Skip to main content

Web Based Multi Purpose Annotation - ML backend

Project description

PaddleLabel-ML

PaddleLabel机器学习辅助标注后端。

目前基于EISeg实现了交互式分割功能。

安装说明

通过PIP安装

pip install paddlelabel-ml

通过源码安装

首先将代码克隆到本地:

git clone https://github.com/PaddleCV-SIG/PaddleLabel-ML

安装:

cd PaddleLabel-ML
python setup.py install

启动

完成上述的安装操作后,可以直接在终端使用如下指令启动PaddleLabel的机器学习端。

paddlelabel_ml  # 启动ml后端

*模型下载

模型类型 适用场景 模型结构 模型下载地址
高精度模型 通用场景的图像标注 HRNet18_OCR64 static_hrnet18_ocr64_cocolvis
轻量化模型 通用场景的图像标注 HRNet18s_OCR48 static_hrnet18s_ocr48_cocolvis
高精度模型 通用图像标注场景 EdgeFlow static_edgeflow_cocolvis
高精度模型 人像标注场景 HRNet18_OCR64 static_hrnet18_ocr64_human
轻量化模型 人像标注场景 HRNet18s_OCR48 static_hrnet18s_ocr48_human
轻量化模型 遥感建筑物标注场景 HRNet18s_OCR48 static_hrnet18_ocr48_rsbuilding_instance
高精度模型* x光胸腔标注场景 Resnet50_Deeplabv3+ static_resnet50_deeplab_chest_xray
轻量化模型 医疗肝脏标注场景 HRNet18s_OCR48 static_hrnet18s_ocr48_lits
轻量化模型* MRI椎骨图像标注场景 HRNet18s_OCR48 static_hrnet18s_ocr48_MRSpineSeg
轻量化模型* 质检铝板瑕疵标注场景 HRNet18s_OCR48 static_hrnet18s_ocr48_aluminium

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

paddlelabel_ml-0.5.0.tar.gz (67.2 MB view hashes)

Uploaded Source

Built Distribution

paddlelabel_ml-0.5.0-py3-none-any.whl (67.2 MB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page