Masataka Zen's starred repositories
VehicleReIdentificationDataset
Vehicle Re-Identification (ReID) dataset contains over 55,000 images for training and validation of the vehicle re-identification model
Japan_footprint_dataset
The Japan Footprint Dataset comprises approximately 50 million building footprints located within Japan extracted from Mapbox satellite imagery through the utilization of instance segmentation methods
GlobalMLBuildingFootprints
Worldwide building footprints derived from satellite imagery
chatgpt-on-wechat
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择GPT3.5/GPT-4o/GPT4.0/ Claude/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Claude/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
SpatialCorrection
Learning to Segment from Noisy Annotations: A Spatial Correction Approach
boxlevelset
The code for "Box-supervised Instance Segmentation with Level Set Evolution(ECCV2022)"
BoxTeacher
[CVPR 2023] Exploring High-Quality Pseudo Masks for Weakly Supervised Instance Segmentation
RSPrompter
This is the pytorch implement of our paper "RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model"
UC22-008-Building-matching-WebAPI
2D 地図データおよび 3D 点群データを 3D都市モデルの建物データと突合し、建物 ID との関連付けを行うWebAPI 機能を提供するサービスアプリケーションです。
segment-geospatial
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
Image2Paragraph
[A toolbox for fun.] Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.
Building-matching-WebAPI
2D建物ポリゴン/3D点群データと3D都市モデルのマッチングを行うシステム
segment-anything-eo
Earth observation tools for Meta AI Segment Anything
gpt_academic
为GPT/GLM等LLM大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。
awesome-chatgpt-prompts-zh
ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。
ultralytics
NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
japan-mesh-tool
地域メッシュを作成するツール