How to get training accuracy in bidirectional LSTM?

Question

Hany Ferdinando ，2018-6-23

0
链接

Direct link to this question

https://ww2.mathworks.cn/matlabcentral/answers/407037-how-to-get-training-accuracy-in-bidirectional-lstm

回答： Prajit T R ，2018-6-26

Hi,

I used the bidirectional LSTM and I would like to save its training accuracy. According to trainingoptions, 'OutputFcn' is output functions to call during training, specified as the comma-separated pair consisting of 'OutputFcn' and a function handle or cell array of function handles. trainNetwork calls the specified functions once before the start of training, after each iteration, and once after training has finished. trainNetwork passes a structure containing information in certain fields. One of them is TrainingAccuracy. How can I accomplish my goal to save training accuracy of my trained network?

Thanks a lot

Hany

0 个评论
显示 -1更早的评论隐藏 -1更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Prajit T R 2018-6-26

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/407037-how-to-get-training-accuracy-in-bidirectional-lstm#answer_326293

Hi Hany

To save the training accuracy of the model you would have to write a custom output function and pass it to the parameter 'OutputFcn' as demonstrated in the following example:

https://www.mathworks.com/help/nnet/examples/customize-output-during-deep-learning-training.html

In your output function, you could obtain and store the training accuracy for each epoch by using info.TrainingAccuracy.

Hope this helps

Prajit