Cannot process data set - find log file

Task output: on ?

Sorry, never clicked that before lol.

Hey! I was just curious if this was an issue with my data? That's what's mentioned at the bottom of the log, but this wasn't captured any differently than other orthos i've done.

This could be a bug; ValueError: matmul: Input operand 1 has a mismatch in its core dimension 0, with gufunc signature (n?,k),(k,m?)->(n?,m?) (size 128 is different from 3) does it happen again if you restart?

yes, it gets less than 10s in before failing now.

with the same error or a different one? (is there a matmul: Input ... error in the log)?

here's the most recent attempt.

: matmul: Input operand 1 has a mismatch in its core dimension 0, with gufunc signature (n?,k),(k,m?)->(n?,m?) (size 128 is different from 3)

^ I'm around an hour into processing a 5k image ortho, it must just be something with my data set, or a glitch specific to that data set.

Mm, if you can isolate a subset of the images (20-40) that can trigger the issue reliably it would be interesting to take a look.

I guess I could split the ortho into thousands > hundreds > then tens of images till I find a pair that doesn’t work.

Hopefully future me understands what I meant by that

completed both halfs... i guess i'll try to reupload the full one.