Dear organizers.
I got this error for my last submission today:
WARNING: Your kernel does not support swap limit capabilities or the cgroup is not mounted. Memory limited without swap.
Traceback (most recent call last):
File "/tmp/codalab/tmpT8f9iI/run/program/evaluate.py", line 80, in
cer = cal_cer(ref_text_arr, pred_text_arr)
File "/tmp/codalab/tmpT8f9iI/run/program/evaluate.py", line 49, in cal_cer
all_cer_arr.append(calculate_cer(ref, pred))
File "/tmp/codalab/tmpT8f9iI/run/program/evaluate.py", line 20, in calculate_cer
distance = levenshteinDistance(ref_text, pred_text)
File "/tmp/codalab/tmpT8f9iI/run/program/evaluate.py", line 28, in levenshteinDistance
if len(s1) > len(s2):
TypeError: object of type 'float' has no len()
It's hard for us to understand which format we should follow because the sample submission file is very simple and not realistic.
Please guide us more detail about this format and check your evaluation scripts.
Hi SDSV_AICR,
Please submit again. We recently updated the evaluation process to handle the issue.
Regards,
/The MC-OCR Team.
I met with this error when submit nan values of dataframe.
Posted by: litmitc @ Jan. 12, 2021, 2:22 a.m.