Maxfashko

@elaith9 I managed to train two classes on the MS COCO data set. This requires a large amount of time and pre-weighed scales. One of the classes after 300 epochs...

It is bad style to change the compiler version on the system. Use cmake flags instead: ``` cmake -DTENSORRT_DIR= -DCMAKE_CXX_COMPILER=/usr/bin/g++-8 -DCMAKE_C_COMPILER=gcc-8 .. ``` @grimoire I propose to indicate in the...

@marwaSaid, the problem was solved?

Hello. Why not use cudnn? Why not add support cudnn in caffe-segnet?

You are welcome. I'm not sure that this is the final project code. I do not support him anymore. But the main frame is there. so here is the wrong...

@myth, the best thing I can advise you is to suppress the missing parts of the code yourself and fix the compilation errors. I'm not doing this project anymore.

Hi @chenzhi1992. I can not understand in what format the data to the enqueue function come to me. I realized that the data comes in an enqueue function in the...

What is the ConcatPlugin class implemented for? This class is not used anywhere. Instead it is used createConcatPlugin declared NvInferPlugin.h. ``` else if (!strcmp(layerName, "mbox_loc")) { assert(mBox_loc_layer.get() == nullptr); mBox_loc_layer...

@chenzhi1992 , I've reviewed the code caffe softmax layer https://github.com/BVLC/caffe/blob/master/src/caffe/layers/softmax_layer.cu. The main problem for me is how to set the axis for maximum summation and exponent operations. I understand correctly,...

@tianfanzhu, no, I did not solve this problem. I have other tasks, but as soon as I have time, I will study the code caffe