valid_sub_YouTube_VOS_dataset about stmask HOT 1 CLOSED

Since the GT of validation set is not public, we have to submit the .json file of validation set to the official web of Codelab to test the performance of models. It is very inconvenient. We, therefore, divide the train set of train.json into train_sub.json (top nine tenths) and valid_sub.json (the last tenth), hoping to make it more convenient to verify some ideas.

But for all reported results, we keep same settings with other methods. We train STMask on all train set after 12 epochs for YT and 20 epochs for OVIS. Because the more data, the better the result.

from stmask.