sygoing / lffd-openvino Goto Github PK

Dear SyGoing,
I have been trying to convert lffd models to openvino, I have edited the symbol .json as stated but I keep facing this error :

[ ERROR ] Input model name /home/avidbeam/amrm_workspace/lffd_openvino/v4_openvino/train_30_320_20L_4scales_v1_iter_500000.params is not in an expected format, cannot extract iteration number.

here is my conversion command:
python3 mo_mxnet.py --input_symbol ./v4_openvino_deploy.json --input_model ./v4_iter_320000.params

Do you have any hints for a successful conversion?
Thanks in advance

Hi,

Anybody has tested this software with Intel VPU?

Any reference on the performance compared to GPU, CPU?

Thank you

I'm new to Openvino, can you provide the CMakeLists.txt. thx!

你好，我用VS2015、openvino_2019.2.242版本进行编译，报如下错误：

错误 C2664 “int LFFD::detect(cv::Mat &,std::vector<FaceInfo,std::allocator<Ty>> &,int,int,float,float,int,std::vector<int,std::allocator>)”: 无法将参数 3 从“cv::Size”转换为“int” OpenVINO_LFFD E:\clion_kdevelop\OpenCV\dnn_VS\OpenVINO_LFFD\main.cpp 37

错误 C2664 “int LFFD::detect(cv::Mat &,std::vector<FaceInfo,std::allocator<Ty>> &,int,int,float,float,int,std::vector<int,std::allocator>)”: 无法将参数 3 从“cv::Size”转换为“int” OpenVINO_LFFD E:\clion_kdevelop\OpenCV\dnn_VS\OpenVINO_LFFD\main.cpp 67

错误 C4996 'InferenceEngine::PluginDispatcher::getPluginByDevice': 被声明为已否决 OpenVINO_LFFD E:\clion_kdevelop\OpenCV\dnn_VS\OpenVINO_LFFD\OpenVINO_LFFD.cpp 58

错误 C4996 'InferenceEngine::Blob::dims': 被声明为已否决 OpenVINO_LFFD E:\clion_kdevelop\OpenCV\dnn_VS\OpenVINO_LFFD\OpenVINO_LFFD.cpp 131

错误 C4996 'InferenceEngine::Blob::dims': 被声明为已否决 OpenVINO_LFFD E:\clion_kdevelop\OpenCV\dnn_VS\OpenVINO_LFFD\OpenVINO_LFFD.cpp 132

请问应该用什么版本的OpenVINO？谢谢！

Hi! I'm trying to use the code with OpenVINO 2020.4. But it does not work. It cannot find any faces on video (