shouxieai/tensorRT_Pro
C++ library based on tensorrt integration
This framework helps computer vision engineers and AI developers quickly deploy high-performance object detection and recognition systems. It takes trained deep learning models (like YOLO) and images as input, then outputs the locations and categories of objects found in those images. This is ideal for those needing to integrate fast, accurate visual AI into their applications or devices.
2,861 stars. No commits in the last 6 months.
Use this if you need to deploy object detection models with high speed and efficiency on NVIDIA TensorRT-compatible hardware, supporting both C++ and Python.
Not ideal if you are looking for a tool to train new deep learning models or if your deployment environment does not support NVIDIA GPUs with TensorRT.
Stars
2,861
Forks
578
Language
C++
License
MIT
Category
Last pushed
May 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/shouxieai/tensorRT_Pro"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
ultralytics/yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
ultralytics/yolov3
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
mindspore-lab/mindyolo
A toolbox of yolo models and algorithms based on MindSpore
ultralytics/assets
Ultralytics assets
stephanecharette/DarkHelp
C++ wrapper library for Darknet