深度学习_线性神经网络

JamyJ

于 2022-06-22 08:26:37 发布

阅读量455

点赞数

本文链接：https://blog.csdn.net/weixin_42754174/article/details/125180021

版权

深度学习神经网络 python

%matplotlib inline
import random
import torch
from d2l import torch as d2l

def synthetic_data(w, b, num_examples):  #@save
    """生成y=Xw+b+噪声"""
    X = torch.normal(0, 1, (num_examples, len(w)))
    y = torch.matmul(X, w) + b
    y += torch.normal(0, 0.01, y.shape)
    return X, y.reshape((-1, 1))

true_w = torch.tensor([2, -3.4])
true_b = 4.2
features, labels = synthetic_data(true_w, true_b, 1000)

print('features:', features[0],'\nlabel:', labels[0])

d2l.set_figsize()
d2l.plt.scatter(features[:, 1].detach().numpy(), labels.detach().numpy(), 1)

def data_iter(batch_size, features, labels):
    num_examples = len(features)
    indices = list(range(num_examples))
    # 这些样本是随机读取的，没有特定的顺序
    random.shuffle(indices)
    for i in range(0, num_examples, batch_size):
        batch_indices = torch.tensor(
            indices[i: min(i + batch_size, num_examples)])
        yield features[batch_indices], labels[batch_indices]

batch_size = 10

for X, y in data_iter(batch_size, features, labels):
    print(X, '\n', y)
    break

w = torch.normal(0, 0.01, size=(2,1), requires_grad=True)
b = torch.zeros(1, requires_grad=True)

def linreg(X, w, b):  #@save
    """线性回归模型"""
    return torch.matmul(X, w) + b

def squared_loss(y_hat, y):  #@save
    """均方损失"""
    return (y_hat - y.reshape(y_hat.shape)) ** 2 / 2

def sgd(params, lr, batch_size):  #@save
    """小批量随机梯度下降"""
    with torch.no_grad():
        for param in params:
            param -= lr * param.grad / batch_size
            param.grad.zero_()

lr = 0.03
num_epochs = 3
net = linreg
loss = squared_loss

for epoch in range(num_epochs):
    for X, y in data_iter(batch_size, features, labels):
        l = loss(net(X, w, b), y)  # X和y的小批量损失
        # 因为l形状是(batch_size,1)，而不是一个标量。l中的所有元素被加到一起，
        # 并以此计算关于[w,b]的梯度
        l.sum().backward()
        sgd([w, b], lr, batch_size)  # 使用参数的梯度更新参数
    with torch.no_grad():
        train_l = loss(net(features, w, b), labels)
        print(f'epoch {epoch + 1}, loss {float(train_l.mean()):f}')

print(f'w的估计误差: {true_w - w.reshape(true_w.shape)}')
print(f'b的估计误差: {true_b - b}')

# 如果我们将权重初始化为零，会发生什么。算法仍然有效吗？
w = torch.zeros((2,1), requires_grad=True)
b = torch.zeros(1, requires_grad=True)

def linreg(X, w, b):  #@save
    """线性回归模型"""
    return torch.matmul(X, w) + b

def squared_loss(y_hat, y):  #@save
    """均方损失"""
    return (y_hat - y.reshape(y_hat.shape)) ** 2 / 2

def sgd(params, lr, batch_size):  #@save
    """小批量随机梯度下降"""
    with torch.no_grad():
        for param in params:
            param -= lr * param.grad / batch_size
            param.grad.zero_()
            
lr = 0.03
num_epochs = 3
net = linreg
loss = squared_loss

for epoch in range(num_epochs):
    for X, y in data_iter(batch_size, features, labels):
        l = loss(net(X, w, b), y)  # X和y的小批量损失
        # 因为l形状是(batch_size,1)，而不是一个标量。l中的所有元素被加到一起，
        # 并以此计算关于[w,b]的梯度
        l.sum().backward()
        sgd([w, b], lr, batch_size)  # 使用参数的梯度更新参数
    with torch.no_grad():
        train_l = loss(net(features, w, b), labels)
        print(f'epoch {epoch + 1}, loss {float(train_l.mean()):f}')
        
print(f'w的估计误差: {true_w - w.reshape(true_w.shape)}')
print(f'b的估计误差: {true_b - b}')

# 假设你是乔治·西蒙·欧姆，试图为电压和电流的关系建立一个模型。你能使用自动微分来学习模型的参数吗?
%matplotlib inline
import random
import torch
from d2l import torch as d2l

def synthetic_data_IU(r, b, numb_examples):  #@save
    """生成电压电流的关系式"""
    I = torch.rand(numb_examples,1)
    u = I*r.T + b
    return I, u.reshape((1, -1))

true_r = torch.tensor([2])
true_b = 0.2
features, labels = synthetic_data_IU(true_r, true_b, 1000)

def data_iter_IU(batch_size,features,labels):
    numb_examples = len(features)
    indices =list(range(numb_examples))
    random.shuffle(indices)
    for i in range(0,numb_examples,batch_size):
        batch_indices=torch.tensor(indices[i:min(i+batch_size,numb_examples)])
        yield features[batch_indices],labels[0,batch_indices]

batch_size =10
for I,u in data_iter_IU(batch_size,features,labels):
    print(I,'\n',u)
    break


r = torch.zeros(1 ,requires_grad=True)
b = torch.zeros(1, requires_grad=True)

def linreg(I, r, b):  
    '''线性回归模型。'''
    return I*r.T+b

def squared_loss(u_hat, u):
    '''均方损失。'''
    return (u_hat - u.reshape(u_hat.shape)) ** 2 / 2


def sgd(params, lr, batch_size):  
    '''小批量随机梯度下降。'''
    with torch.no_grad():
        for param in params:
            param -= lr * param.grad / batch_size
            param.grad.zero_()


lr = 0.03
num_epochs = 3
net = linreg
loss = squared_loss

for epoch in range(num_epochs):
    for I, u in data_iter_IU(batch_size, features, labels):
        l = loss(net(I, r, b), u)  
        l.sum().backward()
        sgd([r, b], lr, batch_size)  # 使用参数的梯度更新参数
    with torch.no_grad():
        train_l = loss(net(features, r, b), labels)
        print(f'epoch {epoch + 1}, loss {float(train_l.mean()):f}')


print(f'w的估计误差: {true_r - r.reshape(true_r.shape)}')
print(f'b的估计误差: {true_b - b}')

# 尝试使用不同的学习率，观察损失函数值下降的快慢

lr = 0.0003
num_epochs = 3
net = linreg
loss = squared_loss

for epoch in range(num_epochs):
    for I, u in data_iter_IU(batch_size, features, labels):
        l = loss(net(I, r, b), u)  
        l.sum().backward()
        sgd([r, b], lr, batch_size)  # 使用参数的梯度更新参数
    with torch.no_grad():
        train_l = loss(net(features, r, b), labels)
        print(f'epoch {epoch + 1}, loss {float(train_l.mean()):f}')


print(f'w的估计误差: {true_r - r.reshape(true_r.shape)}')
print(f'b的估计误差: {true_b - b}')

# 尝试使用不同的学习率，观察损失函数值下降的快慢
lr = 3
num_epochs = 3
net = linreg
loss = squared_loss

for epoch in range(num_epochs):
    for I, u in data_iter_IU(batch_size, features, labels):
        l = loss(net(I, r, b), u)  
        l.sum().backward()
        sgd([r, b], lr, batch_size)  # 使用参数的梯度更新参数
    with torch.no_grad():
        train_l = loss(net(features, r, b), labels)
        print(f'epoch {epoch + 1}, loss {float(train_l.mean()):f}')


print(f'w的估计误差: {true_r - r.reshape(true_r.shape)}')
print(f'b的估计误差: {true_b - b}')

线性回归的简洁实现

import numpy as np
import torch
from torch.utils import data
from d2l import torch as d2l

# 生成数据集
true_w = torch.tensor([2, -3.4])
true_b = 4.2
features, labels = d2l.synthetic_data(true_w, true_b, 1000)

# 读取数据集
def load_array(data_arrays, batch_size, is_train=True):  #@save
    """构造一个PyTorch数据迭代器"""
    dataset = data.TensorDataset(*data_arrays)
    return data.DataLoader(dataset, batch_size, shuffle=is_train)

batch_size = 10
data_iter = load_array((features, labels), batch_size)

next(iter(data_iter))

# 定义模型
# nn是神经网络的缩写
from torch import nn

net = nn.Sequential(nn.Linear(2, 1))

net[0].weight.data.normal_(0, 0.01)
net[0].bias.data.fill_(0)

# 定义损失函数
loss = nn.MSELoss()
loss1 =  nn.L1Loss()

# 定义优化算法
trainer = torch.optim.SGD(net.parameters(), lr=0.03)

# 训练模型
num_epochs = 3
for epoch in range(num_epochs):
    for X, y in data_iter:
        l = loss(net(X) ,y)
        trainer.zero_grad()
        l.backward()
        trainer.step()
    l = loss(net(features), labels)
    print(f'epoch {epoch + 1}, loss {l:f}')

w = net[0].weight.data
print('w的估计误差：', true_w - w.reshape(true_w.shape))
b = net[0].bias.data
print('b的估计误差：', true_b - b)

# 如果将小批量的总损失替换为小批量损失的平均值，你需要如何更改学习率？
# 定义优化算法
optimizer = torch.optim.SGD(net.parameters(), lr=0.0001)
# 训练模型
num_epochs = 3
for epoch in range(num_epochs):
    for X, y in data_iter:
        l = loss1(net(X) ,y)
        optimizer.zero_grad()
        l.backward()
        optimizer.step()
    l = loss1(net(features), labels)
    print(f'epoch {epoch + 1}, loss {l:f}')