[ECCVW 2022] The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"

Implementation of YOLOv9 QAT optimized for deployment on TensorRT platforms.

YOLOv8 using TensorRT accelerate !

This repository is based on shouxieai/tensorRT_Pro, with adjustments to support YOLOv8.

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Implementation of popular deep learning networks with TensorRT network definition API

State-of-the-art 2D and 3D Face Analysis Project

An open source library for face detection in images. The face detection speed can reach 1000FPS.

This is a note for ML2021 (Prof. Hung-Yi Lee, NTU).

🔥 YOLOv9 paper解析，训练自己的数据集，TensorRT端到端部署， NCNN安卓手机部署

YOLOv9 with Openvino Backend (C++ and Python)

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

QAT implementation on YOLOv8

Quantization Aware Training

A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT

A tutorial introducing knowledge distillation as an optimization technique for deployment on NVIDIA Jetson

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

YoloV6 for a bare Raspberry Pi using ncnn.

Stable Diffusion in NCNN with c++, supported txt2img and img2img

Fast Segment Anything

Official Implementation for "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery" (ICCV 2021 Oral)

YOLO-FaceV2: A Scale and Occlusion Aware Face Detector

Jupyter notebook tutorials for mmpose

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)

C++ library based on tensorrt integration

mobilenetv3 with pytorch，provide pre-train model

yolov5 segmentation with onnxruntime and opencv