iuria
iuria
Hi, thanks for the repo, it's fantastic! No issues but some questions for you: I tried to train the Transformer with the whole dataset, but the loss is getting stuck...
Hello, first thanks for your work. I trained the model with the same data as you, and I got similar results in the training (except the time):  But then...
Any idea of how could I train it with multi-gpu? thanks!
Hello, Could you explain why do you define a loss function (cost) instead of using a pre-defined one in TFLearn? Thanks!