Derek-Gong
Results
2
comments of
Derek-Gong
That's true. But this is not about synchronization. I would also like to keep the LR schedule the same no matter how many GPUs I use. For now, If I...
@farizrahman4u In docs/readout.md: for cell in cells: lstms_output, h, c = cell([lstms_output, h, c]) which means h and c passed to next layer, but isn't c an internal state? why...