๐ŸŽฏLand Your Dream Jobโ€ข500+ Mock Interviews
โœจTransform Your Tasks with AIโ€ขGet 3x more done

PyTorch for Deep Learning & Machine Learning โ€“ Full Course

By - freeCodeCamp.org

๐Ÿ“š Course Information

Channel

freeCodeCamp.org

Published On

10/6/2022

๐Ÿ“ Description

Learn PyTorch for deep learning in this comprehensive course for beginners. PyTorch is a machine learning framework written in Python. โœ๏ธ Daniel Bourke developed this course. Check out his channel: https://www.youtube.com/channel/UCr8O8l5cCX85Oem1d18EezQ ๐Ÿ”— Code: https://github.com/mrdbourke/pytorch-deep-learning ๐Ÿ”— Ask a question: https://github.com/mrdbourke/pytorch-deep-learning/discussions ๐Ÿ”— Course materials online: https://learnpytorch.io ๐Ÿ”— Full course on Zero to Mastery (20+ hours more video): https://dbourke.link/ZTMPyTorch Some sections below have been left out because of the YouTube limit for timestamps. 0:00:00 Introduction ๐Ÿ›  Chapter 0 โ€“ PyTorch Fundamentals 0:01:45 0. Welcome and "what is deep learning?" 0:07:41 1. Why use machine/deep learning? 0:11:15 2. The number one rule of ML 0:16:55 3. Machine learning vs deep learning 0:23:02 4. Anatomy of neural networks 0:32:24 5. Different learning paradigms 0:36:56 6. What can deep learning be used for? 0:43:18 7. What is/why PyTorch? 0:53:33 8. What are tensors? 0:57:52 9. Outline 1:03:56 10. How to (and how not to) approach this course 1:09:05 11. Important resources 1:14:28 12. Getting setup 1:22:08 13. Introduction to tensors 1:35:35 14. Creating tensors 1:54:01 17. Tensor datatypes 2:03:26 18. Tensor attributes (information about tensors) 2:11:50 19. Manipulating tensors 2:17:50 20. Matrix multiplication 2:48:18 23. Finding the min, max, mean & sum 2:57:48 25. Reshaping, viewing and stacking 3:11:31 26. Squeezing, unsqueezing and permuting 3:23:28 27. Selecting data (indexing) 3:33:01 28. PyTorch and NumPy 3:42:10 29. Reproducibility 3:52:58 30. Accessing a GPU 4:04:49 31. Setting up device agnostic code ๐Ÿ—บ Chapter 1 โ€“ PyTorch Workflow 4:17:27 33. Introduction to PyTorch Workflow 4:20:14 34. Getting setup 4:27:30 35. Creating a dataset with linear regression 4:37:12 36. Creating training and test sets (the most important concept in ML) 4:53:18 38. Creating our first PyTorch model 5:13:41 40. Discussing important model building classes 5:20:09 41. Checking out the internals of our model 5:30:01 42. Making predictions with our model 5:41:15 43. Training a model with PyTorch (intuition building) 5:49:31 44. Setting up a loss function and optimizer 6:02:24 45. PyTorch training loop intuition 6:40:05 48. Running our training loop epoch by epoch 6:49:31 49. Writing testing loop code 7:15:53 51. Saving/loading a model 7:44:28 54. Putting everything together ๐Ÿคจ Chapter 2 โ€“ Neural Network Classification 8:32:00 60. Introduction to machine learning classification 8:41:42 61. Classification input and outputs 8:50:50 62. Architecture of a classification neural network 9:09:41 64. Turing our data into tensors 9:25:58 66. Coding a neural network for classification data 9:43:55 68. Using torch.nn.Sequential 9:57:13 69. Loss, optimizer and evaluation functions for classification 10:12:05 70. From model logits to prediction probabilities to prediction labels 10:28:13 71. Train and test loops 10:57:55 73. Discussing options to improve a model 11:27:52 76. Creating a straight line dataset 11:46:02 78. Evaluating our model's predictions 11:51:26 79. The missing piece โ€“ non-linearity 12:42:32 84. Putting it all together with a multiclass problem 13:24:09 88. Troubleshooting a mutli-class model ๐Ÿ˜Ž Chapter 3 โ€“ Computer Vision 14:00:48 92. Introduction to computer vision 14:12:36 93. Computer vision input and outputs 14:22:46 94. What is a convolutional neural network? 14:27:49 95. TorchVision 14:37:10 96. Getting a computer vision dataset 15:01:34 98. Mini-batches 15:08:52 99. Creating DataLoaders 15:52:01 103. Training and testing loops for batched data 16:26:27 105. Running experiments on the GPU 16:30:14 106. Creating a model with non-linear functions 16:42:23 108. Creating a train/test loop 17:13:32 112. Convolutional neural networks (overview) 17:21:57 113. Coding a CNN 17:41:46 114. Breaking down nn.Conv2d/nn.MaxPool2d 18:29:02 118. Training our first CNN 18:44:22 120. Making predictions on random test samples 18:56:01 121. Plotting our best model predictions 19:19:34 123. Evaluating model predictions with a confusion matrix ๐Ÿ—ƒ Chapter 4 โ€“ Custom Datasets 19:44:05 126. Introduction to custom datasets 19:59:54 128. Downloading a custom dataset of pizza, steak and sushi images 20:13:59 129. Becoming one with the data 20:39:11 132. Turning images into tensors 21:16:16 136. Creating image DataLoaders 21:25:20 137. Creating a custom dataset class (overview) 21:42:29 139. Writing a custom dataset class from scratch 22:21:50 142. Turning custom datasets into DataLoaders 22:28:50 143. Data augmentation 22:43:14 144. Building a baseline model 23:11:07 147. Getting a summary of our model with torchinfo 23:17:46 148. Creating training and testing loop functions 23:50:59 151. Plotting model 0 loss curves 24:00:02 152. Overfitting and underfitting 24:32:31 155. Plotting model 1 loss curves 24:35:53 156. Plotting all the loss curves 24:46:50 157. Predicting on custom data

๐ŸŽฏ What You'll Learn

โœ“

Complete understanding of the topic

โœ“

Hands-on practical knowledge

โœ“

Real-world examples and use cases

โœ“

Industry best practices

โญ Course Features

๐Ÿค–

AI Support

24/7 doubt solving

๐Ÿ“

Practice Quiz

Test your knowledge

๐Ÿ†

Certificate

Course completion

๐Ÿ“‹ Prerequisites

  • โ€ข

    Basic understanding of programming concepts

  • โ€ข

    Eagerness to learn and practice

AI MentorLive Chat
Always here to help you learn
Premium

Get Full Course Access

Take your learning to the next level with premium features

Unlimited access to all chapters
Interactive quizzes & assessments
Downloadable certificate

Course Content

Introduction
1
1 min

Introduction

5 Questions Ready
0. Welcome and "what is deep learning?"
2
5 min

0. Welcome and "what is deep learning?"

5 Questions Locked
1. Why use machine/deep learning?
3
3 min

1. Why use machine/deep learning?

5 Questions Locked
2. The number one rule of ML
4
5 min

2. The number one rule of ML

5 Questions Locked
3. Machine learning vs deep learning
5
6 min

3. Machine learning vs deep learning

5 Questions Locked
4. Anatomy of neural networks
6
9 min

4. Anatomy of neural networks

5 Questions Locked
5. Different learning paradigms
7
4 min

5. Different learning paradigms

5 Questions Locked
6. What can deep learning be used for?
8
6 min

6. What can deep learning be used for?

5 Questions Locked
7. What is/why PyTorch?
9
10 min

7. What is/why PyTorch?

5 Questions Locked
8. What are tensors?
10
4 min

8. What are tensors?

5 Questions Locked
9. Outline
11
6 min

9. Outline

5 Questions Locked
10. How to (and how not to) approach this course
12
5 min

10. How to (and how not to) approach this course

5 Questions Locked
11. Important resources
13
5 min

11. Important resources

5 Questions Locked
12. Getting setup
14
7 min

12. Getting setup

5 Questions Locked
13. Introduction to tensors
15
13 min

13. Introduction to tensors

5 Questions Locked
14. Creating tensors
16
18 min

14. Creating tensors

5 Questions Locked
17. Tensor datatypes
17
9 min

17. Tensor datatypes

5 Questions Locked
18. Tensor attributes (information about tensors)
18
8 min

18. Tensor attributes (information about tensors)

5 Questions Locked
19. Manipulating tensors
19
6 min

19. Manipulating tensors

5 Questions Locked
20. Matrix multiplication
20
30 min

20. Matrix multiplication

5 Questions Locked
23. Finding the min, max, mean & sum
21
9 min

23. Finding the min, max, mean & sum

5 Questions Locked
25. Reshaping, viewing and stacking
22
13 min

25. Reshaping, viewing and stacking

5 Questions Locked
26. Squeezing, unsqueezing and permuting
23
11 min

26. Squeezing, unsqueezing and permuting

5 Questions Locked
27. Selecting data (indexing)
24
9 min

27. Selecting data (indexing)

5 Questions Locked
28. PyTorch and NumPy
25
9 min

28. PyTorch and NumPy

5 Questions Locked
29. Reproducibility
26
10 min

29. Reproducibility

5 Questions Locked
30. Accessing a GPU
27
11 min

30. Accessing a GPU

5 Questions Locked
31. Setting up device agnostic code
28
12 min

31. Setting up device agnostic code

5 Questions Locked
33. Introduction to PyTorch Workflow
29
2 min

33. Introduction to PyTorch Workflow

5 Questions Locked
34. Getting setup
30
7 min

34. Getting setup

5 Questions Locked
35. Creating a dataset with linear regression
31
9 min

35. Creating a dataset with linear regression

5 Questions Locked
36. Creating training and test sets (the most important concept in ML)
32
16 min

36. Creating training and test sets (the most important concept in ML)

5 Questions Locked
38. Creating our first PyTorch model
33
20 min

38. Creating our first PyTorch model

5 Questions Locked
40. Discussing important model building classes
34
6 min

40. Discussing important model building classes

5 Questions Locked
41. Checking out the internals of our model
35
9 min

41. Checking out the internals of our model

5 Questions Locked
42. Making predictions with our model
36
11 min

42. Making predictions with our model

5 Questions Locked
43. Training a model with PyTorch (intuition building)
37
8 min

43. Training a model with PyTorch (intuition building)

5 Questions Locked
44. Setting up a loss function and optimizer
38
12 min

44. Setting up a loss function and optimizer

5 Questions Locked
45. PyTorch training loop intuition
39
37 min

45. PyTorch training loop intuition

5 Questions Locked
48. Running our training loop epoch by epoch
40
9 min

48. Running our training loop epoch by epoch

5 Questions Locked
49. Writing testing loop code
41
26 min

49. Writing testing loop code

5 Questions Locked
51. Saving/loading a model
42
28 min

51. Saving/loading a model

5 Questions Locked
54. Putting everything together
43
47 min

54. Putting everything together

5 Questions Locked
60. Introduction to machine learning classification
44
9 min

60. Introduction to machine learning classification

5 Questions Locked
61. Classification input and outputs
45
9 min

61. Classification input and outputs

5 Questions Locked
62. Architecture of a classification neural network
46
18 min

62. Architecture of a classification neural network

5 Questions Locked
64. Turing our data into tensors
47
16 min

64. Turing our data into tensors

5 Questions Locked
66. Coding a neural network for classification data
48
17 min

66. Coding a neural network for classification data

5 Questions Locked
68. Using torch.nn.Sequential
49
13 min

68. Using torch.nn.Sequential

5 Questions Locked
69. Loss, optimizer and evaluation functions for classification
50
14 min

69. Loss, optimizer and evaluation functions for classification

5 Questions Locked
70. From model logits to prediction probabilities to prediction labels
51
16 min

70. From model logits to prediction probabilities to prediction labels

5 Questions Locked
71. Train and test loops
52
29 min

71. Train and test loops

5 Questions Locked
73. Discussing options to improve a model
53
29 min

73. Discussing options to improve a model

5 Questions Locked
76. Creating a straight line dataset
54
18 min

76. Creating a straight line dataset

5 Questions Locked
78. Evaluating our model's predictions
55
5 min

78. Evaluating our model's predictions

5 Questions Locked
79. The missing piece โ€“ non-linearity
56
51 min

79. The missing piece โ€“ non-linearity

5 Questions Locked
84. Putting it all together with a multiclass problem
57
41 min

84. Putting it all together with a multiclass problem

5 Questions Locked
88. Troubleshooting a mutli-class model
58
36 min

88. Troubleshooting a mutli-class model

5 Questions Locked
92. Introduction to computer vision
59
11 min

92. Introduction to computer vision

5 Questions Locked
93. Computer vision input and outputs
60
10 min

93. Computer vision input and outputs

5 Questions Locked
94. What is a convolutional neural network?
61
5 min

94. What is a convolutional neural network?

5 Questions Locked
95. TorchVision
62
9 min

95. TorchVision

5 Questions Locked
96. Getting a computer vision dataset
63
24 min

96. Getting a computer vision dataset

5 Questions Locked
98. Mini-batches
64
7 min

98. Mini-batches

5 Questions Locked
99. Creating DataLoaders
65
43 min

99. Creating DataLoaders

5 Questions Locked
103. Training and testing loops for batched data
66
34 min

103. Training and testing loops for batched data

5 Questions Locked
105. Running experiments on the GPU
67
3 min

105. Running experiments on the GPU

5 Questions Locked
106. Creating a model with non-linear functions
68
12 min

106. Creating a model with non-linear functions

5 Questions Locked
108. Creating a train/test loop
69
31 min

108. Creating a train/test loop

5 Questions Locked
112. Convolutional neural networks (overview)
70
8 min

112. Convolutional neural networks (overview)

5 Questions Locked
113. Coding a CNN
71
19 min

113. Coding a CNN

5 Questions Locked
114. Breaking down nn.Conv2d/nn.MaxPool2d
72
47 min

114. Breaking down nn.Conv2d/nn.MaxPool2d

5 Questions Locked
118. Training our first CNN
73
15 min

118. Training our first CNN

5 Questions Locked
120. Making predictions on random test samples
74
11 min

120. Making predictions on random test samples

5 Questions Locked
121. Plotting our best model predictions
75
23 min

121. Plotting our best model predictions

5 Questions Locked
123. Evaluating model predictions with a confusion matrix
76
24 min

123. Evaluating model predictions with a confusion matrix

5 Questions Locked
126. Introduction to custom datasets
77
15 min

126. Introduction to custom datasets

5 Questions Locked
128. Downloading a custom dataset of pizza, steak and sushi images
78
14 min

128. Downloading a custom dataset of pizza, steak and sushi images

5 Questions Locked
129. Becoming one with the data
79
25 min

129. Becoming one with the data

5 Questions Locked
132. Turning images into tensors
80
37 min

132. Turning images into tensors

5 Questions Locked
136. Creating image DataLoaders
81
9 min

136. Creating image DataLoaders

5 Questions Locked
137. Creating a custom dataset class (overview)
82
17 min

137. Creating a custom dataset class (overview)

5 Questions Locked
139. Writing a custom dataset class from scratch
83
39 min

139. Writing a custom dataset class from scratch

5 Questions Locked
142. Turning custom datasets into DataLoaders
84
7 min

142. Turning custom datasets into DataLoaders

5 Questions Locked
143. Data augmentation
85
14 min

143. Data augmentation

5 Questions Locked
144. Building a baseline model
86
27 min

144. Building a baseline model

5 Questions Locked
147. Getting a summary of our model with torchinfo
87
6 min

147. Getting a summary of our model with torchinfo

5 Questions Locked
148. Creating training and testing loop functions
88
33 min

148. Creating training and testing loop functions

5 Questions Locked
151. Plotting model 0 loss curves
89
9 min

151. Plotting model 0 loss curves

5 Questions Locked
152. Overfitting and underfitting
90
32 min

152. Overfitting and underfitting

5 Questions Locked
155. Plotting model 1 loss curves
91
3 min

155. Plotting model 1 loss curves

5 Questions Locked
156. Plotting all the loss curves
92
10 min

156. Plotting all the loss curves

5 Questions Locked
157. Predicting on custom data
93

157. Predicting on custom data

5 Questions Locked