Hello everyone,
I have a short question about the onehot encoding.
From my understanding, every character is onehot encoded and the resulting tensor is fed for training.
My question is, when you retrieve the prediction from the generator, can you confirm that you use argmax to find the index of the character that the generator was intending to produce ?
Thank you very much
Hello everyone,
I have a short question about the onehot encoding.
From my understanding, every character is onehot encoded and the resulting tensor is fed for training.
My question is, when you retrieve the prediction from the generator, can you confirm that you use argmax to find the index of the character that the generator was intending to produce ?
Thank you very much