记录大模型相关的一些知识和方法

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild

A repo for update LLM models training, evaluate and application!

A Pytorch implement of medical image segmentation U-shape architecture benchmarks

Official Pytorch Code base for "CMUNeXt: An Efficient Medical Image Segmentation Network based on Large Kernel and Skip Fusion"

SAM3D: Segment Anything in 3D Scenes

包含人脸检测(Retinaface,yolov5face,yolov7face,yolov8face),人脸检测跟踪(ByteTracker)，人脸角度计算（Face_Angle）人脸矫正(Face_Aligner)，人脸识别(Arcface)，口罩检测(MaskRecognitiion)，年龄性别检测(Gender_age)，静默活体检测(Silent_Face_Anti_Spoofing…

Code for Boundary Difference Over Union Loss For Medical Image Segmentation

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

This project aims to improve image registration accuracy by integrating feature extraction and machine learning techniques. It involves a multi-step process, including preprocessing, feature detect…

Efficient Mixed Transformer for Single Image Super-Resolution

Image segmentation annotation tool with segment anything.（图像分割标注工具，支持语义分割与实例分割，集成segment anything，实现快速图像分割标注）

LDC: Lightweight Dense CNN for Edge Detectionでエッジ抽出を行い、その結果を細線化するサンプル

ChatGLM-6B：开源双语对话语言模型

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

FDSNet: An Accurate Real-Time Surface Defect Segmentation Network

Face Recognition Project on MXNet

This is an official implementation of our AAAI2022 paper“AdaptivePose: Human Parts as Adaptive Points”

Code for the ICCV 2021 paper "Pixel Difference Networks for Efficient Edge Detection" (Oral).

PyTorch implementation of Deep Homography Estimation.

Edge-Aware Multi-Level Interactive Network for Salient Object Detection of Strip Steel Surface Defects

The office implementation of Two-stage Deep Neural Network with Joint Loss and Multi-level Representations for Defect Detection

The official implementation of "Rethink Dilated Convolution for Real-time Semantic Segmentation"

OpenCVのGrabCut()を利用したセマンティックセグメンテーション向けアノテーションツール(Annotation tool using GrabCut() of OpenCV. It can be used to create datasets for semantic segmentation.)

code for Multi-scale Matching Networks for Semantic Correspondence, ICCV