模型基本操作

<!-- #include-env-start: D:/code/klc/test/share4ai/docs/book/dive_into_on_dl/cnn/basic -->
```python
# 解决 jupyter notebook Kernel Restarting内核崩溃
import os
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"

# 多层感知机（MLP）：通过堆叠多个“全连接层 + 非线性激活函数”，让网络能逐步提取更高层次的抽象特征。
import torch
from torch import nn
from torch.nn import functional as F

net = nn.Sequential(nn.Linear(20, 256), nn.ReLU(), nn.Linear(256, 10)) # 标准 MLP

X = torch.rand(2, 20)
net(X)

# 自定义块
class MLP(nn.Module):
    def __init__(self):
        super().__init__()
        self.hidden = nn.Linear(20, 256)
        self.out = nn.Linear(256, 10)

    def forward(self, X):
        return self.out(F.relu(self.hidden(X)))

net = MLP()
net(X)

# 顺序块
class MySequential(nn.Module):
    def __init__(self, *args):
        super().__init__()
        for block in args:
            self._modules[block] = block

    def forward(self, X):
        for block in self._modules.values():
            X = block(X)
        return X

net = MySequential(nn.Linear(20, 256), nn.ReLU(), nn.Linear(256, 10))
net(X)

<!-- #include-env-start: D:/code/klc/test/share4ai/docs/book/dive_into_on_dl/cnn/basic -->
```python
# 解决 jupyter notebook Kernel Restarting内核崩溃
import os
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"

# 参数管理
import torch
from torch import nn

net = nn.Sequential(nn.Linear(4, 8), nn.ReLU(), nn.Linear(8, 1))
X = torch.rand(size=(2, 4))
X, net(X)

# 参数访问
print(net[2].state_dict())

# 目标参数
print(type(net[2].bias))
print(net[2].bias)
print(net[2].bias.data)

net[2].weight.grad == None

# 一次性访问所有参数
print(*[(name, param.shape) for name, param in net.named_parameters()])

# 打印实际值
net.state_dict()['2.bias'].data

# 从嵌套块收集参数
def block1():
    return nn.Sequential(nn.Linear(4, 8), nn.ReLU(), nn.Linear(8, 4),
                         nn.ReLU())

def block2():
    net = nn.Sequential()
    for i in range(4):
        net.add_module(f'block {i}', block1())
    return net

rgnet = nn.Sequential(block2(), nn.Linear(4, 1))
rgnet(X)

print(rgnet)

# 内置初始化
def init_normal(m):
    if type(m) == nn.Linear:
        nn.init.normal_(m.weight, mean=0, std=0.01) # 使用正态分布（高斯分布） 初始化权重，均值 mean = 0，标准差 std = 0.01。_ 表示原地操作（in-place），提高效率
        nn.init.zeros_(m.bias)

net.apply(init_normal) # net.apply(fn) 是 nn.Module 的方法，会递归遍历网络中所有子模块，并对每个子模块调用 fn(module)。
net[0].weight.data[0], net[0].bias.data[0]

def init_constant(m):
    if type(m) == nn.Linear:
        nn.init.constant_(m.weight, 1)
        nn.init.zeros_(m.bias)

net.apply(init_constant)
net[0].weight.data[0], net[0].bias.data[0]

# 对某些块应用不同的初始化方法
def xavier(m):
    if type(m) == nn.Linear:
        nn.init.xavier_uniform_(m.weight) # 对线性层的权重使用 Xavier（Glorot）均匀初始化。

def init_42(m):
    if type(m) == nn.Linear:
        nn.init.constant_(m.weight, 42) # 常数初始化（固定值 42）

net[0].apply(xavier)
net[2].apply(init_42)
print(net[0].weight.data[0])
print(net[2].weight.data)

# 自定义初始化
def my_init(m):
    if type(m) == nn.Linear:
        print(
            "Init",
            *[(name, param.shape) for name, param in m.named_parameters()][0])
        nn.init.uniform_(m.weight, -10, 10) # 将权重 m.weight 原地初始化为从 Uniform(-10, 10) 分布中采样的值。
        m.weight.data *= m.weight.data.abs() >= 5 # 将绝对值小于 5 的权重置为 0，保留绝对值 ≥ 5 的权重

net.apply(my_init)
net[0].weight[:2]

net[0].weight.data[:] += 1
net[0].weight.data[0, 0] = 42
net[0].weight.data[0]

# 参数绑定
shared = nn.Linear(8, 8)
net = nn.Sequential(nn.Linear(4, 8), nn.ReLU(), shared, nn.ReLU(), shared,
                    nn.ReLU(), nn.Linear(8, 1))
net(X)
print(net[2].weight.data[0] == net[4].weight.data[0])
net[2].weight.data[0, 0] = 100
print(net[2].weight.data[0] == net[4].weight.data[0])

<!-- #include-env-start: D:/code/klc/test/share4ai/docs/book/dive_into_on_dl/cnn/basic -->
```python
# 解决 jupyter notebook Kernel Restarting内核崩溃
import os
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"

# 自定义层
# 构造一个没有任何参数的自定义层
import torch
import torch.nn.functional as F
from torch import nn

class CenteredLayer(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, X):
        return X - X.mean()

layer = CenteredLayer()
layer(torch.FloatTensor([1, 2, 3, 4, 5]))

# 将层作为组件合并到构建更复杂的模型中
net = nn.Sequential(nn.Linear(8, 128), CenteredLayer())

Y = net(torch.rand(4, 8))
Y.mean()

# 带参数的层
class MyLinear(nn.Module):
    def __init__(self, in_units, units):
        super().__init__()
        self.weight = nn.Parameter(torch.randn(in_units, units))
        self.bias = nn.Parameter(torch.randn(units,))

    def forward(self, X):
        linear = torch.matmul(X, self.weight.data) + self.bias.data
        return F.relu(linear)

linear = MyLinear(5, 3)
linear.weight

# 使用自定义层直接执行正向传播计算

<!-- #include-env-start: D:/code/klc/test/share4ai/docs/book/dive_into_on_dl/cnn/basic -->
```python
# 解决 jupyter notebook Kernel Restarting内核崩溃
import os
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"

# 读写文件
# 加载和保存张量

import torch
from torch import nn
from torch.nn import functional as F

x = torch.arange(4)
torch.save(x, 'x-file')

x2 = torch.load('x-file')
x2

# 存储一个张量列表，然后把它们读回内存
y = torch.zeros(4)
torch.save([x, y], 'x-files')
x2, y2 = torch.load('x-files')
(x2, y2)

# 写入或读取从字符串映射到张量的字典
mydict = {'x': x, 'y': y}
torch.save(mydict, 'mydict')
mydict2 = torch.load('mydict')
mydict2

# 加载和保存模型参数
class MLP(nn.Module):
    def __init__(self):
        super().__init__()
        self.hidden = nn.Linear(20, 256)
        self.output = nn.Linear(256, 10)

    def forward(self, x):
        return self.output(F.relu(self.hidden(x)))

net = MLP()
X = torch.randn(size=(2, 20))
Y = net(X)

# 将模型的参数存储为一个叫做“mlp.params”的文件
torch.save(net.state_dict(), 'mlp.params')

# 实例化了原始多层感知机模型的一个备份。 直接读取文件中存储的参数
clone = MLP()
clone.load_state_dict(torch.load('mlp.params'))
clone.eval()

Y_clone = clone(X)
Y_clone == Y