Convert Classification Network into Regression Network

2 ビュー (過去 30 日間)
GEORGIOS
GEORGIOS 2024 年 12 月 11 日
編集済み: Cris LaPierre 2024 年 12 月 12 日
I 'm trying to build a regression ResNet 18 model. In previous versions there was lots of output layers. How can i find these layers now ?

採用された回答

Cris LaPierre
Cris LaPierre 2024 年 12 月 12 日
編集済み: Cris LaPierre 2024 年 12 月 12 日
In R2024a, machine learning models were transitioned to dlnetwork. Rather than assign the output, they now output the prediction scores.
So you would still use Deep Network Desigher to build your network. You would then use trainnet with the targets set to 'mse', and minibatchpredict to obtain the predictions from your network.
You can learn more about how to implement regression in R2024b on the regressionLayer doc page.

その他の回答 (0 件)

カテゴリ

Help Center および File ExchangeImage Data Workflows についてさらに検索

Community Treasure Hunt

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

Start Hunting!

Translated by