You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Dear @louis-she,
Thank you for your nice work.
As Shifeng Zhang has mentioned in his paper: Our anchors are 1:1 aspect ratio (_i.e.,_ square anchor), the aspect ratios of all anchor boxes are 1:1. However, if one wants to change the aspect ratios of anchor boxes for example, to 1:1.4 (width:height) the network structure must be changed or just the training code & decoding strategy (i.e.,utils.py or anchor.py) must be changed? Would you please explain how one can change the aspect ratios of anchor boxes?
The text was updated successfully, but these errors were encountered:
Currently the aspect ratio of anchors is hard code to 1:1. But I already have plans to support other object detection(not only for "square" faces) so the aspect ratio of anchors will be necessary. Since then you will be able to change the aspect ratio of anchors. Thanks.
Dear @louis-she,
Thank you for your nice work.
As Shifeng Zhang has mentioned in his paper:
Our anchors are 1:1 aspect ratio (_i.e.,_ square anchor)
, the aspect ratios of all anchor boxes are 1:1. However, if one wants to change the aspect ratios of anchor boxes for example, to 1:1.4 (width:height) the network structure must be changed or just the training code & decoding strategy (i.e.,utils.py
oranchor.py
) must be changed? Would you please explain how one can change the aspect ratios of anchor boxes?The text was updated successfully, but these errors were encountered: