r3det-on-mmdetection
r3det-on-mmdetection copied to clipboard
IndexError: list index out of range
when I run "sh rtools/train.sh",I meet the error. How I can do to solve the problem?
2020-10-17 10:25:11,392 - mmdet - INFO - Saving checkpoint at 1 epochs
completed: 0, elapsed: 0sTraceback (most recent call last):
File "tools/train.py", line 161, in
Have you solved this problem?
Hi,@why228430 I also encountered this problem. Have you solved your problem?
I also encountered this problem. And I have checked the class num repeatedly. Have you solved your problem?
same problem, i met this when just finishing the first epoch
same problem, i met this when just finishing the first epoch
I met the same problem before. Now, I have already fixed it.
Error: num_classes = len(det_results[0]) # positive class num
My problem is due to the det_results is an empty list, because the test.txt is empty. After training the first epoch, there are no data to validate. So it returns the error: list index out of range. I hope it could help those who encounter the same problem.
In my ieda,it's maybe the error of dataset
same problem, i met this when just finishing the first epoch
I met the same problem before. Now, I have already fixed it.
Error: num_classes = len(det_results[0]) # positive class num
My problem is due to the det_results is an empty list, because the test.txt is empty. After training the first epoch, there are no data to validate. So it returns the error: list index out of range. I hope it could help those who encounter the same problem.
Sorry, I don't quite understand this error. If I want to fix this error, do I need to add the relevant files?