[WIP] flownet2-docker comparison

[BlGene]

I've tried to compare the flownet2-pytorch results to flownet2-docker results

1. for this I created copy/simlink of the flownet2-docker directory in the flownet2-pytorch directory.
2. In this directory I then ran the flownet2-docker command ./run-network.sh -n FlowNet2 -v data/0000000-imgL.png data/0000001-imgL.png flow.flo
3. I then ran the new run_pair.py command.

I get a very large difference(L2 norm of 81202.305) between the predicted flows, basically flownet2-pytorch is not working for some reason.

Things that I haven't looked at yet are pre-processing:

1. RGB vs BGR
2. Normalization (divide by 255.0)?
3. multiply by 20?