Info

この質問は閉じられています。 編集または回答するには再度開いてください。

trainNetwork - protect centain layers from changing

1 回表示 (過去 30 日間)
Samuel Ubrezi
Samuel Ubrezi 2019 年 1 月 26 日
閉鎖済み: MATLAB Answer Bot 2021 年 8 月 20 日
Hi,
I am trying to do train a neural net with my own layers but I dont want to change weights and biases in certain layers.
algorithm looks like this:
train Net1 with Layers1
train Net2 with Layers = [Layers2 Layers1]
My problem is that I dont want to anyhow alter weights and biases in Layers1, is there any way to do this?

回答 (1 件)

BERGHOUT Tarek
BERGHOUT Tarek 2019 年 2 月 4 日
yes there is a pssibility take this codes and change the training lope, when you find ''for i=1: nember of layes '' change it to for " i=2:nember of layes ", good luck.

Community Treasure Hunt

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

Start Hunting!

Translated by