TensorRT-Alpha

Visualization

Introduce

This repository provides accelerated deployment cases of deep learning CV popular models, and cuda c supports dynamic-batch image process, infer, decode, NMS.
There are two ways to compile model(pth or onnx):

Update

• 2023.01.01 🔥 update yolov3, yolov4, yolov5, yolov6
• 2023.01.04 🍅 update yolov7, yolox, yolor
• 2023.01.05 🎉 update u2net, libfacedetection
• 2023.01.08 🚀 The whole network is the first to support yolov8
• 2023.01.20 🍏 update efficientdet, pphunmanseg
• 2023.12.09 🍁 update yolov8-pose
• 2023.12.19 🍉 update yolov8-seg
• 2023.12.27 💖 update yolonas

Installation

The following environments have been tested：

# install miniconda first
conda create -n tensorrt-alpha python==3.8 -y
conda activate tensorrt-alpha
git clone https://github.com/FeiYull/tensorrt-alpha
cd tensorrt-alpha
pip install -r requirements.txt  

Installation Tutorial：

• Install For Ubuntu18.04
  
• Docker For Linux
  

Quick Start

Ubuntu18.04

set your TensorRT_ROOT path:

git clone https://github.com/FeiYull/tensorrt-alpha
cd tensorrt-alpha/cmake
vim common.cmake
# set var TensorRT_ROOT to your path in line 20, eg:
# set(TensorRT_ROOT /home/feiyull/TensorRT-8.4.2.4)

start to build project: For example:yolov8

Onnx

At present, more than 30 models have been implemented, and some onnx files of them are organized as follows:

🍉We will test the time of all models on tesla v100 and A100! Now let's preview the performance of yolov8n on RTX2070m(8G)：

model	video resolution	model input size	GPU Memory-Usage	GPU-Util
yolov8n	1920x1080	8x3x640x640	1093MiB/7982MiB	14%

cost time per frame

Some Precision Alignment Renderings Comparison

yolov8n : Offical( left ) vs Ours( right )


yolov7-tiny : Offical( left ) vs Ours( right )


yolov6s : Offical( left ) vs Ours( right )


yolov5s : Offical( left ) vs Ours( right )


yolov5s : Offical( left ) vs Ours( right )


libfacedetection : Offical( left ) vs Ours( right topK:2000)

Citation

@misc{FeiYull_TensorRT-Alpha,  
  author = {FeiYull},  
  title = {TensorRT-Alpha},  
  year = {2023},  
  publisher = {GitHub},  
  journal = {GitHub repository},  
  howpublished = {https://github.com/FeiYull/tensorrt-alpha}
}