Showing 36 of 1845 projects
A JavaScript implementation of the k-nearest neighbors algorithm for supervised machine learning.
A PyTorch framework for reinforcement learning research, focused on reproducibility and fast experimentation.
A Node.js interface for running XGBoost models and making predictions.
Type-safe n-dimensional arrays (tensors) in Scala 3 with compile-time shape, axis label, and data type validation.
Serialize JAX, Flax, Haiku, and Objax model parameters using the safetensors format for safer, pickle-free storage.
A Gymnasium-based benchmarking suite with realistic environments for evaluating reinforcement learning algorithms in practical scenarios.
Composable kernels for scikit-learn implemented in JAX, enabling faster kernel computations and automatic differentiation.
A collection of neural network models ported from torchvision for use with JAX and Flax.
A simple JavaScript implementation of the k-means clustering algorithm for both Node.js and browser environments.
An open-source solution for the Google AI Open Images Object Detection Challenge, providing a RetinaNet-based benchmark with experiment tracking.
A machine learning library built with object-oriented Pascal primitives (interfaces and classes).
A Ruby deep learning library supporting fully connected, convolutional, and recurrent neural networks.
A collection of CoreML examples for Swift Playgrounds on iPadOS demonstrating object recognition and detection models.
A personal data science and machine learning website built with Quarto, tidyverse, and tidymodels.
A Python library for generating contrastive and counterfactual explanations for machine learning models using foil trees.
A Go implementation of k-modes and k-prototypes clustering algorithms for categorical and mixed data.
A JAX-based library for fast, composable image augmentation with geometric and color transformations.
A prompt injection scanner for Claude Code hooks that detects attacks, leaked secrets, and data exfiltration using ML models.
A proof-of-concept for decentralized machine learning using federated learning on the Golem network to distribute training across multiple nodes.
Torch7 library providing SVM implementations including SGD-based methods and LIBLINEAR wrapper.
A collection of demos and tutorials for learning Torch7, a scientific computing framework with deep learning support.
A JAX-based library for coreset algorithms that reduce large datasets to smaller representative subsets while preserving statistical properties.
A ROS2 template node for running PyTorch C++ models, enabling real-time inference in robotics applications.
A Python-based spam detector using Naive Bayes to classify emails as spam or ham.
Ruby SDK for integrating with IBM Watson AI services like speech-to-text, language understanding, and assistant APIs.
Machine learning model that predicts whether Stack Overflow questions will be closed based on their content and metadata.
A Go library for building and evaluating dynamic decision trees programmatically or from JSON, with support for pre-processing inputs.
A pure JavaScript library for linear regression analysis, enabling trendline creation and future value prediction.
Stream Processing Made Easy
A pre-trained image classifier that recognizes 365 different scene and location types using a ResNet18 model fine-tuned on Places365.
Sample code demonstrating Core ML integration with ResNet50 and custom models converted via coremltools.
A machine learning pipeline that predicts 70 cell health phenotypes from Cell Painting image-based morphology profiles.
A framework for automated cryptographic primitive classification using dynamic binary instrumentation and deep learning.
A simple, easy-to-understand library for diffusion models built with Flax and JAX, focusing on readability and learning.
An open-source machine learning library for regression tasks using the Relevance Vector Machine (RVM) technique.
A Python library providing various neural unit implementations including LNU, QNU, RBF, MLP, and MLP-ELM with gradient descent and Levenberg-Marquardt training.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.