FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation (ICRA 2021)

ComfyUI Depth Anything (v1/v2) Tensorrt Custom Node (up to 14x faster)

Анализ трафика на круговом движении с использованием компьютерного зрения

Yolov5 TensorRT Implementations

you can use dbnet to detect word or bar code,Knowledge Distillation is provided,also python tensorrt inference is provided.

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

Production-ready YOLO8 Segmentation deployment with TensorRT and ONNX support for CPU/GPU, including AI model integration guidance for Unitlab Annotate.

VitPose without MMCV dependencies

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.

Convert ONNX models to TensorRT engines and run inference in containerized environments

An oriented object detection framework based on TensorRT

"Narrative Canvas" project is an edge computing project based on Nvidia Jetson. It can transform uploaded images into captivating stories and artworks.

Sinapsis repo with templates for face detection, face recognition and face verification

Export (from Onnx) and Inference TensorRT engine with Python

Dolphin is a python toolkit meant to speed up inference of TensorRT by providing CUDA-Accelerated processing.

Real-time traffic analysis, a small yet tricky pet project

This is an mnist example of how to transfer a .pt file to .onnx, then transfer .onnx file to .trt file.

Practical, beginner-friendly LLM projects using Python, LangChain, and LangSmith. Modular, reusable, and easy to run.