moving-on

I think the loss in the code id wrong, how can you explain about it?

2

self.cross_entropy_loss = tf.nn.softmax_cross_entropy_with_logits(logits=self.logprobs[:, -1, :], labels=self.states) Why you use softmax_cross_entropy_with_logits here， the first state is "[10.0, 128.0, 1.0, 1.0]*args.max_layers"，so does the labels. The final output of RNN contributes to the...

几个问题

1

你好，想问几个问题，训练语料每一行的第一列表示什么？比如_*23134。是每一个文档的语料作为一行吗？那相似文档的输出怎么是没有分过词的？