OOD-CV Challenge 2022 (Classification Track) Forum

Go back to competition Back to thread list Post in this thread

> ValueError: Can only compare identically-labeled Series objects

Hi, when I summit the results, I get the following error:

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/tmp6E8gqX/run/program/main.py", line 54, in
main()
File "/tmp/codalab/tmp6E8gqX/run/program/main.py", line 27, in main
iid_acc = (iid_gt['labels'] == iid_pred['pred']).sum() / len(iid_gt['labels'])
File "/usr/local/lib/python3.6/dist-packages/pandas/core/ops/common.py", line 65, in new_method
return method(self, other)
File "/usr/local/lib/python3.6/dist-packages/pandas/core/ops/__init__.py", line 365, in wrapper
raise ValueError("Can only compare identically-labeled Series objects")
ValueError: Can only compare identically-labeled Series objects

Posted by: TerminusAI @ Sept. 18, 2022, 4:03 p.m.

Hi,

Please ensure that your submitted csv files have the same number of lines as the ground truth file, and also the same order as in the ground truth annotation file, note there are some duplications in the gt file which will be corrected in the final phase.
The gt file can be accessed here: https://github.com/eccv22-ood-workshop/ROBIN-dataset/blob/master/evaluation/cls_ref/ref/iid_test/labels.csv

Posted by: ROBIN @ Sept. 18, 2022, 4:16 p.m.

Thank you for your quick reply! I have solved the problem.

Posted by: TerminusAI @ Sept. 19, 2022, 8:16 a.m.
Post in this thread