matlab trainNetwork mini-batch size

Question

tony gian 2018-10-17

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/424466-matlab-trainnetwork-mini-batch-size

评论： tony gian 2018-10-26

I am using a LSTM neural network(trainNetwork function) for a 2 time series input and a 30 time series output. When i change the minibatch size, in the output window during training the iteration number is constant and equal to the epoch number, whatever the minibatch size. Is the minibatch size really changing or just being equaly to the number of timesteps? I input my data as matrices, with rows corresponding to different outputs/inputs and columns corresponding to timesteps. Thank you in advance

0 个评论
显示 -2更早的评论隐藏 -2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

Viren Gupta 2018-10-26

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/424466-matlab-trainnetwork-mini-batch-size#answer_343509

If I understand correctly, you expect the 'miniBatchSize' to create the batches along the time dimension. But this is not what 'miniBatchSize' does. 'MiniBatchSize' creates batches in the observation dimension, not the time dimension. To create batches in the time dimension, you can use the 'SequenceLength' parameter.The default 'SequenceLength' parameter is ‘longest’, which means that the batch sequence length is determined by the longest sequence in the batch.