apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
Files
fe2882a1ef70ecb54ed2f162c249bb8abc105f96
FastDeploy/examples/vision/segmentation/paddleseg/cpu-gpu
History
chenjian c8bcada1a2 [Doc] Add docs for ppocr ppseg examples (#1429) 
* add docs for examples

* add english doc

* fix

* fix docs
2023-02-28 20:13:01 +08:00
..
c
[Doc] Add docs for ppocr ppseg examples (#1429)
2023-02-28 20:13:01 +08:00
cpp
[Backend] Support onnxruntime DirectML inference. (#1304)
2023-02-17 10:53:51 +08:00
csharp
[Doc] Add docs for ppocr ppseg examples (#1429)
2023-02-28 20:13:01 +08:00
python
Update docs
2023-02-08 16:33:12 +00:00
README.md
Update ppmatting directory
2023-02-09 07:38:11 +00:00

README.md

English | 简体中文

PaddleSeg模型高性能全场景部署方案-FastDeploy

PaddleSeg支持利用FastDeploy在NVIDIA GPU、X86 CPU、飞腾CPU、ARM CPU、Intel GPU(独立显卡/集成显卡)硬件上部署Segmentation模型

模型版本说明

注意：支持PaddleSeg高于2.6版本的Segmentation模型

目前FastDeploy支持如下模型的部署

注意 如部署的为PP-Matting、PP-HumanMatting以及ModNet请参考Matting模型部署

准备PaddleSeg部署模型

PaddleSeg模型导出，请参考其文档说明模型导出

注意

  • PaddleSeg导出的模型包含model.pdmodel、model.pdiparams和deploy.yaml三个文件，FastDeploy会从yaml文件中获取模型在推理时需要的预处理信息

预导出的推理模型

为了方便开发者的测试，下面提供了PaddleSeg导出的部分模型

  • without-argmax导出方式为：不指定--input_shape，指定--output_op none
  • with-argmax导出方式为：不指定--input_shape，指定--output_op argmax

开发者可直接下载使用。

模型 参数文件大小 输入Shape mIoU mIoU (flip) mIoU (ms+flip)
Unet-cityscapes-with-argmax | Unet-cityscapes-without-argmax 52MB 1024x512 65.00% 66.02% 66.89%
PP-LiteSeg-B(STDC2)-cityscapes-with-argmax | PP-LiteSeg-B(STDC2)-cityscapes-without-argmax 31MB 1024x512 79.04% 79.52% 79.85%
PP-HumanSegV1-Lite-with-argmax(通用人像分割模型) | PP-HumanSegV1-Lite-without-argmax(通用人像分割模型) 543KB 192x192 86.2% - -
PP-HumanSegV2-Lite-with-argmax(通用人像分割模型) | PP-HumanSegV2-Lite-without-argmax(通用人像分割模型) 12MB 192x192 92.52% - -
PP-HumanSegV2-Mobile-with-argmax(通用人像分割模型) | PP-HumanSegV2-Mobile-without-argmax(通用人像分割模型) 29MB 192x192 93.13% - -
PP-HumanSegV1-Server-with-argmax(通用人像分割模型) | PP-HumanSegV1-Server-without-argmax(通用人像分割模型) 103MB 512x512 96.47% - -
Portait-PP-HumanSegV2-Lite-with-argmax(肖像分割模型) | Portait-PP-HumanSegV2-Lite-without-argmax(肖像分割模型) 3.6M 256x144 96.63% - -
FCN-HRNet-W18-cityscapes-with-argmax | FCN-HRNet-W18-cityscapes-without-argmax(暂时不支持ONNXRuntime的GPU推理) 37MB 1024x512 78.97% 79.49% 79.74%
Deeplabv3-ResNet101-OS8-cityscapes-with-argmax | Deeplabv3-ResNet101-OS8-cityscapes-without-argmax 150MB 1024x512 79.90% 80.22% 80.47%
SegFormer_B0-cityscapes-with-argmax | SegFormer_B0-cityscapes-without-argmax 15MB 1024x1024 76.73% 77.16% -

详细部署文档