-
Notifications
You must be signed in to change notification settings - Fork 93
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Confidence Maps Offset #1611
Labels
bug
Something isn't working
Comments
Right, I think we add padding to the image to avoid truncation when downsampling --> upsampling, but not to the confidence maps, which might result in weird aspect ratio issues? Relevant plotting code: Lines 81 to 96 in 16241e0
Called from here during training (for single instance -- other model types plot a bit differently): Lines 1068 to 1122 in 16241e0
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Discussed in #1608
Originally posted by daskandalis November 25, 2023
I've often observed that the validation confidence maps are highly offset. Is this just a display issue? It's highly directional and the green (MAP?) estimate lies outside the confidence bound.
I'm wondering though if it's related to this printout:
The width is 1088 but I think it should be 1080, the resolution of the image (unless the convolution kernels are padded in width but not height?).
Incidentally, is it possible to access the variance of the estimated position from the outputs? The measurement error would be useful in filtering.
Model parameters:
"unet": {
"stem_stride": null,
"max_stride": 64,
"output_stride": 4,
"filters": 32,
"filters_rate": 1.5,
"middle_block": true,
"up_interpolate": true,
"stacks": 1
}
EDIT: or maybe comes from translation in the augmentation step?
This looks to be a visualization issue. The red predicted points should be centered on the peak value of the green 2D Gaussian (which depicts confidence values at pixel locations). While it seems that the red predicted and green ground truth points are correctly overlaid on the image, the confidence maps (from which the predicted points are derived from) are not being correctly displayed. We must be missing some offset for the visualization of the confidence maps.
Thanks for reporting this! - I'll convert this discussion to an issue.
Liezl
The text was updated successfully, but these errors were encountered: