Modefied from https://github.com/spro/char-rnn.pytorch
Run train.py with the dataset filename to train and save the network:
> python train.py ab.txt
Training for 2000 epochs...
(... 10 minutes later ...)
Saved as ab.pt
After training the model will be saved as [filename].pt.
Usage: train.py [filename] [options]
Options:
--model Whether to use LSTM or GRU units gru
--n_epochs Number of epochs to train 2000
--print_every Log learning rate at this interval 100
--hidden_size Hidden size of GRU 50
--n_layers Number of GRU layers 2
--learning_rate Learning rate 0.01
--chunk_len Length of training chunks 200
--batch_size Number of examples per batch 100
--cuda Use CUDA
Run generate.py with the saved model from training, and a "priming string" to start the text with.
> python generate.py norep7.pt --prime_str "a"
Usage: generate.py [filename] [options]
Options:
-p, --prime_str String to prime generation with
-l, --predict_len Length of prediction
-t, --temperature Temperature (higher is more chaotic)
--cuda Use CUDA
norep7.pt is the pretrained model
label*.txt are the generated samples which labeled with repetition