PyTorch for Deep Learning Bootcamp
Learn PyTorch. Become a Deep Learning Engineer. Get Hired.
Created by Andrei Neagoie
About this course
Course content
14 chapters · 363 lessons · 52h 13m totalZeroToMastery - PyTorch for Deep Learning Bootcamp Zero to Mastery 2025-4 1 lessons
1. Introduction 7 lessons
1. PyTorch for Deep Learning Bootcamp Zero to Mastery
Video
2. Course Welcome and What Is Deep Learning
Video
2. Section 00 PyTorch Fundamentals 33 lessons
1. Why Use Machine Learning or Deep Learning
Video
2. The Number 1 Rule of Machine Learning and What Is Deep Learning Good For
Video
3. Machine Learning vs. Deep Learning
Video
4. Anatomy of Neural Networks
Video
5. Different Types of Learning Paradigms
Video
6. What Can Deep Learning Be Used For
Video
7. What Is and Why PyTorch
Video
8. What Are Tensors
Video
9. What We Are Going To Cover With PyTorch
Video
10. How To and How Not To Approach This Course
Video
11. Important Resources For This Course
Video
12. Getting Setup to Write PyTorch Code
Video
13. Introduction to PyTorch Tensors
Video
14. Creating Random Tensors in PyTorch
Video
15. Creating Tensors With Zeros and Ones in PyTorch
Video
16. Creating a Tensor Range and Tensors Like Other Tensors
Video
17. Dealing With Tensor Data Types
Video
18. Getting Tensor Attributes
Video
19. Manipulating Tensors (Tensor Operations)
Video
20. Matrix Multiplication (Part 1)
Video
21. Matrix Multiplication (Part 2) The Two Main Rules of Matrix Multiplication
Video
22. Matrix Multiplication (Part 3) Dealing With Tensor Shape Errors
Video
23. Finding the Min Max Mean and Sum of Tensors (Tensor Aggregation)
Video
24. Finding The Positional Min and Max of Tensors
Video
25. Reshaping, Viewing and Stacking Tensors
Video
26. Squeezing, Unsqueezing and Permuting Tensors
Video
27. Selecting Data From Tensors (Indexing)
Video
28. PyTorch Tensors and NumPy
Video
29. PyTorch Reproducibility (Taking the Random Out of Random)
Video
30. Different Ways of Accessing a GPU in PyTorch
Video
31. Setting up Device Agnostic Code and Putting Tensors On and Off the GPU
Video
32. PyTorch Fundamentals Exercises and Extra-Curriculum
Video
3. Section 01 PyTorch Workflow 28 lessons
1. Introduction and Where You Can Get Help
Video
2. Getting Setup and What We Are Covering
Video
3. Creating a Simple Dataset Using the Linear Regression Formula
Video
4. Splitting Our Data Into Training and Test Sets
Video
5. Building a function to Visualize Our Data
Video
6. Creating Our First PyTorch Model for Linear Regression
Video
7. Breaking Down What's Happening in Our PyTorch Linear regression Model
Video
8. Discussing Some of the Most Important PyTorch Model Building Classes
Video
9. Checking Out the Internals of Our PyTorch Model
Video
10. Making Predictions With Our Random Model Using Inference Mode
Video
11. Training a Model Intuition (The Things We Need)
Video
12. Setting Up an Optimizer and a Loss Function
Video
13. PyTorch Training Loop Steps and Intuition
Video
14. Writing Code for a PyTorch Training Loop
Video
15. Reviewing the Steps in a Training Loop Step by Step
Video
16. Running Our Training Loop Epoch by Epoch and Seeing What Happens
Video
17. Writing Testing Loop Code and Discussing What's Happening Step by Step
Video
18. Reviewing What Happens in a Testing Loop Step by Step
Video
19. Writing Code to Save a PyTorch Model
Video
20. Writing Code to Load a PyTorch Model
Video
21. Setting Up to Practice Everything We Have Done Using Device-Agnostic Code
Video
22. Putting Everything Together (Part 1) Data
Video
23. Putting Everything Together (Part 2) Building a Model
Video
24. Putting Everything Together (Part 3) Training a Model
Video
25. Putting Everything Together (Part 4) Making Predictions With a Trained Model
Video
26. Putting Everything Together (Part 5) Saving and Loading a Trained Model
Video
27. PyTorch Workflow Exercises and Extra-Curriculum
Video
4. Section 02 PyTorch Neural Network Classification 33 lessons
1. Introduction to Machine Learning Classification With PyTorch
Video
2. Classification Problem Example Input and Output Shapes
Video
3. Typical Architecture of a Classification Neural Network (Overview)
Video
4. Making a Toy Classification Dataset
Video
5. Turning Our Data into Tensors and Making a Training and Test Split
Video
6. Laying Out Steps for Modelling and Setting Up Device-Agnostic Code
Video
7. Coding a Small Neural Network to Handle Our Classification Data
Video
8. Making Our Neural Network Visual
Video
9. Recreating and Exploring the Insides of Our Model Using nn.Sequential
Video
10. Setting Up a Loss Function Optimizer and Evaluation Function for Our Classification Network
Video
11. Going from Model Logits to Prediction Probabilities to Prediction Labels
Video
12. Coding a Training and Testing Optimization Loop for Our Classification Model
Video
13. Writing Code to Download a Helper Function to Visualize Our Models Predictions
Video
14. Discussing Options to Improve a Model
Video
15. Creating a New Model with More Layers and Hidden Units
Video
16. Writing Training and Testing Code to See if Our New and Upgraded Model Performs Better
Video
17. Creating a Straight Line Dataset to See if Our Model is Learning Anything
Video
18. Building and Training a Model to Fit on Straight Line Data
Video
19. Evaluating Our Models Predictions on Straight Line Data
Video
20. Introducing the Missing Piece for Our Classification Model Non-Linearity
Video
21. Building Our First Neural Network with Non-Linearity
Video
22. Writing Training and Testing Code for Our First Non-Linear Model
Video
23. Making Predictions with and Evaluating Our First Non-Linear Model
Video
24. Replicating Non-Linear Activation Functions with Pure PyTorch
Video
25. Putting It All Together (Part 1) Building a Multiclass Dataset
Video
26. Creating a Multi-Class Classification Model with PyTorch
Video
27. Setting Up a Loss Function and Optimizer for Our Multi-Class Model
Video
28. Going from Logits to Prediction Probabilities to Prediction Labels with a Multi-Class Model
Video
29. Training a Multi-Class Classification Model and Troubleshooting Code on the Fly
Video
30. Making Predictions with and Evaluating Our Multi-Class Classification Model
Video
31. Discussing a Few More Classification Metrics
Video
32. PyTorch Classification Exercises and Extra-Curriculum
Video
5. Section 03 PyTorch Computer Vision 35 lessons
1. What Is a Computer Vision Problem and What We Are Going to Cover
Video
2. Computer Vision Input and Output Shapes
Video
3. What Is a Convolutional Neural Network (CNN)
Video
4. Discussing and Importing the Base Computer Vision Libraries in PyTorch
Video
5. Getting a Computer Vision Dataset and Checking Out Its- Input and Output Shapes
Video
6. Visualizing Random Samples of Data
Video
7. DataLoader Overview Understanding Mini-Batch
Video
8. Turning Our Datasets Into DataLoaders
Video
9. Model 0 Creating a Baseline Model with Two Linear Layers
Video
10. Creating a Loss Function an Optimizer for Model 0
Video
11. Creating a Function to Time Our Modelling Code
Video
12. Writing Training and Testing Loops for Our Batched Data
Video
13. Writing an Evaluation Function to Get Our Models Results
Video
14. Setup Device-Agnostic Code for Running Experiments on the GPU
Video
15. Model 1 Creating a Model with Non-Linear Functions
Video
16. Model 1 Creating a Loss Function and Optimizer
Video
17. Turing Our Training Loop into a Function
Video
18. Turing Our Testing Loop into a Function
Video
19. Training and Testing Model 1 with Our Training and Testing Functions
Video
20. Getting a Results Dictionary for Model 1
Video
21. Model 2 Convolutional Neural Networks High Level Overview
Video
22. Model 2 Coding Our First Convolutional Neural Network with PyTorch
Video
23. Model 2 Breaking Down Conv2D Step by Step
Video
24. Model 2 Breaking Down MaxPool2D Step by Step
Video
25. Model 2 Using a Trick to Find the Input and Output Shapes of Each of Our Layers
Video
26. Model 2 Setting Up a Loss Function and Optimizer
Video
27. Model 2 Training Our First CNN and Evaluating Its Results
Video
28. Comparing the Results of Our Modelling Experiments
Video
29. Making Predictions on Random Test Samples with the Best Trained Model
Video
30. Plotting Our Best Model Predictions on Random Test Samples and Evaluating Them
Video
31. Making Predictions Across the Whole Test Dataset and Importing Libraries to Plot a Confusion Matrix
Video
32. Evaluating Our Best Models Predictions with a Confusion Matrix
Video
33. Saving and Loading Our Best Performing Model
Video
34. Recapping What We Have Covered Plus Exercises and Extra-Curriculum
Video
6. Section 04 PyTorch Custom Datasets 38 lessons
1. What Is a Custom Dataset and What We Are Going to Cover
Video
2. Importing PyTorch and Setting Up Device-Agnostic Code
Video
3. Downloading a Custom Dataset of Pizza, Steak and Sushi Images
Video
4. Becoming One With the Data (Part 1) Exploring the Data Format
Video
5. Becoming One With the Data (Part 2) Visualizing a Random Image
Video
6. Becoming One With the Data (Part 3) Visualizing a Random Image with Matplotlib
Video
7. Transforming Data (Part 1) Turning Images Into Tensors
Video
8. Transforming Data (Part 2) Visualizing Transformed Images
Video
9. Loading All of Our Images and Turning Them Into Tensors With ImageFolder
Video
10. Visualizing a Loaded Image From the Train Dataset
Video
11. Turning Our Image Datasets into PyTorch DataLoaders
Video
12. Creating a Custom Dataset Class in PyTorch High Level Overview
Video
13. Creating a Helper Function to Get Class Names From a Directory
Video
14. Writing a PyTorch Custom Dataset Class from Scratch to Load Our Images
Video
15. Compare Our Custom Dataset Class to the Original ImageFolder Class
Video
16. Writing a Helper Function to Visualize Random Images from Our Custom Dataset
Video
17. Turning Our Custom Datasets Into DataLoaders
Video
18. Exploring State of the Art Data Augmentation With Torchvision Transforms
Video
19. Building a Baseline Model (Part 1) Loading and Transforming Data
Video
20. Building a Baseline Model (Part 2) Replicating Tiny VGG from Scratch
Video
21. Building a Baseline Model (Part 3) Doing a Forward Pass to Test Our Model Shapes
Video
22. Using the Torchinfo Package to Get a Summary of Our Model
Video
23. Creating Training and Testing loop Functions
Video
24. Creating a Train Function to Train and Evaluate Our Models
Video
25. Training and Evaluating Model 0 With Our Training Functions
Video
26. Plotting the Loss Curves of Model 0
Video
27. Discussing the Balance Between Overfitting and Underfitting and How to Deal With Each
Video
28. Creating Augmented Training Datasets and DataLoaders for Model 1
Video
29. Constructing and Training Model 1
Video
30. Plotting the Loss Curves of Model 1
Video
31. Plotting the Loss Curves of All of Our Models Against Each Other
Video
32. Predicting on Custom Data (Part 1) Downloading an Image
Video
33. Predicting on Custom Data (Part2) Loading In a Custom Image With PyTorch
Video
34. Predicting on Custom Data (Part 3) Getting Our Custom Image Into the Right Format
Video
35. Predicting on Custom Data (Part 4) Turning Our Models Raw Outputs Into Prediction Labels
Video
36. Predicting on Custom Data (Part 5) Putting It All Together
Video
37. Summary of What We Have Covered Plus Exercises and Extra-Curriculum
Video
38. Exercise Imposter Syndrome
Video
7. Section 05 PyTorch Going Modular 10 lessons
1. What Is Going Modular and What We Are Going to Cover
Video
2. Going Modular Notebook (Part 1) Running It End to End
Video
3. Downloading a Dataset
Video
4. Writing the Outline for Our First Python Script to Setup the Data
Video
5. Creating a Python Script to Create Our PyTorch DataLoaders
Video
6. Turning Our Model Building Code into a Python Script
Video
7. Turning Our Model Training Code into a Python Script
Video
8. Turning Our Utility Function to Save a Model into a Python Script
Video
9. Creating a Training Script to Train Our Model in One Line of Code
Video
10. Going Modular Summary, Exercises and Extra-Curriculum
Video
8. Section 06 PyTorch Transfer Learning 19 lessons
1. Introduction What is Transfer Learning and Why Use It
Video
2. Where Can You Find Pretrained Models and What We Are Going to Cover
Video
3. Installing the Latest Versions of Torch and Torchvision
Video
4. Downloading Our Previously Written Code from Going Modular
Video
5. Downloading Pizza, Steak, Sushi Image Data from Github
Video
6. Turning Our Data into DataLoaders with Manually Created Transforms
Video
7. Turning Our Data into DataLoaders with Automatic Created Transforms
Video
8. Which Pretrained Model Should You Use
Video
9. Setting Up a Pretrained Model with Torchvision
Video
10. Different Kinds of Transfer Learning
Video
11. Getting a Summary of the Different Layers of Our Model
Video
12. Freezing the Base Layers of Our Model and Updating the Classifier Head
Video
13. Training Our First Transfer Learning Feature Extractor Model
Video
14. Plotting the Loss Curves of Our Transfer Learning Model
Video
15. Outlining the Steps to Make Predictions on the Test Images
Video
16. Creating a Function Predict On and Plot Images
Video
17. Making and Plotting Predictions on Test Images
Video
18. Making a Prediction on a Custom Image
Video
19. Main Takeaways, Exercises and Extra Curriculum
Video
9. Section 07 PyTorch Experiment Tracking 22 lessons
1. What Is Experiment Tracking and Why Track Experiments
Video
2. Getting Setup by Importing Torch Libraries and Going Modular Code
Video
3. Creating a Function to Download Data
Video
4. Turning Our Data into DataLoaders Using Manual Transforms
Video
5. Turning Our Data into DataLoaders Using Automatic Transforms
Video
6. Preparing a Pretrained Model for Our Own Problem
Video
7. Setting Up a Way to Track a Single Model Experiment with TensorBoard
Video
8. Training a Single Model and Saving the Results to TensorBoard
Video
9. Exploring Our Single Models Results with TensorBoard
Video
10. Creating a Function to Create SummaryWriter Instances
Video
11. Adapting Our Train Function to Be Able to Track Multiple Experiments
Video
12. What Experiments Should You Try
Video
13. Discussing the Experiments We Are Going to Try
Video
14. Downloading Datasets for Our Modelling Experiments
Video
15. Turning Our Datasets into DataLoaders Ready for Experimentation
Video
16. Creating Functions to Prepare Our Feature Extractor Models
Video
17. Coding Out the Steps to Run a Series of Modelling Experiments
Video
18. Running Eight Different Modelling Experiments in 5 Minutes
Video
19. Viewing Our Modelling Experiments in TensorBoard
Video
20. Loading In the Best Model and Making Predictions on Random Images from the Test Set
Video
21. Making a Prediction on Our Own Custom Image with the Best Model
Video
22. Main Takeaways, Exercises and Extra Curriculum
Video
10. Section 08 PyTorch Paper Replicating 50 lessons
1. What Is a Machine Learning Research Paper
Video
2. Why Replicate a Machine Learning Research Paper
Video
3. Where Can You Find Machine Learning Research Papers and Code
Video
4. What We Are Going to Cover
Video
5. Getting Setup for Coding in Google Colab
Video
6. Downloading Data for Food Vision Mini
Video
7. Turning Our Food Vision Mini Images into PyTorch DataLoaders
Video
8. Visualizing a Single Image
Video
9. Replicating a Vision Transformer - High Level Overview
Video
10. Breaking Down Figure 1 of the ViT Paper
Video
11. Breaking Down the Four Equations Overview and a Trick for Reading Papers
Video
12. Breaking Down Equation 1
Video
13. Breaking Down Equations 2 and 3
Video
14. Breaking Down Equation 4
Video
15. Breaking Down Table 1
Video
16. Calculating the Input and Output Shape of the Embedding Layer by Hand
Video
17. Turning a Single Image into Patches (Part 1 Patching the Top Row)
Video
18. Turning a Single Image into Patches (Part 2 Patching the Entire Image)
Video
19. Creating Patch Embeddings with a Convolutional Layer
Video
20. Exploring the Outputs of Our Convolutional Patch Embedding Layer
Video
21. Flattening Our Convolutional Feature Maps into a Sequence of Patch Embeddings
Video
22. Visualizing a Single Sequence Vector of Patch Embeddings
Video
23. Creating the Patch Embedding Layer with PyTorch
Video
24. Creating the Class Token Embedding
Video
25. Creating the Class Token Embedding - Less Birds
Video
26. Creating the Position Embedding
Video
27. Equation 1 Putting it All Together
Video
28. Equation 2 Multihead Attention Overview
Video
29. Equation 2 Layernorm Overview
Video
30. Turning Equation 2 into Code
Video
31. Checking the Inputs and Outputs of Equation
Video
32. Equation 3 Replication Overview
Video
33. Turning Equation 3 into Code
Video
34. Transformer Encoder Overview
Video
35. Combining Equation 2 and 3 to Create the Transformer Encoder
Video
36. Creating a Transformer Encoder Layer with In-Built PyTorch Layer
Video
37. Bringing Our Own Vision Transformer to Life - Part 1 Gathering the Pieces of the Puzzle
Video
38. Bringing Our Own Vision Transformer to Life - Part 2 Putting Together the Forward Method
Video
39. Getting a Visual Summary of Our Custom Vision Transformer
Video
40. Creating a Loss Function and Optimizer from the ViT Paper
Video
41. Training our Custom ViT on Food Vision Mini
Video
42. Discussing what Our Training Setup Is Missing
Video
43. Plotting a Loss Curve for Our ViT Model
Video
44. Getting a Pretrained Vision Transformer from Torchvision and Setting it Up
Video
45. Preparing Data to Be Used with a Pretrained ViT
Video
46. Training a Pretrained ViT Feature Extractor Model for Food Vision Mini
Video
47. Saving Our Pretrained ViT Model to File and Inspecting Its Size
Video
48. Discussing the Trade-Offs Between Using a Larger Model for Deployments
Video
49. Making Predictions on a Custom Image with Our Pretrained ViT
Video
50. PyTorch Paper Replicating Main Takeaways, Exercises and Extra-Curriculum
Video
11. Section 09 PyTorch Model Deployment 57 lessons
1. What is Machine Learning Model Deployment and Why Deploy a Machine Learning Model
Video
2. Three Questions to Ask for Machine Learning Model Deployment
Video
3. Where Is My Model Going to Go
Video
4. How Is My Model Going to Function
Video
5. Some Tools and Places to Deploy Machine Learning Models
Video
6. What We Are Going to Cover
Video
7. Getting Setup to Code
Video
8. Downloading a Dataset for Food Vision Mini
Video
9. Outlining Our Food Vision Mini Deployment Goals and Modelling Experiments
Video
10. Creating an EffNetB2 Feature Extractor Model
Video
11. Create a Function to Make an EffNetB2 Feature Extractor Model and Transforms
Video
12. Creating DataLoaders for EffNetB2
Video
13. Training Our EffNetB2 Feature Extractor and Inspecting the Loss Curves
Video
14. Saving Our EffNetB2 Model to File
Video
15. Getting the Size of Our EffNetB2 Model in Megabytes
Video
16. Collecting Important Statistics and Performance Metrics for Our EffNetB2 Model
Video
17. Creating a Vision Transformer Feature Extractor Model
Video
18. Creating DataLoaders for Our ViT Feature Extractor Model
Video
19. Training Our ViT Feature Extractor Model and Inspecting Its Loss Curves
Video
20. Saving Our ViT Feature Extractor and Inspecting Its Size
Video
21. Collecting Stats About Our ViT Feature Extractor
Video
22. Outlining the Steps for Making and Timing Predictions for Our Models
Video
23. Creating a Function to Make and Time Predictions with Our Models
Video
24. Making and Timing Predictions with EffNetB2
Video
25. Making and Timing Predictions with ViT
Video
26. Comparing EffNetB2 and ViT Model Statistics
Video
27. Visualizing the Performance vs Speed Trade-off
Video
28. Gradio Overview and Installation
Video
29. Gradio Function Outline
Video
30. Creating a Predict Function to Map Our Food Vision Mini Inputs to Outputs
Video
31. Creating a List of Examples to Pass to Our Gradio Demo
Video
32. Bringing Food Vision Mini to Life in a Live Web Application
Video
33. Getting Ready to Deploy Our App Hugging Face Spaces Overview
Video
34. Outlining the File Structure of Our Deployed App
Video
35. Creating a Food Vision Mini Demo Directory to House Our App Files
Video
36. Creating an Examples Directory with Example Food Vision Mini Images
Video
37. Writing Code to Move Our Saved EffNetB2 Model File
Video
38. Turning Our EffNetB2 Model Creation Function Into a Python Script
Video
39. Turning Our Food Vision Mini Demo App Into a Python Script
Video
40. Creating a Requirements File for Our Food Vision Mini App
Video
41. Downloading Our Food Vision Mini App Files from Google Colab
Video
42. Uploading Our Food Vision Mini App to Hugging Face Spaces Programmatically
Video
43. Running Food Vision Mini on Hugging Face Spaces and Trying it Out
Video
44. Food Vision Big Project Outline
Video
45. Preparing an EffNetB2 Feature Extractor Model for Food Vision Big
Video
46. Downloading the Food 101 Dataset
Video
47. Creating a Function to Split Our Food 101 Dataset into Smaller Portions
Video
48. Turning Our Food 101 Datasets into DataLoaders
Video
49. Training Food Vision Big Our Biggest Model Yet!
Video
50. Outlining the File Structure for Our Food Vision Big
Video
51. Downloading an Example Image and Moving Our Food Vision Big Model File
Video
52. Saving Food 101 Class Names to a Text File and Reading them Back In
Video
53. Turning Our EffNetB2 Feature Extractor Creation Function into a Python Script
Video
54. Creating an App Script for Our Food Vision Big Model Gradio Demo
Video
55. Zipping and Downloading Our Food Vision Big App Files
Video
56. Deploying Food Vision Big to Hugging Face Spaces
Video
57. PyTorch Mode Deployment Main Takeaways, Extra-Curriculum and Exercises
Video
12. Introduction to PyTorch 2.0 and torch.compile 24 lessons
1. Introduction to PyTorch 2.0
Video
2. What We Are Going to Cover and PyTorch 2 Reference Materials
Video
3. Getting Started with PyTorch 2.0 in Google Colab
Video
4. PyTorch 2.0 - 30 Second Intro
Video
5. Getting Setup for PyTorch 2.0
Video
6. Getting Info from Our GPUs and Seeing if They're Capable of Using PyTorch 2.0
Video
7. Setting the Default Device in PyTorch 2.0
Video
8. Discussing the Experiments We Are Going to Run for PyTorch 2.0
Video
9. Creating a Function to Setup Our Model and Transforms
Video
10. Discussing How to Get Better Relative Speedups for Training Models
Video
11. Setting the Batch Size and Data Size Programmatically
Video
12. Getting More Speedups with TensorFloat-32
Video
13. Downloading the CIFAR10 Dataset
Video
14. Creating Training and Test DataLoaders
Video
15. Preparing Training and Testing Loops with Timing Steps
Video
16. Experiment 1 - Single Run without Torch Compile
Video
17. Experiment 2 - Single Run with Torch Compile
Video
18. Comparing the Results of Experiments 1 and 2
Video
19. Saving the Results of Experiments 1 and 2
Video
20. Preparing Functions for Experiments 3 and 4
Video
21. Experiment 3 - Training a Non-Compiled Model for Multiple Runs
Video
22. Experiment 4 - Training a Compiled Model for Multiple Runs
Video
23. Comparing the Results of Experiments 3 and 4
Video
24. Potential Extensions and Resources to Learn More
Video
Instructor
Andrei Neagoie
Featured course instructor on CourseDen. Follow the source link above to see more of their work.
No account needed — jump straight in.
This course includes:
- 52h 13m of on-demand video
- 363 lessons
- en language
- Access on mobile and TV
- Certificate of completion