Kin-Yiu, Wong

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

An official real-time object detection system that identifies and labels objects in images and video at up to 161 frames per second, with pre-trained models ready to use immediately and support for pose estimation and instance segmentation.

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

Scaled-YOLOv4: Scaling Cross Stage Partial Network

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)

PyTorch implementation of YOLOv4

Cross Stage Partial Networks

partial residual networks

Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual Language Models

Few Shot Semantic Segmentation Meets SAM3

Tutorial of sequential model of Keras

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

A simple baseline for one-shot multi-object tracking

No description.

No description.

No description.

Personal website of WongKinYiu

No description.

No description.

No description.

No description.

No description.

Models built with TensorFlow

No description.

OpenMMLab Detection Toolbox and Benchmark

No description.

No description.