search

zhongkaifu / RNNSharp

RNNSharp is a toolkit of deep recurrent neural network which is widely used for many different kinds of tasks, such as sequence labeling, sequence-to-sequence and so on. It's written by C# language and based on .NET framework 4.6 or above versions. RNNSharp supports many different types of networks, such as forward and bi-directional network, sequence-to-sequence network, and different types of layers, such as LSTM, Softmax, sampled Softmax and others.
BSD 3-Clause "New" or "Revised" License
285 stars 91 forks source link

Need Help With PRETRAIN_TYPE=Autoencoder #30

Closed bill3code closed 7 years ago

bill3code commented 7 years ago

Hello! You wrote: "You need to train an auto encoder-decoder model by RNNSharp at first, and then use this pretrained model for your task"

But I do not see how to do it. Finaly what do you mean by "pretrained model is trained by RNNSharp itself"?

zhongkaifu commented 7 years ago

Hi @bill3code ,

The previous description may nit clearly, so I updated it to:

#For 'Autoencoder', the pretrained model is trained by RNNSharp itself. For sequence-to-sequence task, "Autoencoder" is required, since source sequence needs to be encoded by this model at first, and then target sequence would be generated by decoder.  

So, it means that you need to run RNNSharp to build autoencoder model at first, and then use it as one of input to build decoder model for your sequence-to-sequence task.

bill3code commented 7 years ago

Thank you!