Closed OYsJcHar closed 2 years ago
Thx for the interest. As formulated in equ 7 in the paper of EIoU, EIoU loss = DIoU loss + aspect loss. So you should generalize it in a similar way for DIoU (or CIoU), with examples available in equ 4 in our paper. We should add the power parameter alpha for each term in the equ. Thx.
Thx for the interest. As formulated in equ 7 in the paper of EIoU, EIoU loss = DIoU loss + aspect loss. So you should generalize it in a similar way for DIoU (or CIoU), with examples available in equ 4 in our paper. We should add the power parameter alpha for each term in the equ. Thx.
Thank you very much for your quick reply! According to what you said, I read the formula in the paper again. I think the the part of EIoU in the code provided by CSDN blog above is the method you said, so it should be correct in theory. However, the effect on the dataset I use is not as good as the CIoU combined with alpha-IoU provided by your code. I think it may be the problem of the dataset I use that makes the results different. In the future, I will see the effect through training with other dataset. Thank you again for your reply!
Hi, I have applied alpha IOU to yolov5, but I also applied EIOU to the algorithm. It seems that the function in your file named "general.py" code does not contain EIOU. Would you like to know how to modify the code if you want to add it? The following is the code written by a blogger I saw on CSDN, but when I train the model, the effect is not as good as the alpha IOU or eiou provided by you. The training effect is reduced by combining these two items. I think it may be a code problem, (Maybe it is the problem of dataset that I used.) so I want to ask you how you can combine eiou and alpha IOU?
Hope to get your reply as soon as possible. Thank you so much!!!