CSP icon indicating copy to clipboard operation
CSP copied to clipboard

Published 20 hours ago • verified publisher icon liuwei16

Can not reproduce the results in the paper！

Open a1aaaaagithub opened this issue 5 years ago • 5 comments

Can not reproduce the results in the paper, using resnet-50, I loaded the weight provided by the author (net_e110_l0.0082234138241.hdf5), in the parse_det_offset function, when the threshold corresponding to seman is 0.01, there are countless misdetections, small targets Pedestrians can hardly detect it. Can anyone tell me how to reproduce the results in the author's paper?

a1aaaaagithub avatar Jul 18 '19 08:07 a1aaaaagithub

check this https://github.com/liuwei16/CSP/issues/38

msha096 avatar Jul 19 '19 16:07 msha096

@a1aaaaagithub did you solve the problem? I run his code and his model with paper's setting,but I can't get 4.5(MR), Do you know the reason?

super-wcg avatar Oct 08 '19 03:10 super-wcg

@a1aaaaagithub did you solve the problem? I run his code and his model with paper's setting,but I can't get 4.5(MR), Do you know the reason?

I run test model on Caltech and use his data/cache file.

super-wcg avatar Oct 08 '19 03:10 super-wcg

hello？Did you evaluate this weight？I evaluated this weight and got the MR of 99.8%. I am confused and do not know what's wrong.

fyture avatar Dec 20 '20 11:12 fyture

@a1aaaaagithub did you solve the problem? I run his code and his model with paper's setting,but I can't get 4.5(MR), Do you know the reason?

I run test model on Caltech and use his data/cache file.

What result do you got? I got MR of 99.8% which seems not right.

fyture avatar Dec 20 '20 11:12 fyture