seed_split is used instead of split_seed

[rashadkp]

FlowNetPytorch/main.py

Line 113 in 60c72a9

if args.seed_split is not None:

Code is crashing because the usage seed_split instead we should use:
if args.split_seed is not None:
np.random.seed(args.split_seed)

[ClementPinard]

Hi, I do believe it's solved with the commits I just made, can you check it out ?

Moreover, I added the feature of saving the generated the split in a file to check that the split seed feature was working properly. This should now be saved in the folder contained in the save_path variable.