Hadi Ghahremannezhad

@jcarletgo thank you for the helpful tips. I removed the **conv5** and **pool4** layers and changed the lines below: ``` self._feat_stride = [16, ] self._feat_compress = [1. / 16., ]...

@yaoqi-zd Before I remove the conv5 and pool4 layers, when the feat_stride was still 16, I trained the model with anchor base size 16, 8 , 4 and 2. The...

@yaoqi-zd I haven't tried your suggestion yet, but it seems to be a good idea. I am going to try it hoping the results would become better than the full...

@smajida I have the same question. Have you managed to do the rotation along flipping code? Which file is the flipping code written in?

Yes, the problem is OpenCV DNN doesn't work with NVidia GPU. I found that out the hard way. If you have NVidia GPU try deep learning with other platforms, such...

@eweill Hello. I have a similar problem and have a basic question. For multi class detection do I have to change the dataset first? I mean if the dataset label...

@zyclarkcheng I changed my dataset format to **pascal_VOC** format and replaced pascal with my own. haven't tried @Mirorrn 's solution yet.

@ailias not yet. I have reduced the anchor base size from 16 to 2. It helped but not enough. I am trying to change the scale size to see if...

same problem here. Did you find any solution?

@lee2430 thanks a lot. setting "-D_GLIBCXX_USE_CXX11_ABI=0" to both the g++ lines for roi_pooling layer and psroi_pooling layer solved my problem.