Batch size? about flowtron HOT 5 OPEN

Yes! It's worth trying and can lead to lower validation losses.
Let us know what your findings are.

from flowtron.

Yes! It's worth trying and can lead to lower validation losses.
Let us know what your findings are.

Is there any prior guidance for setting batch_size to 1?
I found that for my data, batch_size can be set to 16.

from flowtron.

@IsakWesterlundBitville Thanks for your comment, I tried your suggestion to compare training with batch size 4 against default batch size 1 when using 2 GPUs. However, when I use batch size 4, I just get the the diagonal line of the alignment till a much smaller decoder time step compared with the alignment obtained with batch size 1. Please could you tell if you changed any other config settings to take into account the change in batch size.

from flowtron.

@IsakWesterlundBitville Thanks for your comment, I tried your suggestion to compare training with batch size 4 against default batch size 1 when using 2 GPUs. However, when I use batch size 4, I just get the the diagonal line of the alignment till a much smaller decoder time step compared with the alignment obtained with batch size 1. Please could you tell if you changed any other config settings to take into account the change in batch size.

@rafaelvalle Do you have any idea why I get this difference in the alignment plots?

from flowtron.

The two samples are different, hence the alignment plots are different.

from flowtron.