What the meaning of the 'response_up=8' in tracking.py?

[poppinjie]

trafficstars

I am confused with the viriable 'response_up' in 'disp_in_xcrop = disp_in_area * float(tot_stride) / response_up',in addition,what is the reason for calculating the distance like this.Can you explain it?

[bertinetto]

Hi, At inference time, the response is upsample. This has to be taken into account when computing the position in original frame coordinates.

Best, Luca

On Tue, Jul 9, 2019 at 10:32 AM poppinjie [email protected] wrote:

I am confused with the viriable 'response_up' in 'disp_in_xcrop = disp_in_area * float(tot_stride) / response_up',in addition,what is the reason for calculating the distance like this.Can you explain it?

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/bertinetto/siamese-fc/issues/75?email_source=notifications&email_token=AAZNDOMYHVIZLO675B6CJWLP6RLKNA5CNFSM4H7DRGE2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4G6BUGVA, or mute the thread https://github.com/notifications/unsubscribe-auth/AAZNDOJ2SBQH2EOL7T5MN3TP6RLKNANCNFSM4H7DRGEQ .

--

Luca Bertinetto | Research Scientist Oxford | +44 (0)7754214724 | www.robots.ox.ac.uk/~luca | @often_worried https://twitter.com/often_worried

[poppinjie]

Thank you so much for your reply! Another question comes to my mind now,I guess the variable 'tot_stride' means the multiple of overall stride in the network,right?So why you choose 4 as total stride in the code rather than 8 designed in the paper.