search

williamSYSU / TextGAN-PyTorch

TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.
MIT License
878 stars 207 forks source link

Where generated text is stored? #31

Open ghost opened 4 years ago

ghost commented 4 years ago

I checked files are being produced by the name of samples_MLE in sample folder but they consist of numbers. I guess they are the tokens of the individual word, if this is the case can you tell me how can I map these words back to words.

Neelisha-saxena commented 4 years ago

I checked files are being produced by the name of samples_MLE in sample folder but they consist of numbers. I guess they are the tokens of the individual word, if this is the case can you tell me how can I map these words back to words.

This is the case when you are working with oracle data. If you work with real data set this is not the case.

Mehdi-Sheikh commented 2 years ago

@Neelisha-saxena I have the same issue, I ran the seqgan like this: python3 run_seqgan.py 0 3 --if_real_data I added a text file in this path: dataset/oracle/oracle.txt but I still get some numbers ...