输入数据在哪?

[Perfeee]

你好,我想问一下,这源码的输入数据是哪一个数据集?又是何种形式输入的?可否分享一份与源码兼容的输入数据?

[EternalFeather]

@Perfeee The source code uses Oracle data generated from pretrain corpus-lstm model by providing Start_Token as the first token of each sentence. So it dosen't really need a corpus.

[yuyuqi]

I want to know how to use real-world data like Chinese quatrains as the input corpus in this model？