MATLAB Answers

LSTM padding and masking

40 ビュー (過去 30 日間)
Ao Du
Ao Du 2020 年 12 月 10 日
コメント済み: Yildirim Kocoglu 2021 年 1 月 16 日
I am solving a sequence-to-sequence classification problem based on LSTM using Matlab 2020b. The sequences have varaible length so padding within each minibatch is needed. However, I am not sure if Matlab automatically do the masking when calculating the crossentroy loss as well as the training/validation accuracy. From the training plot, the reported accuracy (around 70%) is much lower than those manually calculated by using checkpoints (where I get around 90% accuracy). I suspect although Matlab 2020b supports sequence padding and validation data in LSTM, it still did not offer the option of masking to reduce the influence caused by padding. Any insights?

  0 件のコメント


回答 (1 件)

Aditya Patil
Aditya Patil 2020 年 12 月 22 日
Currently, masking is not supported in MATLAB. I have brought the request to the notice of concerned people.
As a workaround, you can sort the inputs so that the amount of padding required is minimized. You may also set the minibatch size to 1, so that no padding is required.

  1 件のコメント

Yildirim Kocoglu
Yildirim Kocoglu 2021 年 1 月 16 日
Thank you! I was really curious about this as well since it can be done in python. I really hope they can add this feature.


Community Treasure Hunt

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

Start Hunting!

Translated by