PaddleSeg v2.3.0
·
57 commits
to release/2.3
since this release
新特性
- 发布交互式分割SOTA算法论文，EdgeFlow。
- 开源精细化分割Matting算法，DIM和MODNet。
- 新增分割模型压缩高阶功能，蒸馏和量化。
- 提供基于Paddle Inference的C++的分割模型预测指南。
- 提供Paddle Servering部署和导出ONNX模型的示例和指南。
- 新增经典模型SegNet，PointRend，图结构模型GINet，轻量级模型STDC，轻量级Transformer系列模型SegFormer。
- 新增损失函数：RMI Loss，Focal Loss，KL Loss，Detail Aggregate Loss， Point CE Loss。
- 支持自定义任意类别数量的color map，提升可视化效果。
问题修复
- #1240 修复CrossEntropyLoss在加权情况下的值越界问题。
- #1219 #1385 修复未训练完完整epoch退出时，dataloader随机抛出段错误的问题。
- #1113 修复多进程dataloader在不同epoch下随机数种子相同的bug。
New Features
- Published a paper on interactive segmentation named EdgeFlow.
- Released two Matting algorithms, DIM and MODNet.
- Provided advanced features on segmentation model compression, Knowledge Distillation and “Molde Quantization”.
- Provided the model inference tutorial based on Paddle Inference and Paddle Serving.
- Provided the ONNX exporting tutorial, which allows cross-platform deployment.
- Added five models, SegNet, PointRend, GINet, STDC, SegFormer.
- Added RMI Loss，Focal Loss，KL Loss，Detail Aggregate Loss， Point CE Loss.
- Support customized color map.