Errors when run cnn_wsddn_demo.m

[anthony123]

the error messages is as followings:

尝试将 SCRIPT vl_nnspp 作为函数执行: /media/liuwq/7A0EA5000EA4B713/WSDDN/layers/matlab/vl_nnspp.m 出错 SPP/forward (line 97) outputs{1} = vl_nnspp(inputs{1}, self.levels, rois, ... 出错 dagnn.Layer/forwardAdvanced (line 85) outputs = obj.forward(inputs, {net.params(par).value}) ; 出错 dagnn.DagNN/eval (line 88) obj.layers(l).block.forwardAdvanced(obj.layers(l)) ; 出错 cnn_wsddn_demo (line 100) net.eval(inputs) ;

the scripts are:

opts.modelPath= 'models/vggf-edgeboxes-boxsc-spatreg.mat' ; opts.imdbPath = 'exp/imdb.mat' ; opts.train.gpus = 0; cnn_wsddn_demo(opts);

So what's the problem?

[hbilen]

You need to compile the code with vl_wsddn_compilenn.m instead of vl_compilenn.m and set opts.train.gpus = [] or opts.train.gpus =1 if you have a gpu

[anthony123]

Thank you. It solved my problem

[alexshaodong]

You need to compile the code with vl_wsddn_compilenn.m instead of vl_compilenn.m and set opts.train.gpus = [] or opts.train.gpus =1 if you have a gpu

Hello! If I want to train with my own data, how to generate edgeboxes mat files, similar to EdgeBoxes VOC2007trainval. mat and EdgeBoxes VOC2007test. mat files.

[alexshaodong]

Thank you. It solved my problem

Hello! If I want to train with my own data, how to generate edgeboxes mat files, similar to EdgeBoxes VOC2007trainval. mat and EdgeBoxes VOC2007test. mat files.