textgenrnn
textgenrnn copied to clipboard
minimaxir
Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.
Hi, When I train my models, I randomly get the following key error. Any idea what might be causing the problem? Traceback (most recent call last): File "train.py", line 39,...
I'm really new to all of these. I'm trying to train it with Chinese text, but I got an error. The txt file can be open in local with no...
https://github.com/keras-team/keras/releases/tag/2.3.0 ``` Change default recurrent activation to sigmoid (from hard_sigmoid) in all RNN layers. ``` This _shouldn't_ affect textgenrnn because I was accidentally ahead of the curve and made the...
I just install the textgenrnn by conda https://anaconda.org/RMG/textgenrnn and I follow the document ``` from textgenrnn import textgenrnn textgen = textgenrnn() textgen.generate() ``` And it gives me an error ```OSError:...
mycode: from textgenrnn import textgenrnn textgen = textgenrnn() textgen.train_from_file('hacker-news- 2000.txt ',num_epochs = 1) textgen.generate() textgen.save('trainedRnn.hdf5') error:ValueError: Layer #1 (named "embedding"), weight has shape (209, 100), but the saved weight has...
There is an issue about application in Chinese that said it could be applied to Chinese. But I got nothing (only English words or punctuation mark) with following code. I...
I've been doing a grid search on most of the hyperparameters provided, and have reduced my loss to 0.529. My dataset is 2.9 MB (roughly 102,000 lines of text). I...
is there any functionality to save the model file at every k epochs? the reason is; when i train after a certain point the model overfits, so i want to...
Hi, My dataset is in Thai language. I tokenize words with ' ' and train successfully. But when the model generate sentences, it appeared to be just only white spaces...
