update state in dlnetworks

4 次查看（过去 30 天）
sepid_kl
sepid_kl 2020-12-13
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?

请先登录，再回答此问题。

回答（1 个）

Katja Mogalle
Katja Mogalle 2021-7-1
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
Tao
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。

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 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