Why do you use only kernel_size=3?
jmjeon94 opened this issue · comments
An adaptive kernel_size is proposed with Eq. (9) in your paper.
But in your source code, all the kernel_size is not calculated by Eq.(9) but 3.
Is there any specific reason to use only 3?
The model we released is the same as in the paper, and the parameters in the code can be customized.
Thank you for your reply!
But in the eca_module.py, there isn't the implementation of Eq.(9) like 5, 6 lines in Figure 3.
Can you let me know which src the implementation belongs?
At present, most of the mainstream models are block-wise. Our method can calculate the corresponding kernel size very conveniently, so it can be predefined or adjusted appropriately without implementing it in code.
All right, I understand what you meant.
Thank you again!