KeyError: 'frames'

[hyping111]

My purpose is to calculate the evaluation metrics in the paper，and I found instructions and codes for calculating Multi Object Tracking and Segmentation metrics on BDD100K's website(https://doc.bdd100k.com/evaluate.html#multi-object-tracking-and-segmentation-segmentation-tracking), when I run the following code to evaluate the algorithms with public annotations,

python -m bdd100k.bdd100k.eval.run -t seg_track -g /home/dlz/pcan/data/bdd/labels/seg_track_20/seg_track_val_cocoformat.json -r /home/dlz/pcan/paintedimg.zip

I got an error:
Traceback (most recent call last):
File "/home/dlz/anaconda3/envs/pcan/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/home/dlz/anaconda3/envs/pcan/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/dlz/PCAN/bdd100k/bdd100k/eval/run.py", line 319, in
run()
File "/home/dlz/PCAN/bdd100k/bdd100k/eval/run.py", line 292, in run
args.gt, args.result, bdd100k_config, args.nproc
File "/home/dlz/PCAN/bdd100k/bdd100k/eval/run.py", line 226, in _load_frames
gt_frames = bdd100k_to_scalabel(load(gt_base, nproc).frames, config)
File "/home/dlz/PCAN/scalabel/scalabel/label/io.py", line 90, in load
ret_cfg = process_file(inputs)
File "/home/dlz/PCAN/scalabel/scalabel/label/io.py", line 77, in process_file
raw_frames.extend(content["frames"])
KeyError: 'frames'

The real data I passed in is the seg_track_val_cocoformat.json file, and I found that the raw_frames and raw_cfg(config) parameters required by the code are not given in the file. Does the ground-truth JSON file need further processing?How to solve this problem? Thanks for your answer!

[lkeab]

Yes. It needs further data format conversion. Please refer to the instructions here on further data format conversion, where this script helps you converting result from coco to bdd format. Then, after conversion, please refer to this script on evaluating the final performance on validation set or directly submitting to the leader board.