Closed ankurhanda closed 10 years ago
I think this has been solved in the dev branch and you can have some information here https://github.com/BVLC/caffe/issues/460 and here https://github.com/BVLC/caffe/pull/523
Closing -- this will be addressed by #523.
Dear all,
I would like to use conv-nets on NYU dataset http://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html where instead of one label per image you have multiple labels in an image i.e. per pixel labels for each image in the training dataset. Can somebody point me to any example in caffe that does that? How should one set up the first data layer? Is top: images_label exactly for this kind of stuff I'm looking for?
Regards, Ankur.