T

TensorRT

High-performance Ultralytics YOLO inference in Rust with ONNX Runtime, GPU backends, CLI, and WebGPU/WASM.

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

https://docs.ultralytics.com/inference

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

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

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

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/

Edge deployment suite for RTUAV-YOLO frequency-attention drone detector (Zhang et al.). Trained on Seraphim dataset (95.63% mAP50, 0.78M params). Features NVIDIA TensorRT (445+ FPS), Apple CoreML ANE (328+ FPS), static ONNX, FastAPI, & Docker.

DeepSpeed / PyTorch Distributed + TensorRT export

Real-time YOLOv7/YOLOv7‑Tiny object detection on low‑powered Jetson Orin Nano using TensorRT and a multi‑threaded ROS 1 pipeline for edge robotics, drone monitoring.

Jetnet is a blazing fast TensorRT implementation in C++ of YOLOv3, YOLOV3-tiny and YOLOv2