Open LiwangChen opened 4 days ago
Hi, Thanks for your interest in this work. The released code actually not include this additional scale layer. However, you can also implement this layer for better performance.
OK!Thanks for your reply!
------------------ 原始邮件 ------------------ 发件人: "csguoh/AdaptIR" @.>; 发送时间: 2024年11月15日(星期五) 晚上8:24 @.>; @.**@.>; 主题: Re: [csguoh/AdaptIR] about Frequency Affine Module (Issue #2)
Hi, Thanks for your interest in this work. The released code actually not include this additional scale layer. However, you can also implement this layer for better performance.
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
Hello!The paper says 'another depth-separable 1 × 1 convolution is used as a scale layer for subsequent feature ensemble', but I did not find it in the code