How to change the default loss function from "crossentropyex" to "crossentropy" using the pixelClassificationLayer in MATLAB?

7 次查看（过去 30 天）
Gobert
Gobert 2023-7-13
编辑： Malay Agarwal 2023-7-13
Hi,
The properties of the pixelClassificationLayer include the LossFunction "crossentropyex" by default. When I attempted to change it as shown below:
SegLayer = pixelClassificationLayer('LossFunction', 'crossentropy');
I encountered the following error:
Error using nnet.cnn.layer.PixelClassificationLayer.parseInputs 'LossFunction' is not a recognized parameter.
Could you please demonstrate how to modify the default loss function? I am using the Unet model for semantic segmentation, and I want to switch from "crossentropyex" to "crossentropy" because the former is only suitable for mutually exclusive scenarios.
Thank you!

请先登录，再回答此问题。

采纳的回答

Malay Agarwal
Malay Agarwal 2023-7-13
编辑：Malay Agarwal 2023-7-13
Hi @Gobert,
Unfortunately, the LossFunction property of the pixelClassificationLayer is read-only and cannot be changed. What you can do instead is create a custom pixel classification layer, as demonstrated here: Define Custom Pixel Classification Layer with Tversky Loss - MATLAB & Simulink - MathWorks India. The example demonstrates how to use the Tversky loss but it shouldn't be too difficult to adapt the example to use the crossentropy loss. Please make sure you use functions supported by dlarray to make use of automatic differentiation.

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Get Started with MATLAB 的更多信息

标签

产品


版本

R2023a

Community Treasure Hunt

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

Start Hunting!

Translated by