Skip to content

Coleção de snippets e rascunhos reunidos durante meus estudos sobre machine learning

License

Notifications You must be signed in to change notification settings

vjucosky/learning-machine-learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

40 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Estudos sobre machine learning

Este repositório contém snippets e rascunhos de código que foram reunidos durante meus estudos sobre machine learning. Todo o material é feito em Python e está organizado de acordo com a biblioteca principal utilizada.

PyTorch

Tutorial: PyTorch for Deep Learning & Machine Learning – Full Course

Chapter 0 – PyTorch Fundamentals

  1. 28/07/2025 Why use machine/deep learning?
  2. 28/07/2025 The number one rule of ML
  3. 28/07/2025 Machine learning vs deep learning
  4. 28/07/2025 Anatomy of neural networks
  5. 28/07/2025 Different learning paradigms
  6. 28/07/2025 What can deep learning be used for?
  7. 28/07/2025 What is/why PyTorch?
  8. 28/07/2025 What are tensors?
  9. 28/07/2025 Outline
  10. 28/07/2025 How to (and how not to) approach this course
  11. 28/07/2025 Important resources
  12. 29/07/2025 Getting setup
  13. 29/07/2025 Introduction to tensors
  14. 29/07/2025 Creating random tensors in PyTorch
  15. 29/07/2025 Creating tensors with zeros and ones in PyTorch
  16. 29/07/2025 Creating tensors in a range
  17. 29/07/2025 Tensor datatypes
  18. 29/07/2025 Getting tensor attributes (information about tensors)
  19. 30/07/2025 Manipulating tensors (tensor operations)
  20. 30/07/2025 Matrix multiplication (part 1)
  21. 30/07/2025 Matrix multiplication (part 2: the two main rules of matrix multiplication)
  22. 30/07/2025 Matrix multiplication (part 3: dealing with tensor shape errors)
  23. 02/08/2025 Finding the min, max, mean and sum of tensors (tensor aggregation)
  24. 02/08/2025 Finding the positional min and max of tensors
  25. 02/08/2025 Reshaping, viewing and stacking tensors
  26. 02/08/2025 Squeezing, unsqueezing and permuting tensors
  27. 02/08/2025 Selecting data from tensors (indexing)
  28. 02/08/2025 PyTorch and NumPy
  29. 02/08/2025 PyTorch reproducibility (taking the random out of random)
  30. 02/08/2025 Different ways of accessing a GPU in PyTorch
  31. 02/08/2025 Setting up device agnostic code and putting tensors on and off the GPU
  32. PyTorch Fundamentals exercises & extra-curriculum

Chapter 1 – PyTorch Workflow

  1. 03/08/2025 Introduction to PyTorch Workflow
  2. 03/08/2025 Getting setup for the PyTorch Workflow module
  3. 03/08/2025 Creating a simple dataset using linear regression
  4. 03/08/2025 Splitting our data into training and test sets (possibly the most important concept in machine learning)
  5. 03/08/2025 Building a function to visualize our data
  6. 03/08/2025 Creating our first PyTorch model for linear regression
  7. 03/08/2025 Breaking down what's happening in our PyTorch linear regression model
  8. 03/08/2025 Discussing some of the most important PyTorch model building classes
  9. 04/08/2025 Checking out the internals of our PyTorch model
  10. 04/08/2025 Making predictions with our random model using torch.inference_mode()
  11. 04/08/2025 Training a model with PyTorch (intuition building)
  12. 04/08/2025 Setting up a loss function and optimizer with PyTorch
  13. 05/08/2025 PyTorch training loop steps and intuition
  14. 05/08/2025 Writing code for a PyTorch training loop
  15. 05/08/2025 Reviewing the steps in a PyTorch trainig loop
  16. 05/08/2025 Running our training loop epoch by epoch and seeing what happens
  17. 05/08/2025 Writing testing loop code and discussing what's happening
  18. 05/08/2025 Reviewing what happens in a testing loop step by step
  19. 06/08/2025 Writing code to save a PyTorch model
  20. 06/08/2025 Writing code to load a PyTorch model
  21. 07/08/2025 Getting ready to practice everything we've done so far with device agnostic-code
  22. 07/08/2025 Putting everything together part 1: preparing data
  23. 07/08/2025 Putting everything together part 2: building a model
  24. 07/08/2025 Putting everything together part 3: training a model
  25. 07/08/2025 Putting everything together part 4: making predictions with a trained model
  26. 07/08/2025 Putting everything together part 5: saving and loading a trained model
  27. PyTorch Workflow exercises & extra-curriculum

Chapter 2 – PyTorch Neural Network Classification

  1. 08/08/2025 Introduction to machine learning classification with PyTorch
  2. 08/08/2025 Classification problem input and output shapes
  3. 08/08/2025 Typically architecture of a classification neural network (overview)
  4. 09/08/2025 Making a toy classification dataset
  5. 09/08/2025 Turing our data into tensors and making a training and test split
  6. 09/08/2025 Laying out steps for modelling and setting up device agnostic code
  7. 09/08/2025 Coding a small neural network to handle our classification data
  8. 09/08/2025 Making our neural network visual
  9. 09/08/2025 Recreating our model using torch.nn.Sequential
  10. Setting up a loss function, optimizer and evaluation function for our classification neural network
  11. From model logits to prediction probabilities to prediction labels
  12. Train and test loops
  13. Discussing options to improve a model
  14. Creating a straight line dataset
  15. Evaluating our model's predictions
  16. The missing piece – non-linearity
  17. Putting it all together with a multiclass problem
  18. Troubleshooting a mutli-class model

Chapter 3 – Computer Vision

  1. Introduction to computer vision
  2. Computer vision input and outputs
  3. What is a convolutional neural network?
  4. TorchVision
  5. Getting a computer vision dataset
  6. Mini-batches
  7. Creating DataLoaders
  8. Training and testing loops for batched data
  9. Running experiments on the GPU
  10. Creating a model with non-linear functions
  11. Creating a train/test loop
  12. Convolutional neural networks (overview)
  13. Coding a CNN
  14. Breaking down nn.Conv2d/nn.MaxPool2d
  15. Training our first CNN
  16. Making predictions on random test samples
  17. Plotting our best model predictions
  18. Evaluating model predictions with a confusion matrix

Chapter 4 – Custom Datasets

  1. Introduction to custom datasets
  2. Downloading a custom dataset of pizza, steak and sushi images
  3. Becoming one with the data
  4. Turning images into tensors
  5. Creating image DataLoaders
  6. Creating a custom dataset class (overview)
  7. Writing a custom dataset class from scratch
  8. Turning custom datasets into DataLoaders
  9. Data augmentation
  10. Building a baseline model
  11. Getting a summary of our model with torchinfo
  12. Creating training and testing loop functions
  13. Plotting model 0 loss curves
  14. Overfitting and underfitting
  15. Plotting model 1 loss curves
  16. Plotting all the loss curves
  17. Predicting on custom data

Links úteis:

About

Coleção de snippets e rascunhos reunidos durante meus estudos sobre machine learning

Topics

Resources

License

Stars

Watchers

Forks