jkjung-avt/tensorrt_demos
Collection of examples optimizing Caffe, TensorFlow, DarkNet, and PyTorch models for inference using NVIDIA TensorRT.
Not currently ranked — collecting fresh signals.
star history
This repository provides demos for running optimized deep learning models on NVIDIA hardware using TensorRT. It covers multiple computer vision tasks including object detection with YOLOv3 and YOLOv4, SSD-based detection, MTCNN face detection, GoogLeNet image classification, and MODNet video matting. The demos target embedded NVIDIA Jetson platforms as well as x86_64 PCs with NVIDIA GPUs, focusing on practical inference performance optimization.
Frequently asked
- What is jkjung-avt/tensorrt_demos?
- Collection of examples optimizing Caffe, TensorFlow, DarkNet, and PyTorch models for inference using NVIDIA TensorRT.
- Is tensorrt_demos open source?
- Yes — jkjung-avt/tensorrt_demos is open source, released under the MIT license.
- What language is tensorrt_demos written in?
- jkjung-avt/tensorrt_demos is primarily written in Python.
- How popular is tensorrt_demos?
- jkjung-avt/tensorrt_demos has 1.8k stars on GitHub.
- Where can I find tensorrt_demos?
- jkjung-avt/tensorrt_demos is on GitHub at https://github.com/jkjung-avt/tensorrt_demos.