search

open-mmlab / mmocr

OpenMMLab Text Detection, Recognition and Understanding Toolbox
https://mmocr.readthedocs.io/en/dev-1.x/
Apache License 2.0
4.32k stars 747 forks source link

fcenet的head部分和论文的不一致 #880

Closed ocrhei closed 2 years ago

ocrhei commented 2 years ago

为啥代码head中的每一部分只有一个3✖️3卷积呢，而论文说的是3个

Mountchicken commented 2 years ago

In the original paper, there are indeed three 3x3 convolution layers in each head. However, according to the author of FCENet, using one 3x3 convolution layer in each head makes no difference and the accuracy are almost the same. So we just use one here.

ocrhei commented 2 years ago

谢谢您，回复非常及时