Code discontinued - please refer to the CFNet baseline-conv5 code

[bertinetto]

Hi all, I feel I could have it made clearer, so sorry about that.

At CVPR'17 we presented CFNet, which uses a slightly modified version of SiamFC (which I have been calling v2 or baseline-conv5) to compare against that paper's Correlation Filter Network. The difference is simply that it has only 32 output channel instead of 256 and it has activations with higher spatial resolutions. Results are slightly better, speed is slightly worse.

For this reason, if you are starting fresh it makes much more sense to use the more recent code from the CFNet repository, which is also a bit cleaner I think. However, if you have started with this repo, no worries. Things are just marginally different so there is no much use in switching.

Hope this clarifies the confusion!

I have also fixed the few broken links, so check again if you had a problem with that.

Cheers, Luca

[guwenning]

@bertinetto Hello ，awesome expert , I don't quite understand the 8 coordinates in ground_truth. I used a trace with a number of coordinates of 4 and found that the coordinates of the first frame did not completely wrap the target on the target.