the error appears in defining weightedAdditionLayer

1 次查看（过去 30 天）
li
li 2019-6-20
回答： Gabija Marsalkaite 2019-7-2
hi, i have defined the weightedAdditionLayer according to the code provided in the help document, but a error'Incorrect number of input arguments for 'backward' in Layer weightedAdditionLayer. Expected to have 5, but instead it has 2.' appears, why?

请先登录，再回答此问题。

回答（1 个）

Gabija Marsalkaite
Assuming you have a layer with two inputs (input1 and input2) and one output, 'backward' expects layer, input1, input2, output, dLdz, memory, but if any of them is not used, it can be replaced with ~ e.g. backward(~, ~,~,~,dLdz,~).
This documentation page may help you: https://www.mathworks.com/help/deeplearning/ug/define-custom-deep-learning-layers.html
If that does not solve your problem, could you share your code?

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by