Open ahrnbom opened 4 years ago
Hi,
there is a slight inconsistency, we first created a version of the MOTSchallenge data in the same format as KITTI and put it on https://www.vision.rwth-aachen.de/page/mots (where you still find it). Then we also put the MOTSChallene data under https://motchallenge.net/data/MOTS/ and changed the format slightly for consistency with MOT17. Probably we should modify the tools to support both formats, but I'll currently not get to this. Pull requests very welcome :) Soon also a separate repository with tools for all datasets of motchallenge.net will be released which will handle the new format (but will then not work with KITTI).
Hi,
there is a slight inconsistency, we first created a version of the MOTSchallenge data in the same format as KITTI and put it on https://www.vision.rwth-aachen.de/page/mots (where you still find it). Then we also put the MOTSChallene data under https://motchallenge.net/data/MOTS/ and changed the format slightly for consistency with MOT17. Probably we should modify the tools to support both formats, but I'll currently not get to this. Pull requests very welcome :) Soon also a separate repository with tools for all datasets of motchallenge.net will be released which will handle the new format (but will then not work with KITTI).
I've downloaded all KITTI_MOTS, MOTSChallenge, Detections for Tracking Only Challenge 2020 files from https://www.vision.rwth-aachen.de/page/mots but i don't known where to put them correctly.
Can you show the full tree list of the project? Thank you very much.
See issue #12
If one downloads the MOTS dataset from https://motchallenge.net/data/MOTS/, you get a folder structure for the training set, where ground truth files are all called
gt.txt
and placed in different folders for each sequence. io.py does not expect this, soload_sequences
fails unless you manually move and rename these files, which seems to work as a workaround...