Closed jiangzhengkai closed 3 years ago
code here might be helpful. During inference, image padding is applied on four sides, and a new affine matrix is calculated. Did you forget such an operation?
@FateScript code aims to generate affine matrix to map the regressed box results to image size. Because the regressed boxes downsample 4 according to code, thus we need to map regressed boxes to origin image size. I still can not figure out the reason why using image padding and why the performance drops when using cv2.warpAffine to resize the original image.
Did you retrain your model since you are using a different augmentation?
@FateScript @jiangzhengkai Hi~ I follow you guys for a very long time! It is very exciting to see you two battle~
However, I am a little confused about: Is there difference between image padding applied on four sides and only right bottom sides? Why does CenterNet apply image padding on four sides?
@PeizeSun Amazing to talk here with feng wang.
Did you retrain your model since you are using a different augmentation?
When training, CenterAffine is used to do augmentation, no padding. So, why do we need to retrain the model?
Did you retrain your model since you are using a different augmentation?
When training, CenterAffine is used to do augmentation, no padding. So, why do we need to retrain the model?
Since you are using a different aug which might bring difference between training and infernce.
got it!
Feng wang:
I tried to understand padding operations during inference but failed. You should give an explanation.
Following the original CenterNet implementation, replacing the padding with CenterAffine, mAP drops to 28% compared with original 34.4% performance!
You are expected to give the reason!