RNN_Text_Generation_Tensorflow
RNN_Text_Generation_Tensorflow copied to clipboard
spiglerg
Need help
Hi. It's me again :)
K, i used command $ python rnn_tf.py and some hours ago it was finished. And what should i do now? Should i use command $ python rnn_tf.py saved/model.ckpt "The " to generate my text? Will it generate a new file at "saved" directory ? How can i find text file? Or mb i need to use another prefix? I didn't understand it yet :( Can u explain me a little, please?
Thx a lot and sorry for giving u some work :)
Did you see the output of the program at the end of training (it should output the first example of generated text).
If you use the command with saved/model.ckpt, it will use the trained model to generate new text. The trained model is saved automatically in that folder after you run the program in training mode. :)
Yeah. I saw, thx :) But there's one more question: if i want to use another textfile to train with another language, should i delete model.ckpt or delete some other files. Or all files (language, characters for new language) will be rewrite and work correctly?
Well, model.ckpt will get overwritten with the new training anyway. Just replace the line of code where the text file is loaded with your own text file. :)
Okay. If i'll try to set something like 50000 batches - will it be too much or everything will be ok? :)
And what about using 2 or more texts to train the model? For example: There's a writer and soon he'll die (holly shit!), but he want to train this programm to continue his job. He wants to train this programm over 100+ texts for learning his "writing style".
Can we do something like that?
Just concatenate the text files / copy all their contents in the same file / modify the code to load all the text files you want and concatenate them in the same string used for training. ;)