mview/mxnet-samples

mxnet-samples's Issues

the engine.h cannot find on windows? you may test this on ubuntu?

Did you test it on ubuntu,since you include engine.h. I just build it on windows, but cannot find the engine.h, so the speed is not well, it cost 100ms on windows when I Remove it. could please implete it on windows? if so, thank you very much

[bug] Obvious memory leaks were detected.

Hello, thank you for your work. I ran this code, but found that memory keeps going up when I calculate the same picture iteratively.
In addition, I found that the speed of CPU single-core single-threading is: Detect 690X460 Time Using CPU: 170, which is about twice slower than the c_api version of MTCNN (of course, speed is not so important if memory problems can be solved).

This function has obvious problems:

    inline const std::vector<Blob*> output_blobs(){
        out_blobs.erase( out_blobs.begin(),out_blobs.end() );
        for (auto &output:executor_->outputs) {
            Blob *data=new Blob(output.GetShape(),Context::cpu());
            output.SyncCopyToCPU(data->cpu_data(),data->Size());
            out_blobs.push_back(data); 
        }
        return out_blobs;
    }

The new Blob pointer is stored in the vector, and the erase vector's content only destroys the pointer but does not release the memory pointed to by the pointer.
I try to delete all the pointers in vector before erase, but core dumped. It is estimated that the pointer is still used by other functions, so I'm afraid the whole code structure needs to be modified.

cmake

请问你是在ubuntu上执行的main吗？只看到了make文件，想找cmakelist

mxnet mtcnn c++ version runtime error

Segmentation fault (core dumped)