Implementation of linear regression model in Python task 1

Linear regression belongs to regression model, i.e. it assumes that the output and input of the model are time-linear.

First, import dependencies

import torch
from torch import nn
import numpy as np


Generate part of data set randomly

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)

Read data set

import 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

Check the basic information of the data, where X is the characteristic column of the data and y is the label of the data.

for X, y in data_iter:
    print(X, '\n', y)

Definition model

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)

# 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))
          # ......


Initialize parameters of the model

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]` to modify it directly

for param in net.parameters():

The parameters are as follows

Define loss function

loss = nn.MSELoss()    # nn built-in squared loss function
                       # function prototype: `torch.nn.MSELoss(size_average=None, reduce=None, reduction='mean')`

Define optimization function

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)`

Related parameters of optimization function

Training. Only three generations have been trained here

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()
    print('epoch %d, loss: %f' % (epoch, l.item()))

Finally, the comparison of results

# result comparision
dense = net[0]

The content comes from the hands-on learning of Boyu platform

Published 3 original articles, won praise 3, visited 2338
Private letter follow

Tags: network

Posted on Fri, 14 Feb 2020 10:32:25 -0500 by skyriders