12910 texture patches.
Running global seam leveling:
Create matrices for optimization…
done.
Lhs dimensionality: 220076 x 220076
Calculating adjustments:
Color channel 0: CG took 119 iterations. Residual is 8.8939e-05
Color channel 2: CG took 116 iterations. Residual is 9.93064e-05
Color channel 1: CG took 119 iterations. Residual is 8.9781e-05
Took 0.997 seconds
Adjusting texture patches 100%… done. (Took 11.519s)
Running local seam leveling:
Blending texture patches 100%… done. (Took 175.265s)
Generating texture atlases:
Sorting texture patches…
done.
Killed
===== Dumping Info for Geeks (developers need this to fix bugs) =====
Child returned 137
===== Done, human-readable information to follow… =====
[ERROR] Whoops! You ran out of memory! Add more RAM to your computer, if you’re using docker configure it to use more memory, for WSL2 make use of .wslconfig (Advanced settings configuration in WSL | Microsoft Learn), resize your images, lower the quality settings or process the images using a cloud provider (e.g. https://webodm.net).
Traceback (most recent call last):
File “/code/stages/odm_app.py”, line 83, in execute
self.first_stage.run()
File “/code/opendm/types.py”, line 338, in run
self.next_stage.run(outputs)
File “/code/opendm/types.py”, line 338, in run
self.next_stage.run(outputs)
File “/code/opendm/types.py”, line 338, in run
self.next_stage.run(outputs)
[Previous line repeated 4 more times]
File “/code/opendm/types.py”, line 319, in run
self.process(self.args, outputs)
File “/code/stages/mvstex.py”, line 108, in process
system.run('“{bin}” “{nvm_file}” “{model}” “{out_dir}” ’
File “/code/opendm/system.py”, line 90, in run
raise SubprocessException(“Child returned {}”.format(retcode), retcode)
opendm.system.SubprocessException: Child returned 137
100 - done.
It does indeed seem like it’s running out of memory (which is strange, we allocate plenty of memory for processing ~200 images). Is there something different/unique about this dataset? Is the GCP formatted correctly?
I would try to remove some GCPs (you have 10 of them). Perhaps leave P7, P1 and P5. This will reduce the possibility of mistags. If it works, add 2 more for additional accuracy. There’s probably little benefit in having 10 GCPs (for such a small area, too).
