PyTorch

Free, open-source (AGPL) mosaic restoration for Windows: detects pixelated regions in video and restores them with a temporal model, plus whole-frame upscaling. One source tree, three editions: NVIDIA RTX (TensorRT, NVDEC/NVENC, RTX Super-Res), AMD Radeon (PyTorch ROCm, AMF) and Intel Arc (PyTorch XPU, Quick Sync). Desktop UI with Test Frame preview, folder batches, 4K/VR (SBS, fisheye) support, VRAM preflight, custom super-resolution models with TensorRT compilation. Installers and patches on the Releases page; the GitHub repos (seatv/ChitraMaya, -AMD-ROCM, -Intel-ARC) are mirrors of this one.

Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

GitHub: https://github.com/ultralytics/ultralytics

https://platform.ultralytics.com

Self-hosted forecasting + prediction service. Five zero-shot time-series foundation models (Chronos-2, TimesFM 2.5, Moirai-2, Toto-1, Sundial) across six forecast types, plus nine supervised tabular ML backends (LightGBM, XGBoost, sklearn family) with calibrated / stacking / diversified meta-learners. Unified REST API + MCP server.

Implementation of the Sliced Iterative Normalizing Flow Algorithm as introduced by Dai and Seljak ( https://arxiv.org/abs/2007.00674 ) with additional features

The ImagesAnnotator application project` annotations format data exporters library for NN training software

Sign Language Recognition using Computer Vision and Deep Learning

Detect and classify objects in Panoramax pictures

PyTorch model profiler for computing MACs and parameter counts to measure deep learning model complexity.

GitHub: https://github.com/ultralytics/thop

https://pypi.org/project/ultralytics-thop/

PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.

GitHub: https://github.com/ultralytics/yolov3

https://docs.ultralytics.com/models/yolov3/

Make the call. Run local Laya, Von, CLM or hosted Jev for typed classification and scoring through one HTTP and MCP API, with resource-aware batches.

Ultralytics fork of Apple MobileCLIP for fast image-text inference, training, evaluation, and an iOS demo.

GitHub: https://github.com/ultralytics/mobileclip

https://docs.ultralytics.com

OpenAI CLIP for zero-shot image-text classification and embeddings with ResNet and Vision Transformer models.

GitHub: https://github.com/ultralytics/CLIP

https://www.ultralytics.com

Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

GitHub: https://github.com/ultralytics/yolov5

https://docs.ultralytics.com/yolov5/

ML engine for discrete circuit design: simulates and labels circuits, trains a GNN surrogate, then uses it to design, self-tune, and run inference on a microcontroller.

Tiny neural amp/pedal capture: a small GRU learns a guitar amp's sound, small enough to run in real time on a sub-$5 microcontroller.

Pinned PyTorch CPU and CUDA base images. Build the damn stack once.

A torch.compile backend for Qualcomm QNN on Windows ARM64 Snapdragon devices, enabling PyTorch inference acceleration on supported NPU and GPU backends.

Ultralytics YOLO26 quickstart for detection, instance and semantic segmentation, depth estimation, classification, pose, OBB, and tracking.

GitHub: https://github.com/ultralytics/yolo26

https://platform.ultralytics.com/ultralytics/yolo26

Ultralytics YOLO11 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

GitHub: https://github.com/ultralytics/yolo11

https://platform.ultralytics.com/ultralytics/yolo11

Ultralytics YOLOv8 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

GitHub: https://github.com/ultralytics/yolov8

https://platform.ultralytics.com/ultralytics/yolov8