(in_channels=1, out_channels=3, kernel_size=3)
input = torch.randn(1, 1, 5, 5)
output = conv(input)
print(output)

2.3 nn.MaxPool2d（二维最大池化层）

maxpool = nn.MaxPool2d(kernel_size=2)
input = torch.randn(1, 1, 4, 4)
output = maxpool(input)
print(output)

3. Loss Functions（损失函数）

3.1 nn.MSELoss（均方误差损失）

mse_loss = nn.MSELoss()
input = torch.randn(3, 5)
target = torch.randn(3, 5)
loss = mse_loss(input, target)
print(loss)

3.2 nn.CrossEntropyLoss（交叉熵损失）

cross_entropy_loss = nn.CrossEntropyLoss()
input = torch.randn(3, 5)
target = torch.tensor([1, 0, 4])
loss = cross_entropy_loss(input, target)
print(loss)

4. Optimizers（优化器）

4.1 torch.optim.SGD（随机梯度下降）

import torch.optim as optim

model = MyModel()
optimizer = optim.SGD(model.parameters(), lr=0.01)
criterion = nn.MSELoss()

# Training loop
for epoch in range(100):
    optimizer.zero_grad()
    output = model(torch.randn(1, 10))
    loss = criterion(output, torch.randn(1, 1))
    loss.backward()
    optimizer.step()

4.2 torch.optim.Adam（自适应矩估计）

optimizer = optim.Adam(model.parameters(), lr=0.001)
# Training loop
for epoch in range(100):
    optimizer.zero_grad()
    output = model(torch.randn(1, 10))
    loss = criterion(output, torch.randn(1, 1))
    loss.backward()
    optimizer.step()

5. Activation Functions（激活函数）

5.1 nn.ReLU（修正线性单元）

relu = nn.ReLU()
input = torch.randn(2)
output = relu(input)
print(output)

6. Normalization Layers（归一化层）

6.1 nn.BatchNorm2d（二维批量归一化）

batch_norm = nn.BatchNorm2d(3)
input = torch.randn(1, 3, 5, 5)
output = batch_norm(input)
print(output)

7. Dropout Layers（丢弃层）

7.1 nn.Dropout

dropout = nn.Dropout(p=0.5)
input = torch.randn(2, 3)
output = dropout(input)
print(output)

8. Container Modules（容器模块）

8.1 nn.Sequential（顺序容器）

model = nn.Sequential(
    nn.Linear(10, 20),
    nn.ReLU(),
    nn.Linear(20, 5)
)
input = torch.randn(1, 10)
output = model(input)
print(output)

8.2 nn.ModuleList（模块列表）

layers = nn.ModuleList([
    nn.Linear(10, 20),
    nn.ReLU(),
    nn.Linear(20, 5)
])

input = torch.randn(1, 10)
for layer in layers:
    input = layer(input)
print(input)

9. Functional API (torch.nn.functional)

9.1 F.relu（ReLU 激活函数）

import torch.nn.functional as F

input = torch.randn(2)
output = F.relu(input)
print(output)

9.2 F.cross_entropy（交叉熵损失函数）

input = torch.randn(3, 5)
target = torch.tensor([1, 0, 4])
loss = F.cross_entropy(input, target)
print(loss)

9.3 F.conv2d（二维卷积）

input = torch.randn(1, 1, 5, 5)
weight = torch.randn(3, 1, 3, 3)  # Manually defined weights
output = F.conv2d(input, weight)
print(output)

10. Parameter (torch.nn.Parameter)

示例代码：

class MyModelWithParam(nn.Module):
    def __init__(self):
        super(MyModelWithParam, self).__init__()
        self.my_param = nn.Parameter(torch.randn(10, 10))
    
    def forward(self, x):
        return x @ self.my_param

model = MyModelWithParam()
input = torch.randn(1, 10)
output = model(input)
print(output)

# 查看模型参数
for name, param in model.named_parameters():
    print(name, param.size())

综合示例

下面是一个结合上述各个部分的综合示例：

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

class MyComplexModel(nn.Module):
    def __init__(self):
        super(MyComplexModel, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3)
        self.bn1 = nn.BatchNorm2d(32)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3)
        self.bn2 = nn.BatchNorm2d(64)
        self.dropout = nn.Dropout(0.25)
        self.fc1 = nn.Linear(64*12*12, 128)
        self.fc2 = nn.Linear(128, 10)
        self.custom_param = nn.Parameter(torch.randn(128, 128))

    def forward(self, x):
        x = F.relu(self

.bn1(self.conv1(x)))
        x = F.max_pool2d(x, 2)
        x = F.relu(self.bn2(self.conv2(x)))
        x = F.max_pool2d(x, 2)
        x = self.dropout(x)
        x = x.view(x.size(0), -1)
        x = F.relu(self.fc1(x))
        x = x @ self.custom_param
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

model = MyComplexModel()
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

for epoch in range(10):
    optimizer.zero_grad()
    input = torch.randn(64, 1, 28, 28)
    target = torch.randint(0, 10, (64,))
    output = model(input)
    loss = criterion(output, target)
    loss.backward()
    optimizer.step()
    print(f'Epoch {epoch+1}, Loss: {loss.item()}')

通过以上示例，可以更清晰地理解 torch.nn 模块的整体架构、原理、要点及其具体使用场景。

到此这篇关于PyTorch中torch.nn模块的实现的文章就介绍到这了,更多相关PyTorch torch.nn模块内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家！

您可能感兴趣的文章:
阅读全文