Difference between trainnet and trainNetwork

Question

Isaiah 2023-12-13

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2060029-difference-between-trainnet-and-trainnetwork

评论： Onur Kilic 2024-3-12

Hi, I am creating a deep neural network for a regression problem with tabular data as the inputs (6 features and 1 target).

I was wondering if there is any difference between the trainnet and trainNetwork functions? They seem to be quite similar so I am unsure of the pros and cons to using either function?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Ben Hinkle 2023-12-13

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2060029-difference-between-trainnet-and-trainnetwork#answer_1371029

编辑：Ben Hinkle 2023-12-13

Here are some of the differences between the two trainers:

trainnet accepts a loss function input, which makes it easier to customize the loss if the standard regression loss is not enough.
trainnet lets you track additional metrics while training.
trainnet supports the LBFGS solver, which can converge quickly for small problems
trainnet outputs a dlnetwork, while trainNetwork outputs a SeriesNetwork or DAGNetwork.
trainNetwork accepts a table as input, while trainnet does not. This might make trainNetwork slightly easier to use when training data is in a table.

3 个评论
显示 1更早的评论隐藏 1更早的评论

Cris LaPierre 2023-12-15

编辑：Cris LaPierre 2023-12-16

trainnet was introduced in R2023b. You must be using at least R2023b to access it.

Onur Kilic 2024-3-12

Thank you, this is useful information. Should we expect performance improvements for trainnet in the near future? Currently, when training larger models, trainnet is much slower than trainNetwork and also gives 'out of memory' errors (GPU training) for model or minibatch sizes that trainNetwork would handle without issues.

请先登录，再进行评论。