I’m working on a multi-animal project on monkey videos. In each video there are two monkeys.
I defined 31 body parts with 2 individuals (monkey 1 & monkey 2) and defined the skeletons following the over-connect rule in maDLC. I’m doing the training up to 103K iterations.
I do the training each time I add a few frames, and I notice that the train_rmse (calculated at the cross validation step) does not have a downward trend with increased frames, which is kind of counterintuitive to me. Here is the trend:
- What might be the possible reasons behind this? I double checked all the labels in all the frames, so there is no label quality issue here.
- Is train_rmse a good indicator at all to evaluate the performance of the model?
Any advice or comment is appreciated.