LFFD-MNN icon indicating copy to clipboard operation
LFFD-MNN copied to clipboard

MNN Implementation of the paper of LFFD: A Light and Fast Face Detector for Edge Devices

Results 8 LFFD-MNN issues
Sort by recently updated
recently updated
newest added

在mac上编译运行成功了,想测试一下使用opencl是否会更快一点,但是编译报错 Undefined symbols for architecture x86_64: "MNN::Interpreter::releaseModel()", referenced from: LFFD::~LFFD() in MNN_LFFD.cpp.o "MNN::Interpreter::resizeTensor(MNN::Tensor*, std::__1::vector const&)", referenced from: LFFD::detect(cv::Mat&, std::__1::vector&, int, int, float, float, int, std::__1::vector) in MNN_LFFD.cpp.o "MNN::Interpreter::createSession(MNN::ScheduleConfig const&)", referenced...

你好 我参考face detection 的方法转了head detection,得到了onnx和mnn模型 mnn模型检测的时候,没有框输出

Thank you very much for your efforts and contributions.

把mxnet模型转onnx模型前需要Note out(注释掉) the line 57(predict_score = mxnet.symbol.slice_axis(predict_score, axis=1, begin=0, end=1),现在我想用python+tensorrt推理onnx模型,如何得到注释the line 57之前的结果呢?

您好,您的源码可以在树莓派上正常编译和运行,不过,推理的时间较长,需要2s多; 如果我想在windows上测试,该如何修改?我修改了cmakelists文件如下:能够编译,但是运行的时候,报错:缺少MNN.dll和opencv_world410d.dll,请教正确的cmakelists文件该如何修改? 另外,我看到您的博客,讲如何在windows平台上编译转换工具,非常详细,但是我按照步骤进行下来报错: 一开始报运行时版本不匹配,我在vs里面修改了运行时以后,编译到99%的时候链接失败。。。 #1.cmake verson cmake_minimum_required(VERSION 2.8) #2.project name project(test C CXX) #opencv set(OpenCV_DIR C:/Users/YuKai/Downloads/opencv/opencv/build) #set(OpenCV_DIR env{OpenCV_DIR}) find_package(OpenCV REQUIRED) #3.set environment variable set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11") #4.mnn include include_directories(${CMAKE_CURRENT_LIST_DIR}/MNN/include) #...

您好,下载您的源码后,Ubuntu16.04上成功编译了,但进行测试时就报了Segmentation fault (core - dumped)的错误,debug后发现在`sess_lffd = lffd->createSession(config);`就莫名地报错停止了,请教您如何解决这个问题呢?