How can I retrain a model, for example an Isolation Forest (or another used for anomaly detection), it gives the error Function 'iforest' not supported for code generation.
What I intend to do is generate a static library in C and train the model after I collect some Normal data, I intend for the train to be done through the library generated by codegen.
I have already looked at the documentation and it is also not possible with the following algorithms aswell:
  • one-class support vector machine
  • Robust Random Cut Forest
I was also looking at incremental learning:
  • incrementalRobustRandomCutForest
  • incrementalOneClassSVM
and it is also not possible to use the codegen.
Does anyone have any suggestions on how this could be done?

 採用された回答

Walter Roberson
Walter Roberson 2023 年 10 月 6 日

1 投票

You will need to write your own training code. As a general rule, MATLAB Coder does not support code generation for training most models (across most toolboxes)

1 件のコメント

Hélio Pereira
Hélio Pereira 2023 年 10 月 6 日
Ok. Thanks for the answer.

サインインしてコメントする。

その他の回答 (0 件)

カテゴリ

ヘルプ センター および File Exchange で Deep Learning Toolbox についてさらに検索

製品

リリース

R2023a

Community Treasure Hunt

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

Start Hunting!

Translated by