enazoe/yolo-tensorrt

Health v2 · maintenance only

Adoption not part of the score

1202 stars · 312 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A C++ wrapper around NVIDIA TensorRT for running YOLO object detection models (YOLOv3, YOLOv4, YOLOv5) with support for FP32, FP16, and INT8 precision. It converts Darknet weights and PyTorch YOLOv5 models into optimized TensorRT engines for x86 GPUs and Jetson embedded platforms.

Use cases

• deploy yolo models with tensorrt
• run yolov5 inference on jetson xavier nx
• convert darknet weights to tensorrt engine
• int8 quantized object detection on gpu
• batch inference for yolo models in c++
• fast object detection on embedded nvidia devices

When to choose

• you need high-performance YOLO inference via TensorRT in C++
• you are deploying on NVIDIA Jetson (L4T) hardware
• you want FP16/INT8 optimized YOLOv3/v4/v5 detection

When to avoid

• you need a Python-first inference pipeline
• you use YOLO versions beyond v5 or dynamic input sizes
• you want a maintained framework with frequent updates

Facets

library · maturity maintenance

machine-learning computer-vision image-processing gpu-computing computer-vision deep-learning gpu-computing embedded-systems windows cpp yolo tensorrt object-detection darknet inference jetson fp16 int8-quantization linux gpu nvidia-jetson

Member repositories

For agents

markdown · JSON · MCP: product_card(name="enazoe/yolo-tensorrt")