-
Notifications
You must be signed in to change notification settings - Fork 2.6k
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
Computing confidence mask #22
Comments
I found the part you are refering to in the commit history but I am not sure why this filtering was removed. Can you explain @eriklindernoren ? |
I guess because it was redundant / wrong. The mask is computed as: |
This should be fixed in 959e0ff. Before this commit the confidence mask was computed as in YOLOv2. With the latest commit the confidence mask is set as in version 3, i.e. where the anchor has an overlap with a target box larger than 0.5 but is not the anchor with the largest overlap the confidence prediction is ignored during training. |
In
build_targets
function, at the beginning, there's a part that calculates the confidence mask tensor.Initially it is set to a tensor of ones, but the update rule:
doesn't make sense to me. This basically ignores any ious better than
ignore_thres
(currently set to0.5
).I'd think that:
conf_mask[b][cur_ious.view_as(conf_mask[b]) > thres] = 1
conf_mask[b][cur_ious.view_as(conf_mask[b]) <= thres] = 0
Thanks
The text was updated successfully, but these errors were encountered: