graycrown

@JUGGHM Thanks for your excellent work. I am trying to re-implement your training process, but there's a few questions confused me: 1. Whether the larger batch size leads to better...

> > @JUGGHM Thanks for your excellent work. I am trying to re-implement your training process, but there's a few questions confused me: > > > > 1. Whether the...

> Hi @JiaxiongQ , > After I prepared the 3 folders: `RGBLeft`, `lidar` and `Normals_m` from `/Town11/SEQ` (to test that the training work), I'm getting the following error: > >...

Is there any solution for this problem, I met the same problem

In my opinion, I think it should be op_l32_pool.

I can't acess the links you guys providid ( drive link is forbiden in Lab ) Is there any idea about training the mdoel without pretrained model ? Maybe I...

I am in the same condition, have you solved it?

If you run this code on ubuntu , try "g++ -o mtcnn_opencv mtcnn_opencv.cpp -std=c++11", it seems like that the error is caused by C++11 new feature.

What's the resolution of yout test image? I test the code on the image images which resolution is 1024 * 576, it take 0.87s for every image( I have changed...