DeepVO-pytorch
DeepVO-pytorch copied to clipboard
Execution error
Thanks a lot for your work, I'm learning this implementation. But the following error occurs during execution, I don't know why, can you help me? thanks
ValueError: Caught ValueError in DataLoader worker process 0. groundtruth_rotation = raw_groundtruth[1][0].reshape((3, 3)).T # opposite rotation of the first frame ValueError: cannot reshape array of size 0 into shape (3,3)
@Jinbo-Zuo @ChiWeiHsiao
ValueError: Caught ValueError in DataLoader worker process 0. groundtruth_rotation = raw_groundtruth[1][0].reshape((3, 3)).T # opposite rotation of the first frame ValueError: cannot reshape array of size 0 into shape (3,3)
Did you manage to find a solution for this? I am facing the exact same issue. For me the error happens while reshaping the raw_groundtruth
File "/data_helper.py", line 201, in getitem groundtruth_rotation = raw_groundtruth[1][0].reshape((3, 3)).T # opposite rotation of the first frame ValueError: cannot reshape array of size 0 into shape (3,3)
@itz-Anonym Did you manage to find a solution for this? I am facing the exact same issue. For me the error happens while reshaping the raw_groundtruth.
@hiXiaoYU
@itz-Anonym Did you manage to find a solution for this? I am facing the exact same issue. For me the error happens while reshaping the raw_groundtruth.
If you are still stuck, delete the two .pickle files in 'datainfo' folder. If it still doesn't run, go to params.py and set resume=False For some reason, the datainfo provided by the author causes errors in loading.
I did what you said but I still get the error
@itz-Anonym
I did what you said but I still get the error
@itz-Anonym Have you solved it?I met this problem,too.I guess it's a mismatch between the images and the ground truth,cause I print the paramater"train_df",there are some poses being empty,but I don't know how to solve it.
I am also experiencing the same problem, how should I solve it?