custom loss function for DNN training

63 次查看（过去 30 天）
Pratheek
Pratheek 2019-5-16
回答： Dinial Utami Nurul Qomariah 2020-1-27
how can i write a custom loss fucntion for DNN training. I want to try reconstruction loss

请先登录，再回答此问题。

回答（2 个）

Shounak Mitra
Shounak Mitra 2019-5-17
You can create custom layers and define custom loss functions for output layers.
The output layer uses two functions to compute the loss and the derivatives: forwardLoss and backwardLoss. The forwardLoss function computes the loss L. The backwardLoss function computes the derivatives of the loss with respect to the predictions.
Refer https://www.mathworks.com/help/deeplearning/ug/define-custom-deep-learning-layers.html
For eg., to write a weighted cross entropy classification loss, try running this in the MATLAB command window
>> edit(fullfile(matlabroot,'examples','deeplearning_shared','main','weightedClassificationLayer.m'))
Hope this helps
Dinial Utami Nurul Qomariah

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

产品


版本

R2019a

Community Treasure Hunt

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

Start Hunting!

Translated by