PaddleSeg v2.5.0

New Features

• Release PP-LiteSeg, a superior real-time semantic segmentation model. It achieves 273.6FPS on 1080Ti.
• Release PP-Matting, a trimap-free image matting model for extremely fine-grained segmentation. It achieves SOTA performance on Composition-1k and Distinctions-646.
• Release MedicalSeg, a newly easy-to-use toolkit for 3D medical imaging. It supports the whole segmentation process including data preprocessing, model training, and model deployment, and provides high-accuracy models on lung and spine segmentation.
• Release EISeg v0.5, with three more interactive models for chest Xray, MRI spine and defect inspection.
• Add 5 semantic segmentation models: ENet, CCNet, DDRNet, GloRe, PP-LiteSeg.
• Add 1 loss function: MultiClassFocalLoss.
• Support AMP training, including O1 and O2 levels.

新特性

• 发布超轻量级语义分割模型PP-LiteSeg技术报告以及开源模型，在1080Ti GPU上推理速度达到273.6FPS。
• 发布高精度抠图模型PP-Matting技术报告以及开源模型，在Composition-1K和Distinctions-646上实现SOTA。
• 发布3D医疗影像开发套件MedicalSeg，支持数据预处理、模型训练、模型部署等全流程开发，并提供肺部、椎骨数据上的高精度分割模型。
• 发布交互式分割工具EISeg v0.5版本，新增胸片X光、医学椎骨、工业质检标注垂类方向。
• 新增5个分割模型：ENet, CCNet, DDRNet, GloRe, PP-LiteSeg。
• 新增1个损失函数：MultiClassFocalLoss。
• 完整支持混合精度训练能力，包括O1、O2模式训练、边训边评估。

Bug Fix

• Add init weights for hrnet_contrast. #1746
• Fix the overflow error in calculating kappa. #1788
• Fix GINet interpolate problem. #1846
• Fix the error of nonetype object for quant. #1854
• Fix Enet export and infer problem. #1919
• Fix SemanticConnectivityLoss bug on cpu. #1940
• Fix import error of tensor_fusion. #2023
• Fix a prediction bug without val dataset. #1816

New Contributors

• @xmba15 made their first contribution in #1743
• @ChenjieXu made their first contribution in #1791
• @ykkk2333 made their first contribution in #1815
• @windstamp made their first contribution in #1926

Full Changelog: v2.2.0...v2.5