def trainDemo(lang, dataSet, nlVocab, codeVocab, train_variables):
print("Training...")
encoder1 = EncoderRNN(codeVocab.n_words, setting.HIDDDEN_SIAZE)
attn_decoder1 = AttnDecoderRNN(setting.HIDDDEN_SIAZE,
nlVocab.n_words,
1,
dropout_p=0.1)
if setting.USE_CUDA:
encoder1 = encoder1.cuda()
attn_decoder1 = attn_decoder1.cuda()
trainIters(lang,
dataSet,
train_variables,
encoder1,
attn_decoder1,
2000000,
print_every=5000)
hidden_size = 256
encoder1 = EncoderRNN(input_lang.n_words, hidden_size)
attn_decoder1 = AttnDecoderRNN(hidden_size, output_lang.n_words, dropout_p=0.1)
TRAIN = False
if "-t" in sys.argv:
TRAIN = True
TRAIN_ITER = 7500
if len(sys.argv) == 3:
TRAIN_ITER = int(sys.argv[2])
if use_cuda:
encoder1 = encoder1.cuda()
attn_decoder1 = attn_decoder1.cuda()
if os.path.exists("encoder.pt") and os.path.exists("decoder.pt") and not TRAIN:
print("Found saved models")
encoder_state = torch.load('encoder.pt')
decoder_state = torch.load('decoder.pt')
encoder1.load_state_dict(encoder_state)
attn_decoder1.load_state_dict(decoder_state)
else:
trainIters(encoder1, attn_decoder1, TRAIN_ITER, print_every=50)
torch.save(encoder1.state_dict(), "encoder.pt")
torch.save(attn_decoder1.state_dict(), "decoder.pt")
######################################################################
#