Typos in training guidelines?

[noahcao]

Hi Xingyi,

Thanks for the wonderful job. I tried to run the training on MOT17 following the guidelines. But I found some potential typos making that doable.

1. Should we rename the MOT17 train to trainval, which is not explained in the prepare datasets doc?
2. Should the datasets for training be ("mot17_halftrain","crowdhuman_train") instead of ("mot17_halftrain","crowdhuman_amodal_train") in the config file? the later one would raises an error of unregistered dataset:
   

[xingyizhou]

Thank you a lot for pointing out the issue! You are correct in both. I fixed them in the most recent commit.

Best,
Xingyi

[noahcao]

Thanks. I think the current version fixed the problem.