if tf.reduce_sum(y_hat, 1) == self.token2idx["<pad>"]: break

[gaoxuezhao]

I don't understand the conditional sentence in the loop when infer, it is always false。

if tf.reduce_sum(y_hat, 1) == self.token2idx[""]: break

[ZhichaoOuyang]

Yes, I have this question too.

[tracyfly]

+1

[BetterZH]

+1

[GuoshenLi]

you are right. the author is wrong. I also think the following "decoder_inputs = tf.concat((decoder_inputs, y_hat), 1)" is wrong. cuz what we need to concat is not the total y_hat but the last time step of y_hat. so y_hat[:,-1]