Is the AUC scored 0.665 obtained using this set of parameters?
LCAR979 opened this issue · comments
By keeping your default parameters, without fine-tune, I got 0.6466 on OTB2013 and 0.6206 on OTB2015 (guess you are using py2 so I also tested using py2). So is that 0.665 score obtained by matlab version?
By keeping your default parameters, without fine-tune, I got 0.6466 on OTB2013 and 0.6206 on OTB2015 (guess you are using py2 so I also tested using py2). So is that 0.665 score obtained by matlab version?
why I just got 0.6248 success rate on OTB2013 and 0.6037 on OTB2015？ Have you changed the python version? How's it going?
@jensenzhoujh, I got that result using py2. And I also tested if changed to py3, a few compatible problems will occur
@LCAR979 I changed to python 2.7 but got 0.6336/0.6014. Could you offer more details about the package versions?
By keeping your default parameters, without fine-tune, I got 0.6466 on OTB2013 and 0.6206 on OTB2015 (guess you are using py2 so I also tested using py2). So is that 0.665 score obtained by matlab version?
why I just got 0.6248 success rate on OTB2013 and 0.6037 on OTB2015？ Have you changed the python version? How's it going?
why do the results change when the python version changes?
@jensenzhoujh I tested using python2.7.15 with pytorch0.4.1, under commit #17007f .
@ucasqcz Division behaves differently in py2 and py3 and I think the author codes towards py2 ( there exists some compatibility problems)
I also got the 0.6466 success rate on OTB2013 too with python2.7