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)
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 = None
self.set_data_loader(gen_loader=gen_dataloader,
dis_loader=dis_dataloader,
oracle_loader=oracle_dataloader)
def init_oracle_trainng(self, oracle=None):
goal_out_size = sum(self.num_filters)
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)
discriminator = Discriminator(sequence_length=self.sequence_length, num_classes=2, vocab_size=self.vocab_size,
dis_emb_dim=self.dis_embedding_dim, filter_sizes=self.filter_size,
num_filters=self.num_filters,
batch_size=self.batch_size, hidden_dim=self.hidden_dim,
start_token=self.start_token,
goal_out_size=goal_out_size, step_size=4,
l2_reg_lambda=self.l2_reg_lambda)
self.set_discriminator(discriminator)
generator = Generator(num_classes=2, num_vocabulary=self.vocab_size, batch_size=self.batch_size,
emb_dim=self.emb_dim, dis_emb_dim=self.dis_embedding_dim, goal_size=self.goal_size,
hidden_dim=self.hidden_dim, sequence_length=self.sequence_length,
filter_sizes=self.filter_size, start_token=self.start_token,
num_filters=self.num_filters, goal_out_size=goal_out_size, D_model=discriminator,
step_size=4)
self.set_generator(generator)
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)
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
config.gpu_options.per_process_gpu_memory_fraction = 0.5
self.sess = tf.compat.v1.Session(config=config)
self.set_data_loader(gen_loader=gen_dataloader, dis_loader=dis_dataloader, oracle_loader=oracle_dataloader)
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)
g_embeddings = tf.Variable(
tf.random_normal(shape=[self.vocab_size, self.emb_dim],
stddev=0.1))
discriminator = Discriminator(sequence_length=self.sequence_length,
num_classes=2,
emd_dim=self.emb_dim,
filter_sizes=self.filter_size,
num_filters=self.num_filters,
g_embeddings=g_embeddings,
l2_reg_lambda=self.l2_reg_lambda)
self.set_discriminator(discriminator)
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,
g_embeddings=g_embeddings,
discriminator=discriminator,
start_token=self.start_token)
self.set_generator(generator)
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_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)
discriminator = Discriminator(sequence_length=self.sequence_length,
num_classes=2,
vocab_size=self.vocab_size,
hidden_unit=20,
embedding_size=self.emb_dim,
filter_sizes=self.filter_size,
batch_size=self.batch_size,
num_filters=self.num_filters,
non_static=True,
l2_reg_lambda=self.l2_reg_lambda)
self.set_discriminator(discriminator)
generator = Generator(num_vocabulary=self.vocab_size,
batch_size=self.batch_size,
sess=self.sess,
hidden_dim=self.hidden_dim,
sequence_length=self.sequence_length,
discriminator=discriminator,
start_token=self.start_token)
self.set_generator(generator)
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_oracle_trainng(self, oracle=None):
# oracle, generator都是这里规定的
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)
# 继承GAN
# data pipe在这里处理！！！！！！！！！！！！！！
self.set_data_loader(gen_loader=gen_dataloader,
dis_loader=dis_dataloader,
oracle_loader=oracle_dataloader)
