Closed CYXYZ closed 6 months ago
I've found that when I use parameterizations = ["quaternion"], other errors occur, as follows:
(diffpose_copy) (base) cyx@server1:~/autodl-tmp/DiffPose_copy/experiments/deepfluoro$ python register.py
main
ckpt se3_log_map
0%| | 0/111 [00:00<?, ?it/s]convention None
0%| | 0/111 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/home/data/cyx/autodl-tmp/DiffPose_copy/experiments/deepfluoro/register.py", line 325, in <module>
main(id_number, parameterization=parameterization)
File "/home/data/cyx/autodl-tmp/DiffPose_copy/experiments/deepfluoro/register.py", line 290, in main
df = registration.run(idx)
^^^^^^^^^^^^^^^^^^^^^
File "/home/data/cyx/autodl-tmp/DiffPose_copy/experiments/deepfluoro/register.py", line 143, in run
param, geo, tre = self.evaluate(registration)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/data/cyx/autodl-tmp/DiffPose_copy/experiments/deepfluoro/register.py", line 109, in evaluate
est_pose = registration.get_current_pose()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/data/cyx/miniconda3/envs/diffpose_copy/lib/python3.12/site-packages/diffpose/registration.py", line 248, in get_current_pose
return convert(self.rotation,
^^^^^^^^^^^^^^^^^^^^^^
File "/home/data/cyx/miniconda3/envs/diffpose_copy/lib/python3.12/site-packages/diffdrr/pose.py", line 148, in convert
return convert(matrix, parameterization="matrix")
^^^^^^
UnboundLocalError: cannot access local variable 'matrix' where it is not associated with a value
Hi @CYXYZ sorry for the slow response on this. I am working on a big update to DiffDRR (you can track it here), and am waiting to update DiffPose until this is completed. Thank you for your patience.
Dear Vivek,
I hope this email finds you well. I am writing to address an issue I encountered while working with the register.py file in both the main and refactor-se3 branches of our project.
Specifically, I noticed that when I attempt to input the parameterization "euler_angles," an error occurs, as follows:
This issue seems to persist regardless of the branch I am working in(main and refactor-se3). Upon further investigation, I realized that the code snippet provided below is likely the cause of the error:
Moreover, I am considering using alternative parameterizations in the train.py file. Would it be necessary to modify the function signature in train.py, particularly the parameterization argument, to accommodate these changes? For instance, should I change parameterization="se3_log_map" to parameterization="euler_angles" ?
Could you kindly provide guidance on how to resolve the aforementioned issue? I would greatly appreciate your assistance in this matter.
Thank you for your attention to this matter.
Best regards,