warn about the perils of not initializing the weights.
in the future this will be handled by the FCN solving script, but not
just yet.

The usual FCN-32/16/8s on the 59 class task of the PASCAL-Context full
object and scene labeling of PASCAL VOC 2010.

These nets are jointly trained for segmentation of semantic and
geometric classes since this dataset includes annotations for both.

- FCN-32s SIFT Flow
- FCN-16s SIFT Flow
- FCN-8s SIFT Flow

TODO: fix semantic class evaluation for this dataset, which requires
special care since there are missing classes in the test set.

- FCN-32s Color: FCN-32s arch on BGR input
- FCN-32s HHA: FCN-32s arch on HHA input
- FCN-32s Color-Depth (early): early fusion for BGR-D input
- FCN-32s Color-HHA (late): late fusion of FCN-32s Color + FCN-32s HHA

This net is fine-tuned from VGG-16 all-at-once instead of in stages.
All-at-once learning is faster and less tedious but gives an
ever-so-slightly less accurate model.

include preliminary version of reference PASCAL models for PAMI edition