Introduction to Machine Learning - PyTorch | Original

Home 2025.08

This post was originally written in Chinese. It has been translated to English to facilitate further translations into other languages.

PyTorch

Let’s install it. This supports Python version 3.9.

$ pip install torch torchvision
Collecting torch
  Downloading torch-1.8.0-cp39-none-macosx_10_9_x86_64.whl (120.6 MB)
     |████████████████████████████████| 120.6 MB 224 kB/s
Collecting torchvision
  Downloading torchvision-0.9.0-cp39-cp39-macosx_10_9_x86_64.whl (13.1 MB)
     |████████████████████████████████| 13.1 MB 549 kB/s
Requirement already satisfied: numpy in /usr/local/lib/python3.9/site-packages (from torch) (1.20.1)
Collecting typing-extensions
  Downloading typing_extensions-3.7.4.3-py3-none-any.whl (22 kB)
Requirement already satisfied: pillow>=4.1.1 in /usr/local/lib/python3.9/site-packages (from torchvision) (8.0.1)
Installing collected packages: typing-extensions, torch, torchvision
Successfully installed torch-1.8.0 torchvision-0.9.0 typing-extensions-3.7.4.3

Let’s verify it.

import torch
x = torch.rand(5, 3)
print(x)

An error occurred.

Traceback (most recent call last):
  File "torch.py", line 1, in <module>
    import torch
  File "torch.py", line 2, in <module>
    x = torch.rand(5, 3)
AttributeError: partially initialized module 'torch' has no attribute 'rand' (most likely due to a circular import)

After googling this error message, it turns out our file was also named torch, causing a naming conflict. After renaming it, it works correctly.

tensor([[0.5520, 0.9446, 0.5543],
        [0.6192, 0.0908, 0.8726],
        [0.0223, 0.7685, 0.9814],
        [0.4019, 0.5406, 0.3861],
        [0.5485, 0.6040, 0.2387]])

Let’s find an example.

# -*- coding: utf-8 -*-

import torch
import math
dtype = torch.float
device = torch.device("cpu")
# device = torch.device("cuda:0") # Uncomment this to run on GPU

# Create random input and output data
x = torch.linspace(-math.pi, math.pi, 2000, device=device, dtype=dtype)
y = torch.sin(x)

# Randomly initialize weights
a = torch.randn((), device=device, dtype=dtype)
b = torch.randn((), device=device, dtype=dtype)
c = torch.randn((), device=device, dtype=dtype)
d = torch.randn((), device=device, dtype=dtype)

learning_rate = 1e-6
for t in range(2000):
    # Forward pass: compute predicted y
    y_pred = a + b * x + c * x ** 2 + d * x ** 3

    # Compute and print loss
    loss = (y_pred - y).pow(2).sum().item()
    if t % 100 == 99:
        print(t, loss)

    # Backprop to compute gradients of a, b, c, d with respect to loss
    grad_y_pred = 2.0 * (y_pred - y)
    grad_a = grad_y_pred.sum()
    grad_b = (grad_y_pred * x).sum()
    grad_c = (grad_y_pred * x ** 2).sum()
    grad_d = (grad_y_pred * x ** 3).sum()

    # Update weights using gradient descent
    a -= learning_rate * grad_a
    b -= learning_rate * grad_b
    c -= learning_rate * grad_c
    d -= learning_rate * grad_d
print(f'Result: y = {a.item()} + {b.item()} x + {c.item()} x^2 + {d.item()} x^3')

Let’s run it.

99 1273.537353515625
199 849.24853515625
299 567.4786987304688
399 380.30291748046875
499 255.92752075195312
599 173.2559814453125
699 118.2861328125
799 81.72274780273438
899 57.39331817626953
999 41.198158264160156
1099 30.41307830810547
1199 23.227672576904297
1299 18.438262939453125
1399 15.244369506835938
1499 13.113286972045898
1599 11.690631866455078
1699 10.740333557128906
1799 10.105220794677734
1899 9.6804780960083
1999 9.39621353149414
Result: y = -0.011828352697193623 + 0.8360244631767273 x + 0.002040589228272438 x^2 + -0.09038365632295609 x^3

Let’s look at code using only the numpy library.

# -*- coding: utf-8 -*-
import numpy as np
import math

# Create random input and output data
x = np.linspace(-math.pi, math.pi, 2000)
y = np.sin(x)

# Randomly initialize weights
a = np.random.randn()
b = np.random.randn()
c = np.random.randn()
d = np.random.randn()

learning_rate = 1e-6
for t in range(2000):
    # Forward pass: compute predicted y
    # y = a + b x + c x^2 + d x^3
    y_pred = a + b * x + c * x ** 2 + d * x ** 3

    # Compute and print loss
    loss = np.square(y_pred - y).sum()
    if t % 100 == 99:
        print(t, loss)

    # Backprop to compute gradients of a, b, c, d with respect to loss
    grad_y_pred = 2.0 * (y_pred - y)
    grad_a = grad_y_pred.sum()
    grad_b = (grad_y_pred * x).sum()
    grad_c = (grad_y_pred * x ** 2).sum()
    grad_d = (grad_y_pred * x ** 3).sum()

    # Update weights
    a -= learning_rate * grad_a
    b -= learning_rate * grad_b
    c -= learning_rate * grad_c
    d -= learning_rate * grad_d

print(f'Result: y = {a} + {b} x + {c} x^2 + {d} x^3')

Notice that these are two different ways to perform calculations.

In these examples, a set of x and y values is first generated. Then, it’s assumed to be a cubic equation. Next, some methods are used to iteratively calculate the coefficients. What are these algorithms? Notice that it loops 2000 times, becoming more precise with each iteration. We won’t delve into the details here.

Finally

Currently, we don’t understand how machine learning calculations work behind the scenes. However, that’s not important for now. With the knowledge above, we can already do many things. Machine learning can also be used to process text, audio, and more. After exploring dozens of examples, it won’t be too late to learn the theory.

Exercises

Back Donate