train_step = rvae.trainer(optimizer)
# validate = rvae.validater()
ce_result = []
kld_result = []
# training_data = batch_loader.training_data('train')
# validation_data = batch_loader.training_data('valid')
for iteration in range(args.num_iterations):
print(f"-----Iteration: {iteration}-------------")
x = 0
bar = progressbar.ProgressBar(maxval=130001,
widgets=[progressbar.Bar('=', '[', ']'), ' ', progressbar.Percentage()])
bar.start()
while True:
input = batch_loader.next_batch(x, args.batch_size, "train")
bar.update(x + 1)
if input is None:
break
cross_entropy, kld, coef = train_step(iteration, input, args.use_cuda, args.dropout)
x += args.batch_size
if x == 64:
seed = np.random.normal(size=[1, parameters.latent_variable_size])
sentence, reference, result = rvae.predict(input, batch_loader, 50, seed, args.use_cuda)
print('\n')
print('------------SAMPLE------------')
print('------------------------------')
print(f'original: {sentence.encode("utf-8")}')
print(f'reference: {reference.encode("utf-8")}')
print(f'generated: {result.encode("utf-8")}')
rvae = RVAE(parameters, parameters_2)
rvae.load_state_dict(t.load('trained_RVAE'))
if args.use_cuda:
rvae = rvae.cuda()
n_best = 3
beam_size = 10
assert n_best <= beam_size
for i in range(args.num_sentence):
'''================================================== Input Encoder-1 ========================================================
'''
use_cuda = 1
input = batch_loader.next_batch(1, 'valid', i)
input = [Variable(t.from_numpy(var)) for var in input]
input = [var.long() for var in input]
input = [var.cuda() if use_cuda else var for var in input]
[
encoder_word_input, encoder_character_input, decoder_word_input,
decoder_character_input, target
] = input
''' =================================================== Input for Encoder-2 ========================================================
'''
input_2 = batch_loader_2.next_batch(1, 'valid', i)
input_2 = [Variable(t.from_numpy(var)) for var in input_2]
input_2 = [var.long() for var in input_2]
input_2 = [var.cuda() if use_cuda else var for var in input_2]
batch_loader_2.max_seq_len,
batch_loader_2.words_vocab_size,
batch_loader_2.chars_vocab_size)
'''=================================================================================================
'''
embedding = Embedding(parameters, path)
embedding_2 = Embedding(parameters_2, path, True)
vae, bigdecoder, docoder4 = VAE.create_lstm_vae_1()
start_index = 0
for iteration in range(args.num_iterations):
if True:
#This needs to be changed ##这一步必须保证不大于训练数据数量-每一批数据的大小，否则越界报错######################
start_index = (start_index + 1) % (49999 - args.batch_size)
#start_index = (start_index+args.batch_size)%149163 #计算交叉熵损失，等
#=================================================== Input for Encoder-1,3 ========================================================
input = batch_loader.next_batch(args.batch_size, 'train',
start_index)
input = [Variable(t.from_numpy(var)) for var in input]
input = [var.long() for var in input]
#input = [var.cuda() if args.use_cuda else var for var in input]
#这里是data/train.txt,转换变成embedding，用pand补齐，
#其中encoder_word_input, encoder_character_input是将 xo原始句输入倒过来前面加若干占位符，
# decoder_word_input, decoder_character_input是 xo原始句加了开始符号末端补齐
# target，结束句子后面加了结束符，target是xo原始句加结束符后面加若干占位符
[
encoder_word_input, encoder_character_input,
decoder_word_input, decoder_character_input, target
] = input
# =================================================== Input for Encoder-1,3 ========================================================
''' =================================================== Input for Encoder-2 ========================================================
'''
input_2 = batch_loader_2.next_batch(args.batch_size, 'train',