update state in dlnetworks

Question

sepid_kl 2020-12-13

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/692780-update-state-in-dlnetworks

评论： Tao 2023-2-23

hi

in Train Network Using Custom Training Loop , in training part, state was updated(dlnet.State = state).

i want to train a siamese network, and i saw in matlab example for siamese net , state dosn't update.

so my question is that why we dont update state in second network?

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

Katja Mogalle 2021-7-1

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/692780-update-state-in-dlnetworks#answer_737688

Great question, and good observation. I think it would be best practise to indeed also update the state for the siamese network.

However, the specific network used in the documentation example doesn't contain any layers with state. So the whole network doesn't have any state that needs any updating.

If the network had, for example, batchNormalization layers, then the state would need to be update as shown here: https://www.mathworks.com/help/deeplearning/ug/update-batch-normalization-statistics-in-custom-training-loop.html

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Tao 2023-2-23

I also have a question. Refer to GAN (https://ww2.mathworks.cn/help/deeplearning/ug/train-generative-adversarial-network.html?s_tid=srchtitle_network%20state_8), the netG also has batchNormlization Layers. But the code only output netD.State and does not update netG.State.

So, if the network used in ModelGradient function is "forwarded" more than 1 time. Which "forward" function should output "state"?

请先登录，再进行评论。