English | 简体中文
This repository provides accelerated deployment cases of deep learning CV popular models, and cuda accelerated methods for pre-processing and post-processing of mainstream models. Most of the model transformation process is torch->onnx->tensorrt. There are two ways to obtain onnx files:
- According to the network disk provided by this repository, download ONNX directly
- Follow the instructions provided in this repository to manually export ONNX from the relevant source code framework.
graph LR
pytorch/tensorflow -->onnx-->tensorrt
- 2023.01.01 🔥 update yolov3, yolov4, yolov5, yolov6
- 2023.01.04 🍅 update yolov7, yolox, yolor
- 2023.01.05 🎉 update u2net, libfacedetction
- 2023.01.08 🚀 The whole network is the first to support yolov8
Compatible platforms: windows、linux
- cuda11.6
- cudnn8.4
- tensorrt8.4.2.4
- opencv3.x
python dependent environment(optional):
# 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
set your TensorRT_ROOT path:
cd tensorrt-alpha/cmake
vim common.cmake
# set var TensorRT_ROOT to your path in line 20, eg:
# set(TensorRT_ROOT /root/TensorRT-8.4.2.4)
start to build project: For example:yolov7
waiting for update
At present, more than 30 models have been implemented, and some onnx files of them are organized as follows:
model | weiyun | google driver |
---|---|---|
yolov3 | weiyun | google driver |
yolov4 | weiyun | google driver |
yolov5 | weiyun | google driver |
yolov6 | weiyun | google driver |
yolov7 | weiyun | google driver |
yolov8 | weiyun | google driver |
yolox | weiyun | google driver |
yolor | weiyun | google driver |
u2net | weiyun | google driver |
libfacedet | weiyun | google driver |
facemesh | weiyun | google driver |
more...(🚀: I will be back soon!) |
some precision alignment renderings comparison:
yolov8n : Offical( left ) vs Ours( right )
yolov7-tiny : Offical( left ) vs Ours( right )
yolov5s : Offical( left ) vs Ours( right )
libfacedetction : Offical( left ) vs Ours( right topK:4000)
[0].https://github.com/NVIDIA/TensorRT
[1].https://github.com/onnx/onnx-tensorrt
[2].https://github.com/NVIDIA-AI-IOT/torch2trt
[3].https://github.com/shouxieai/tensorRT_Pro
[4].https://github.com/opencv/opencv_zoo