cvpr15deepcompare icon indicating copy to clipboard operation
cvpr15deepcompare copied to clipboard

Published 20 hours ago • verified publisher icon szagoruyko

caffe model output

Open edgarriba opened this issue 9 years ago • 4 comments

is it correct that the number of outputs is 1 for all the caffe models?

edgarriba avatar Feb 22 '16 19:02 edgarriba

I did not convert descriptor models assuming that its easy to edit prototxt file and get it

szagoruyko avatar Feb 22 '16 20:02 szagoruyko

hey! thanks for your answer but I'm not sure if I understood it. Does it mean that you haven't test it? After running Torch models the resultant descriptors have size 512. Last question about the benchmark, did you proper normalize patches regions before fetching the networks using VL_COVDET() with 'Patch' flag? URL Thanks in advance!

edgarriba avatar Feb 23 '16 09:02 edgarriba

@edgarriba caffe networks are tested against torch on conversion. Regarding VL_COVDET I don't remember, have to dig in the code. will answer later.

szagoruyko avatar Feb 23 '16 15:02 szagoruyko

nice! I'm struggling a bit to get proper results with your network. In the following plot I've tried some feature extractors and injected the results to vlfeat benchmark in the grafitti dataset. graf In this case MSER siam and siam2stream results come from the *.bin files you provide along with the raw patches obtained with MSER+VL_COVDET. MSER Alexnet is a caffe model in caffe repo. MSER iri is the model from this paper http://cvlabwww.epfl.ch/~trulls/pdf/iccv-2015-deepdesc.pdf

Thanks again!

edgarriba avatar Feb 23 '16 15:02 edgarriba