一、IDE:Pycharm
1、生成数据集并绘制:
import random
import torch
from d2l import torch as d2l
import matplotlib.pyplot as plt
def synthetic_data(w,b,num_examples):
"""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()
plt.scatter(features[:,1].detach().numpy(),labels.detach().numpy(),1)
plt.show()
2、读取小批量:
# data_iter函数接收批量大小、特征矩阵和标签向量作为输入,生成大小为batch_size的小批量
def data_iter(batch_size,features,labels):
num_examples = len(features) # 样本个数
indices = list(range(num_examples)) # 样本索引
# 这些样本是随即读取的,没有特定的顺序
random.shuffle(indices) # 把索引随即打乱
for i in range(0, num_examples, batch_size):
batch_indices = torch.tensor(indices[i:min(i+batch_size,num_examples)]) # 当i+batch_size超出时,取num_examples
yield features[batch_indices], labels[batch_indices] # 获得随即顺序的特征,及对应的标签
batch_size = 10
for X,y in data_iter(batch_size, features, labels):
print(X, '\n', y) # 取一个批次后,就break跳出了
break
3、完整训练模型:
import torch
import random
from d2l import torch as d2l
import matplotlib.pyplot as plt
def synthetic_data(w,b,num_examples):
"""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()
plt.scatter(features[:,1].detach().numpy(),labels.detach().numpy(),1)
plt.show()
def data_iter(batch_size, features, labels):
num_examples = len(features) # 样本个数
indices = list(range(num_examples)) # 样本索引
# 这些样本是随即读取的,没有特定的顺序
random.shuffle(indices) # 把索引随即打乱
for i in range(0, num_examples, batch_size):
batch_indices = torch.tensor(
indices[i:min(i + batch_size, num_examples)]) # 当i+batch_size超出时,取num_examples
yield features[batch_indices], labels[batch_indices] # 获得随即顺序的特征,及对应的标签
batch_size = 10
for X, y in data_iter(batch_size, features, labels):
print(X, '\n', y) # 取一个批次后,就break跳出了
break
# 定义初始化模型参数
w = torch.normal(0, 0.01, size=(2, 1), requires_grad=True)
b = torch.zeros(1, requires_grad=True)
# 定义模型
def linreg(X, w, b):
"""线性回归模型"""
return torch.matmul(X, w) + b
# 定义损失函数
def squared_loss(y_hat, y):
"""均方损失"""
return (y_hat - y.reshape(y_hat.shape)) ** 2 / 2 # 将y统一成与y_hat一样同尺寸
# 定义优化算法
def sgd(params, lr, batch_size):
"""小批量随即梯度下降"""
with torch.no_grad(): # 不要产生梯度计算,减少内存消耗
for param in params: # 每个参数进行遍历
param -= lr * param.grad / batch_size # 每个参数进行更新,损失函数没有求均值,所以这里除以 batch_size 求了均值。由于乘法的线性关系,这里除以放在loss的除以是等价的。
param.grad.zero_() # 每个参数的梯度清零
# 训练过程
lr = 0.03
num_epochs = 3
net = linreg # 这里用线性模型,这样写是很方便net赋予其他模型,只需要改一处,不需要下面所有网络模型名称都改
loss = squared_loss
# 训练过程
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是形状是(batch_size,1),而不是一个标量。l中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}')
# 比较真实参数和通过训练学到的参数来评估训练的成功程度
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}')
4、使用pytorch框架完整训练模型:
import numpy as np
import torch
from torch.utils import data
from d2l import torch as d2l
from torch import nn
true_w = torch.tensor([2,-3.4])
true_b = 4.2
features, labels = d2l.synthetic_data(true_w,true_b,1000) # 库函数生成人工数据集
# 调用框架现有的API来读取数据
def load_array(data_arrays,batch_size,is_train=True):
"""构造一个Pytorch数据迭代器"""
dataset = data.TensorDataset(*data_arrays) # dataset相当于Pytorch的Dataset。一个星号*,表示对list解开入参。
return data.DataLoader(dataset,batch_size,shuffle=is_train) # 返回的是从dataset中随机挑选出batch_size个样本出来
batch_size = 10
data_iter = load_array((features,labels),batch_size) # 返回的数据的迭代器
print(next(iter(data_iter))) # iter(data_iter) 是一个迭代器对象,next是取迭代器里面的元素
# 使用框架的预定义好的层
# nn是神经网络的缩写
net = nn.Sequential(nn.Linear(2,1))
# 初始化模型参数
net[0].weight.data.normal_(0,0.01) # 使用正态分布替换掉weight变量里面的数据值
net[0].bias.data.fill_(0) # 偏差bias变量里面的值设置为0
print(net[0])
# 计算均方误差使用的是MSELoss类,也称为平方L2范数
loss = nn.MSELoss() #L1是算术差,L2是平方差
# 实例化SGD实例
trainer = torch.optim.SGD(net.parameters(),lr=0.03)
# 训练过程代码与从零开始时所做的非常相似
num_epochs = 3
for epoch in range(num_epochs):
for X, y in data_iter: # 从DataLoader里面一次一次把所有数据拿出来
# print("X:",X)
# print("y:",y)
l = loss(net(X),y) # net(X) 为计算出来的线性回归的预测值
trainer.zero_grad() # 梯度清零
l.backward()
trainer.step() # SGD优化器优化模型
l = loss(net(features),labels)
print(f'epoch{epoch+1},loss{l:f}')