def init_cfg_training(self, grammar=None):
oracle = OracleCfg(sequence_length=self.sequence_length,
cfg_grammar=grammar)
self.set_oracle(oracle)
self.oracle.generate_oracle()
self.vocab_size = self.oracle.vocab_size + 1
generator = Generator(num_vocabulary=self.vocab_size,
batch_size=self.batch_size,
emb_dim=self.emb_dim,
hidden_dim=self.hidden_dim,
sequence_length=self.sequence_length,
start_token=self.start_token)
self.set_generator(generator)
discriminator = Discriminator(sequence_length=self.sequence_length,
num_classes=2,
vocab_size=self.vocab_size,
emd_dim=self.emb_dim,
filter_sizes=self.filter_size,
num_filters=self.num_filters,
l2_reg_lambda=self.l2_reg_lambda)
self.set_discriminator(discriminator)
gen_dataloader = DataLoader(batch_size=self.batch_size,
seq_length=self.sequence_length)
oracle_dataloader = DataLoader(batch_size=self.batch_size,
seq_length=self.sequence_length)
dis_dataloader = DisDataloader(batch_size=self.batch_size,
seq_length=self.sequence_length)
self.set_data_loader(gen_loader=gen_dataloader,
dis_loader=dis_dataloader,
oracle_loader=oracle_dataloader)
return oracle.wi_dict, oracle.iw_dict
def init_real_trainng(self, data_loc=None):
from utils.text_process import text_precess, text_to_code
from utils.text_process import get_tokenlized, get_word_list, get_dict
if data_loc is None:
data_loc = 'data/image_coco.txt'
self.sequence_length, self.vocab_size = text_precess(data_loc)
generator = Generator(num_vocabulary=self.vocab_size,
batch_size=self.batch_size,
emb_dim=self.emb_dim,
hidden_dim=self.hidden_dim,
sequence_length=self.sequence_length,
start_token=self.start_token)
self.set_generator(generator)
discriminator = Discriminator(sequence_length=self.sequence_length,
num_classes=2,
vocab_size=self.vocab_size,
emd_dim=self.emb_dim,
filter_sizes=self.filter_size,
num_filters=self.num_filters,
l2_reg_lambda=self.l2_reg_lambda)
self.set_discriminator(discriminator)
# 创建dataloader
gen_dataloader = DataLoader(batch_size=self.batch_size,
seq_length=self.sequence_length)
# 这时真实文本就使用现实中的文本
oracle_dataloader = None
dis_dataloader = DisDataloader(batch_size=self.batch_size,
seq_length=self.sequence_length)
# data pipe工作在这里完成！！！！！！！！！11
self.set_data_loader(gen_loader=gen_dataloader,
dis_loader=dis_dataloader,
oracle_loader=oracle_dataloader)
tokens = get_tokenlized(data_loc)
word_set = get_word_list(tokens)
[word_index_dict, index_word_dict] = get_dict(word_set)
with open(self.oracle_file, 'w') as outfile:
# 这里把oracle_file给编码了
outfile.write(
text_to_code(tokens, word_index_dict, self.sequence_length))
return word_index_dict, index_word_dict
def init_oracle_trainng(self, oracle=None):
if oracle is None:
oracle = OracleLstm(num_vocabulary=self.vocab_size, batch_size=self.batch_size, emb_dim=self.emb_dim,
hidden_dim=self.hidden_dim, sequence_length=self.sequence_length,
start_token=self.start_token)
self.set_oracle(oracle)
generator = Generator(num_vocabulary=self.vocab_size, batch_size=self.batch_size, emb_dim=self.emb_dim,
hidden_dim=self.hidden_dim, sequence_length=self.sequence_length,
start_token=self.start_token)
self.set_generator(generator)
discriminator = Discriminator(sequence_length=self.sequence_length, num_classes=2, vocab_size=self.vocab_size,
emd_dim=self.emb_dim, filter_sizes=self.filter_size, num_filters=self.num_filters,
l2_reg_lambda=self.l2_reg_lambda)
self.set_discriminator(discriminator)
gen_dataloader = DataLoader(batch_size=self.batch_size, seq_length=self.sequence_length)
oracle_dataloader = DataLoader(batch_size=self.batch_size, seq_length=self.sequence_length)
dis_dataloader = DisDataloader(batch_size=self.batch_size, seq_length=self.sequence_length)
self.set_data_loader(gen_loader=gen_dataloader, dis_loader=dis_dataloader, oracle_loader=oracle_dataloader)
def init_real_trainng(self, data_loc=None):
from utils.text_process import text_precess, text_to_code
from utils.text_process import get_tokenlized, get_word_list, get_dict
if data_loc is None:
data_loc = 'data/image_coco.txt'
self.sequence_length, self.vocab_size = text_precess(data_loc)
generator = Generator(num_vocabulary=self.vocab_size,
batch_size=self.batch_size,
emb_dim=self.emb_dim,
hidden_dim=self.hidden_dim,
sequence_length=self.sequence_length,
start_token=self.start_token)
self.set_generator(generator)
discriminator = Discriminator(sequence_length=self.sequence_length,
num_classes=2,
vocab_size=self.vocab_size,
emd_dim=self.emb_dim,
filter_sizes=self.filter_size,
num_filters=self.num_filters,
l2_reg_lambda=self.l2_reg_lambda,
splited_steps=self.splited_steps)
self.set_discriminator(discriminator)
gen_dataloader = DataLoader(batch_size=self.batch_size,
seq_length=self.sequence_length)
oracle_dataloader = None
dis_dataloader = DisDataloader(batch_size=self.batch_size,
seq_length=self.sequence_length)
self.set_data_loader(gen_loader=gen_dataloader,
dis_loader=dis_dataloader,
oracle_loader=oracle_dataloader)
tokens = get_tokenlized(data_loc)
with open(self.oracle_file, 'w') as outfile:
outfile.write(
text_to_code(tokens, self.wi_dict, self.sequence_length))
