⚡️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.
rpdzkj@rpdzkj:~/Downloads/fastdeploy1.0.4/examples/vision/detection/paddledetection/a311d/cpp/Adboard$ ./run_demo.sh
[INFO] fastdeploy/vision/common/processors/base.cc(92)::EnableFlyCV Will change to use image processing library ProcLib::FLYCV
[dhq info] runtime.Init(option); Done
[dhq info] cv::imread(image_file); Done
[INFO] fastdeploy/vision/common/processors/transform.cc(93)::FuseNormalizeHWC2CHW Normalize and HWC2CHW are fused to NormalizeAndPermute in preprocessing pipeline.
[INFO] fastdeploy/vision/common/processors/transform.cc(159)::FuseNormalizeColorConvert BGR2RGB and NormalizeAndPermute are fused to NormalizeAndPermute with swap_rb=1
[dhq info] auto preprocessor = fastdeploy::vision::classification::PaddleClasPreprocessor(config_file); Done
./run_demo.sh: line 14: 10508 Segmentation fault (core dumped) ./build/infer_demo ./models/feature_extract_convfalse ./images/Adboard_clas_test_img02.jpg
环境
-【FastDeploy版本】: fastdeploy-linux-1.0.4 源码 -【编译命令】cmake -DCMAKE_TOOLCHAIN_FILE=./../cmake/toolchain.cmake -DWITH_TIMVX=ON -DTARGET_ABI=arm64 -DENABLE_FLYCV=ON -DCMAKE_INSTALL_PREFIX=fastdeploy-timvx -DENABLE_VISION=ON -DENABLE_LITE_BACCKEND=ON -Wno-dev .. -【系统平台】: aarch64 linux kernel 4.9.113,gcc、g++=9.3.0,make=4.2.1,cmake=3.22.6,ubuntu 20.04 arm64 -【硬件】: 荣品A311D,NPU驱动已经安装为 6.4.4.3 -【编译语言】: C++
问题日志及出现问题的操作流程
【模型跑不通】
按这个方式,在程序执行到 preprocessor.Apply(&fd_mats, &inputs); 这一句时报错:
./run_demo.sh: line 14: 10508 Segmentation fault (core dumped) ./build/infer_demo ./models/feature_extract_convfalse ./images/Adboard_clas_test_img02.jpg
完整的Log信息如下:
用到的文件和模型已经打包上传到source_files.zip,其中包含:
推理代码:infer_ppshitu.cc,自己修改过。 编译脚本:generate_demo.sh 运行脚本:run_demo.sh 模型文件:feature_extract_convfalse 测试图片:Adboard_clas_test_img02.jpg