FlowNetPytorch icon indicating copy to clipboard operation
FlowNetPytorch copied to clipboard

seed_split is used instead of split_seed

Open rashadkp opened this issue 1 year ago • 1 comments

https://github.com/ClementPinard/FlowNetPytorch/blob/60c72a9c054e6e525eca5cc129ccafc11758d88f/main.py#L113

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)

rashadkp avatar Mar 23 '24 11:03 rashadkp

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.

ClementPinard avatar Mar 24 '24 21:03 ClementPinard