[example] add fully-convolutional efficiency note + confidence map
authorEvan Shelhamer <shelhamer@imaginarynumber.net>
Sun, 24 Aug 2014 22:36:52 +0000 (15:36 -0700)
committerEvan Shelhamer <shelhamer@imaginarynumber.net>
Sun, 24 Aug 2014 22:40:49 +0000 (15:40 -0700)
commit99bea71ce48eba5a4cd30d7f6b68b30fc9a97f92
tree4e1c7d7b6d3fd2e245810f376391b6609d87ac1b
parentac85f8136b287f231ea495ecba5a72341018a1ae
[example] add fully-convolutional efficiency note + confidence map

- spell out fully-convolutional efficiency
- add confidence map
- fix input size: 451 x 451 is correct for an 8 x 8 output map by the
  equation input size = 227 + 32(d-1) for output map dimension of d
examples/imagenet/imagenet_full_conv.prototxt
examples/net_surgery.ipynb