aladdinpersson/machine-learning-collection

★ 8,435PythonAudience · researcherComplexity · 2/5LicenseSetup · moderate

Mindmap

mindmap
  root((ml-collection))
    Classic Algorithms
      Linear regression
      K-nearest neighbors
      SVM and naive Bayes
    PyTorch Tutorials
      Basic tensors
      Neural net types
      GANs
    TensorFlow Section
      CNN architectures
      Beginner tutorials
    Learning Format
      Python code files
      Jupyter notebooks
      YouTube walkthroughs

mindmap root((ml-collection)) Classic Algorithms Linear regression K-nearest neighbors SVM and naive Bayes PyTorch Tutorials Basic tensors Neural net types GANs TensorFlow Section CNN architectures Beginner tutorials Learning Format Python code files Jupyter notebooks YouTube walkthroughs

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Learn to build and train neural networks in PyTorch by following working code examples paired with YouTube walkthroughs.

USE CASE 2

Implement classic ML algorithms like K-nearest neighbors or SVMs from scratch in Python to understand how they work.

USE CASE 3

Use the GAN tutorial code as a starting point for training your own image-generation model.

USE CASE 4

Reference the transfer learning examples when adapting a pre-trained model for a custom image classification task.

Tech stack

PythonPyTorchTensorFlowJupyter Notebook

Getting it running

Difficulty · moderate Time to first run · 30min

Requires Python plus PyTorch or TensorFlow installed, a GPU is recommended for larger deep learning examples.

Use and modify freely for any purpose, including commercial use, under the MIT license.

In plain English

Machine Learning Collection is a repository of code tutorials and projects covering machine learning and deep learning, created as a learning resource. The author accompanies most entries with video explanations on YouTube so you can watch a walkthrough alongside the code if you prefer that format. The goal is to give people a clear, readable reference they can return to when they need to implement a specific technique. The content is organized into two main areas. The first is a set of classic machine learning algorithms implemented from scratch in Python, including linear regression, logistic regression, K-nearest neighbors, K-means clustering, support vector machines, naive Bayes, decision trees, and a basic neural network. Each one links to a corresponding YouTube video. The second and larger area is a collection of PyTorch tutorials. PyTorch is a widely used Python library for building and training neural networks. The tutorials start with basics: working with tensors (the fundamental data structures PyTorch uses), building simple neural network types, loading custom datasets, applying data augmentation, and using transfer learning (adapting a pre-trained model for a new task). From there the collection moves into more advanced topics, including text generation, semantic segmentation (labeling every pixel in an image), and object detection. There is a dedicated section on generative adversarial networks, which are a type of model that learns to produce new images or data by having two networks compete against each other. The collection also covers several well-known neural network architectures and includes tutorials on PyTorch Lightning, a library that simplifies training code. A separate section covers TensorFlow, another popular deep learning library, with beginner tutorials and examples of common CNN architectures. CNN stands for convolutional neural network, a design commonly used for image-related tasks. The repository is open source under the MIT license and accepts contributions.

Copy-paste prompts

Prompt 1

Using the PyTorch tutorial style in aladdinpersson's collection, write me a complete training loop for a convolutional neural network that classifies images into 10 categories.

Prompt 2

Show me how to implement a GAN in PyTorch with a generator and discriminator for 28x28 grayscale images, following the structure used in this collection.

Prompt 3

Walk me through the transfer learning example: how do I freeze early layers of a ResNet and fine-tune only the final layer on my own dataset?

Prompt 4

Implement K-means clustering from scratch in Python in the style of this collection and apply it to a 2D dataset to show cluster assignments.

Open on GitHub → Explain another repo

← aladdinpersson on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.