Open GeorgePearse opened 1 year ago
Hi, did you find a workaround for this issue?
Nope, spent a while trying to tweak different parts of the architecture but just hit other problems.
Will continue to try whenever I have a bit of spare time.
Bump
Excuse me. Have you solved the problem yet?
No I've not, tried a variety of sizes for different parts of the model. Couldn't work out the bottleneck, very curious to find out the resolution.
Try to set keep_ratio
as False
in train_pipeline
in config file.
Hi @pd162 that's not much of a fix for me, because I definitely do want to keep the same ratio (and all of the transforms I'm trying would do so anyway).
@GeorgePearse did you find the solution? Encountering the same issue now
Can't really remember.
But for anything you try, make sure the dimensions are divisable by 32.
They have a padding operation specifically for that.
Describe the bug
Receive this error for any image size above 1024 (e.g. 1025) but none below.
Looks like all of the model range are designed for 640x640 so I'm not sure what I could change in the neck to allow for larger images.