注:本文主要是对伯禹教育平台线性回归课程总结学习用
矢量直接计算比起简单for循环速度快更简洁,python中的广播学习很重要。
# import packages and modules
%matplotlib inline
import torch
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random
print(torch.__version__)
num_inputs = 2 #特征个数
num_examples = 1000 #样本个数
true_w = [2, -3.4] #已知模型参数的真实值
true_b = 4.2
#模型输入:样本和其特征的矩阵
features = torch.randn(num_examples, num_inputs,dtype=torch.float32)
#利用已知参数和输入矩阵计算真实值
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] +true_b
#真实值不可能完全符合线性模型,加上通过正态分布随机生成的偏置值
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()),
dtype=torch.float32)
可通过图像展示生成的数据
plt.scatter(features[:, 1].numpy(), labels.numpy(), 1);
def data_iter(batch_size, features, labels):
num_examples = len(features)
indices = list(range(num_examples))
random.shuffle(indices) # random read 10 samples
for i in range(0, num_examples, batch_size):
j = torch.LongTensor(indices[i: min(i + batch_size, num_examples)]) # the last time may be not enough for a whole batch
#index_select方法中0是维度:行,j是索引
yield features.index_select(0, j), labels.index_select(0, j)
w = torch.tensor(np.random.normal(0, 0.01, (num_inputs, 1)), dtype=torch.float32)
b = torch.zeros(1, dtype=torch.float32)
w.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)
def linreg(X, w, b):
return torch.mm(X, w) + b
def squared_loss(y_hat, y):
return (y_hat - y.view(y_hat.size())) ** 2 / 2
def sgd(params, lr, batch_size):
for param in params:
param.data -= lr * param.grad / batch_size # ues .data to operate param without gradient track
# super parameters init
lr = 0.03 #学习率
num_epochs = 5 #迭代次数
batch_size = 10 #批量大小
net = linreg #网络即线性回归模型
loss = squared_loss #损失函数
# training
for epoch in range(num_epochs): # training repeats num_epochs times
# in each epoch, all the samples in dataset will be used once
# X is the feature and y is the label of a batch sample
for X, y in data_iter(batch_size, features, labels):
l = loss(net(X, w, b), y).sum()
# calculate the gradient of batch sample loss
l.backward()
# using small batch random gradient descent to iter model parameters
sgd([w, b], lr, batch_size)
# reset parameter gradient
w.grad.data.zero_() #参数清零
b.grad.data.zero_()
train_l = loss(net(features, w, b), labels)
print('epoch %d, loss %f' % (epoch + 1, train_l.mean().item()))
注:将训练好的参数与真实参数比较
w, true_w, b, true_b
import torch
from torch import nn
import numpy as np
torch.manual_seed(1)
print(torch.__version__)
torch.set_default_tensor_type('torch.FloatTensor')
num_inputs = 2
num_examples = 1000
true_w = [2, -3.4]
true_b = 4.2
features = torch.tensor(np.random.normal(0, 1, (num_examples, num_inputs)), dtype=torch.float)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)
import torch.utils.data as Data
batch_size = 10
# combine featues and labels of dataset
dataset = Data.TensorDataset(features, labels)
# put dataset into DataLoader
data_iter = Data.DataLoader(
dataset=dataset, # torch TensorDataset format
batch_size=batch_size, # mini batch size
shuffle=True, # whether shuffle the data or not
num_workers=2, # read data in multithreading
)
class LinearNet(nn.Module):
def __init__(self, n_feature):
super(LinearNet, self).__init__() # call father function to init
self.linear = nn.Linear(n_feature, 1) # function prototype: `torch.nn.Linear(in_features, out_features, bias=True)`
def forward(self, x):
y = self.linear(x)
return y
net = LinearNet(num_inputs)
print(net)
注:初始化多层网络三种方法
# ways to init a multilayer network
# method one
net = nn.Sequential(
nn.Linear(num_inputs, 1)
# other layers can be added here
)
# method two
net = nn.Sequential()
net.add_module('linear', nn.Linear(num_inputs, 1))
# net.add_module ......
# method three
from collections import OrderedDict
net = nn.Sequential(OrderedDict([
('linear', nn.Linear(num_inputs, 1))
# ......
]))
print(net)
print(net[0])
from torch.nn import init
init.normal_(net[0].weight, mean=0.0, std=0.01)
init.constant_(net[0].bias, val=0.0) # or you can use `net[0].bias.data.fill_(0)` to modify it directly
loss = nn.MSELoss() # nn built-in squared loss function
# function prototype: `torch.nn.MSELoss(size_average=None, reduce=None, reduction='mean')`
import torch.optim as optim
optimizer = optim.SGD(net.parameters(), lr=0.03) # built-in random gradient descent function
print(optimizer) # function prototype: `torch.optim.SGD(params, lr=, momentum=0, dampening=0, weight_decay=0, nesterov=False)`
num_epochs = 3
for epoch in range(1, num_epochs + 1):
for X, y in data_iter:
output = net(X)
l = loss(output, y.view(-1, 1))
optimizer.zero_grad() # reset gradient, equal to net.zero_grad()
l.backward()
optimizer.step()
print('epoch %d, loss: %f' % (epoch, l.item()))
注:与真实参数比较
# result comparision
dense = net[0]
print(true_w, dense.weight.data)
print(true_b, dense.bias.data)