FengLi-ust
commented
1 year ago Because we use sigmoid to normalize the boxes. However, operations to the box should be before sigmoid. So we use inverse sigmoid to transfer the anchor.
Closed zkyseu closed 1 year ago
FengLi-ust
commented
1 year ago Because we use sigmoid to normalize the boxes. However, operations to the box should be before sigmoid. So we use inverse sigmoid to transfer the anchor.
Hi, I have a question that what the role of “Inverse Sigmoid” is in your code? I mention that Inverse sigmoid is used in many places in your code