InsightFace REST API for easy deployment of face recognition services with TensorRT in Docker.

针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库

End2EndPerception deployment solution based on vision sparse transformer paradigm is open sourced.

Yolov5 TensorRT Implementations

Base on tensorrt version 8.2.4, compare inference speed for different tensorrt api.

VitPose without MMCV dependencies

Advanced inference pipeline using NVIDIA Triton Inference Server for CRAFT Text detection (Pytorch), included converter from Pytorch -> ONNX -> TensorRT, Inference pipelines (TensorRT, Triton server - multi-format). Supported model format for Triton inference: TensorRT engine, Torchscript, ONNX

The real-time Instance Segmentation Algorithm SparseInst running on TensoRT and ONNX

Convert yolo models to ONNX, TensorRT add NMSBatched.

Advance inference performance using TensorRT for CRAFT Text detection. Implemented modules to convert Pytorch -> ONNX -> TensorRT, with dynamic shapes (multi-size input) inference.

tensorrt-toy code

Simple tool for PyTorch >> ONNX >> TensorRT conversion

Export (from Onnx) and Inference TensorRT engine with Python

Tools for Nvidia Jetson Nano, TX2, Xavier.

Convenient Convert CRAFT Text detection pretrain Pytorch model into TensorRT engine directly, without ONNX step between

Real-time YOLO detection, multi-object tracking, and interactive object locking with TensorRT—optimized for NVIDIA Jetson (ARGUS via GStreamer) and GPUs.

YOLOv11-TensorRT implementation using Python

This repository demonstrates how to export a pre-trained ResNet18 model to ONNX, and then convert it to a TensorRT engine for fast inference.

YOLOv8-TensorRT implementation using Python

A CLI tool to convert Keras models to ONNX models and TensorRT engines