Use trainNetwork funcion to train a feedforwad net

1 次查看（过去 30 天）
Raphael Ruschel
Raphael Ruschel 2018-5-7
评论： Raphael Ruschel 2019-9-6
Does the trainNetwork function can only be used to train CNNs and LSTMs as written in the documentation or can I use it to train a feedforwad net as well?
My idea was to create the ImageInputLayer the size of my feature vector and then use a couple of fullyConnectedLayers followed by RELULayers and dropoutLayers. The reason to want to use this intead of the regular feedforwardnet and train functions are the possibilities to use ReLU and dropout, more flexibility to choose the training parameters, and the usage of the ImageDatastore structure.
Will this method give me similar results to when feedforward and train are used or the way the trainNetwork function is implemented is not recommended for feedforward-only training?

请先登录，再回答此问题。

回答（1 个）

Saeed Mohammadi
Saeed Mohammadi 2019-9-4
Hi,
I think this is a very interesting question. Can someone comment on this?
Thanks.
  1 个评论
Raphael Ruschel
Raphael Ruschel 2019-9-6
I tried using it as described on the question and it achieved good results, so I think it is not a problem!

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by