PaddlePaddle / FastDeploy

⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization, multi-platform and multi-framework support.

Home Page:https://www.paddlepaddle.org.cn/fastdeploy

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Failed to load yaml file weights/cls_mv3.yml

xpzwzwz opened this issue · comments

我用C++部署paddleocr里的官网给的推理模型时,也就是下面这个,
image
对应的yml配置文件也是官网给的推理模型对应的cls_mv3

部署代码也使用的是官方例子,如下:
option.UseGpu();
model = new fastdeploy::vision::classification::MobileNetv2(model_file, params_file, infer_cfg_file, option)
给我报错了:
[ERROR] fastdeploy/vision/classification/ppcls/preprocessor.cc(36)::fastdeploy::vision::classification::PaddleClasPreprocessor::BuildPreprocessPipelineFromConfig Failed to load yaml file weights/cdn_cls.yml, maybe you should check this file.
[ERROR] fastdeploy/vision/classification/ppcls/preprocessor.cc(26)::fastdeploy::vision::classification::PaddleClasPreprocessor::PaddleClasPreprocessor Failed to create PaddleClasPreprocessor.

请问这是怎么回事

是不是因为导出的模型比较新,FD还不支持