How to prepare new dataset?
jdyjjj opened this issue · comments
Great job, I have benefited a lot. I would like to train on the videos I have collected. What should I do if I want to train with my video dataset? Thank you.
I'd also like to know! Is there an "easy" way to take the tracked points and re-train/re-fine the model?
Hi @nikitakaraevv, I adapted the KubrikMovifDataset to a local dataset. In my case, I have 180 points to track per video. However, when sampling data with augmentations, I sometimes end up with fewer points. I these cases, the getitem_helper function return gotit=False. Is that a wished behaviour?
Thanks for your answers!
Hi @Anderstask1, some points don't satisfy the sampling criteria: being visible in the first frame or the middle frame of the sequence. That's why we sometimes end up with fewer points, especially if we don't have additional points to sample from. I think you can modify the sampling criteria to make it less strict:
Hi again @nikitakaraevv, I modified the sampling criteria to make it less strict. However, during training, it seems like several points are sampled mid-sequence in the provided prediction videos (even though the ground truth video don't sample points mid-sequence). Do you know the reason for this?