yolov5
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
- 58k
- Python
- AGPL-3.0
- 3 d ago
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.
Type-safe, distributed orchestration of agents, ML pipelines, and real-time inference on your k8s — in pure Python with async/await, also other languages (rust, go and ts)
🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSys, etc. 🗃️ Llama3, Mistral, etc. 🧑💻 Video Tutorials.
[NeurIPS 2026] DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models
🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥
Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models
AI-native, cloud-native file system in Rust. Full POSIX on object storage with a multi-tier distributed cache, for AI training, inference, and agents. CNCF Sandbox project.
YOLOv3 training, preprocessing, validation, and inference for object detection in xView satellite imagery and the xView detection challenge.
Historical Ultralytics HUB repository — HUB shut down on July 31, 2026 and was replaced by Ultralytics Platform.
Ultralytics YOLO tutorials for Colab, Kaggle, and SageMaker covering training, inference, export, and vision tasks.
Retired Python SDK for the shut-down Ultralytics HUB API, kept for reference; build new integrations on the Ultralytics Platform REST API
Stable Diffusion Regularization Images in 512px, 768px and 1024px on 1.5, 2.1 and SDXL 1.0 checkpoints
Accelerating AI Training and Inference from Storage Perspective (Must-read Papers on Storage for AI)
Agent skills for Ultralytics YOLO, covering models, datasets, training, tuning, inference, tracking, and export.
A curated list of awesome open source tools and commercial products that will help you train, deploy, monitor, version, scale, and secure your production machine learning on kubernetes 🚀
This example shows how to use MATLAB to train a TensorFlow model and tune it's hyperparameters using co-execution with Python.
Implementation of TSDS: Data Selection for Task-Specific Model Finetuning. An optimal-transport framework for selecting domain-specific and task-specific training data to improve LLM finetuning and instruction tuning.
Code for paper "Accelerating Federated Learning for IoT in Big Data Analytics with Pruning, Quantization and Selective Updating"
Understand and build embedding models, focusing on word and sentence embeddings, dual encoder architectures. Learn to train embedding models using contrastive loss, implement them in semantic search and RAG systems.
Learn to optimize machine learning tasks for environmental sustainability. Discover how to use real-time electricity data and low-carbon energy sources for model training and inference, reducing the carbon footprint of your cloud operations.
AI Dev OS is a production-grade autonomous AI agent orchestration platform that combines six cutting-edge AI/ML technologies into a unified workflow. It enables autonomous agents to handle complete engineering tasks—from design through deployment—with human oversight at critical checkpoints.
DataFlex is a data-centric training framework that enhances model performance by either selecting the most influential samples, optimizing their weights, or adjusting their mixing ratios.
Deep learning solution for apple disease detection using CNN architecture. Trained on PlantVillage dataset to classify 4 apple leaf conditions with real-time image analysis.
A practical Deep Learning repository inspired by Codebasics, covering neural networks, TensorFlow, Keras, ANN, CNN, image classification, model training, hyperparameter tuning, and hands-on Python implementations with real-world deep learning applications.
A simple classifier trained on a small tabular dataset using scikit-learn to demonstrate how pipelines are used and how they work.
A practical Large Language Model (LLM) full fine-tuning repository featuring end-to-end implementations of dataset preparation, tokenization, supervised fine-tuning (SFT), transformer model training, loss optimization, evaluation, and model checkpoint management using Python, PyTorch, and Hugging Face Transformers.
Practical Machine Learning repository focused on training, validating, and evaluating Classical ML models using Python and Scikit-learn. Covers regression, classification, model selection, cross-validation, hyperparameter tuning, performance metrics, and model optimization through hands-on implementations.
A comprehensive collection of Deep Learning algorithms and architectures from beginner to advanced, covering neural networks, backpropagation, optimization techniques, CNNs, RNNs, LSTMs, Transformers, and practical implementations using Python, TensorFlow, Keras, and PyTorch.
End-to-end fine-tuning of Hugging Face models using LoRA, QLoRA, quantization, and PEFT techniques. Optimized for low-memory with efficient model deployment
This is a web app (using eel-python) that is used to detect emotions using deep learning. This web app can also train a model.
Developed a Convolutional Neural Network (CNN) model to classify images into 10 categories. The project includes data augmentation, model building, training, and evaluation.