link to our preparation of the dataset with converted depth in the format of Gupta et al. '13

Colorize and visualize outputs by making images instead of relying on
embedded palettes. The palettes are now made in the PASCAL VOC style.

Note that other datasets can be handled by supplying a palette
as a no. of classes x 3 array.

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.

fix paths

FCN-AlexNet is trained with gradient accumulation and normalized loss.
online learning with unnormalized loss was unstable for FCN-AlexNet

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

...even though testing is handled apart from the solver