DigitSuo
tetsuo-ai
48stars
handwritten digit recognition system using a custom neural network architecture. Built with C, it features both training capabilities and an interactive recognition interface. >98% accuracy on the MNIST dataset.
Machine Learning · GitHub
Train, evaluate, and run machine learning models.
Useful GitHub projects
4,624 projects
tevatron
texttron
753stars
Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.
- Training billion-scale LLM neural retriever on GPUs and TPUs.
- Parameter efficient tuning with LoRA.
traiNNer-redux
the-database
139stars
Deep learning training framework for image super resolution and restoration.
yolov4-deepsort
theAIGuysCode
1,422stars
Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.
sslsv
theolepage
41stars
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker Verification (SV).
- Supervised and Self-supervised datasets (siamese and DINO sampling)
- Audio augmentation (noise and reverberation)
3D-Machine-Learning
timzhang642
10,221stars
.jpeg)
A resource repository for 3D machine learning
lacuna-research-mcp
tiptreesystems
63stars
MCP server for Lacuna, a research map for machine learning: search directions, papers, authors, venues, and AI-generated research proposals.
pygcn
tkipf
5,398stars
Graph Convolutional Networks in PyTorch
fire-detection-cnn
tobybreckon
571stars
real-time fire detection in video imagery using a convolutional neural network (deep learning) - from our ICIP 2018 paper (Dunnings / Breckon) + ICMLA 2019 paper (Samarth / Bhowmik / Breckon)
pix2code
tonybeltramelli
12,009stars
pix2code: Generating Code from a Graphical User Interface Screenshot
pytorch-mobilenet-v2
tonylins
1,404stars
A PyTorch implementation of MobileNet V2 architecture and pretrained model.
tsl
TorchSpatiotemporal
392stars
tsl: a PyTorch library for processing spatiotemporal data.
- Create Custom Models and Datasets Easily build your own custom models and datasets for spatiotemporal data analysis. Whether you're working with sensor networks, environmental data, or any other spatiotemporal domain, tsl's high-level APIs empower you to develop tailored solutions.
- Access a Wealth of Existing Datasets and Models Leverage a vast collection of datasets and models from the spatiotemporal data processing literature. Explore and benchmark against state-of-the-art baselines, and test your brand new model on widely used public datasets.
siamfc-tf
torrvision
572stars
SiamFC tracking in TensorFlow.
tmrl
trackmania-rl
750stars
Reinforcement Learning for real-time applications
- Analog control from screenshots: The tmrl example pipeline trains policies that are able to drive from raw screenshots captured in real-time. For beginners, we also provide simpler rangefinder ("LIDAR") observations, which are less potent but easier to learn from. The example pipeline controls the game via a virtual gamepad, which enables analog actions.
- Models: To process LIDAR measurements, the example tmrl pipeline uses a Multi-Layer Perceptron (MLP). To process raw camera images (snapshots), it uses a Convolutional Neural Network (CNN). These models learn the physics of the game from histories or observations equally spaced in time.
dvc
treeverse
15,971stars
🦉 Data Versioning and ML Experiments
tadpole
tum-pbs
29stars
[NeurIPS2026] Flexible scientific foundation models trained with synthetic online data generation
torch-frft
tunakasif
61stars
PyTorch implementation of the fractional Fourier transform with trainable transform order.
flor
ucbrise
161stars
Flow with FlorDB 🌻
skills
ultralytics
38stars
Agent skills for Ultralytics YOLO, covering models, datasets, training, tuning, inference, tracking, and export.
investment-funnel
VanekPetr
77stars
Investment Funnel 📈 is an open-source python platform designed for an easy development and backtesting of outperforming investment strategies.
Torchelie
Vermeille
111stars
Torchélie is a set of utility functions, layers, losses, models, trainers and other things for PyTorch.
geo-clip
VicenteVivan
419stars
This is an official PyTorch implementation of our NeurIPS 2023 paper "GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization"
dreamer_v4
vijayabhaskar-ev
40stars
Code, results and checkpoints for the paper "Silent Pipeline Defects in World-Model RL: A Dreamer 4 Case Study": a PyTorch reimplementation of Dreamer 4, two silent defects that passed 12 checks, and three cheap checks that catch them
modern-llm-notebook
walkinglabs
283stars
A hands-on course on modern LLM architectures, training, and inference, with step-by-step PyTorch implementations and runnable notebooks.