feed-forward layer指的是 a linear layer or a single-layer MLP
说白了就是一个fc层
出自牛津《Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet》
版权声明:本文为hxxjxw原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。
feed-forward layer指的是 a linear layer or a single-layer MLP
说白了就是一个fc层
出自牛津《Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet》