Samples code for world class Artificial Intelligence SoCs for computer vision applications.

1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.

[TPAMI 2024] Probabilistic Contrastive Learning for Long-Tailed Visual Recognition

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

Code for paper DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume Reconstruction

Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.

OpenDILab Decision AI Engine

3D face swapping implemented in Python

Mask-Free Video Instance Segmentation [CVPR 2023]

Scribbles or Points-based weakly-supervised learning for medical image segmentation, a strong baseline, and tutorial for research and application.

Learning OpenCV 4 Computer Vision with Python 3 – Third Edition, published by Packt

code from the AMLP-Conv paper (MLMI 2022)

医学影像数据集列表 『An Index for Medical Imaging Datasets』

OpenCV-Python4.1 中文文档

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image …

Cross-Encoder for Unsupervised Gaze Representation Learning

Fast and flexible Gaussian Process regression in Python

ERPQ (EISeg Remote sensing Plugin in QGIS) is a QGIS plugin extracted by EISeg.

This is the official implementation of "An optimized two-stage cascaded deep neural network for adrenal segmentation on CT images".

[ICCV 2021 Oral] Mining Latent Classes for Few-shot Segmentation

2018年甜橙金融杯大数据建模大赛-初赛第四-复赛线上11-决赛9-复现top1解决方案

Manage and switch between multiple proxies quickly & easily.

常用中国网站白名单，纯列表，用于 SwitchyOmega，控制不走代理的网站。

Website of the book "Learn OpenCV 3 with Python"

PyTorch implementation of One-Shot Video Object Segmentation (OSVOS)

novel deep learning research works with PaddlePaddle

OCR toolkit based on PaddlePaddle （基于飞桨的OCR工具库，包含总模型仅8.6M的超轻量级中文OCR，同时支持多种文本检测、文本识别的训练算法、服务部署和端侧部署）