def build_basic_model(self):
# Encoder
encoder_inputs = Input(shape=(None, ), name='encoder_inputs')
encoder_embedding = Embedding(self.num_encoder_tokens,
200,
name='encoder_embedding')(encoder_inputs)
encoder_lstm = LSTM(self.latent_dim,
return_state=True,
name='encoder_lstm')
encoder_lstm.supports_masking = True
_, *encoder_states = encoder_lstm(encoder_embedding)
# Decoder
decoder_inputs = Input(shape=(None, ), name='decoder_inputs')
decoder_embedding = Embedding(self.num_decoder_tokens,
200,
name='decoder_embedding')(decoder_inputs)
decoder_lstm = LSTM(self.latent_dim,
return_state=True,
return_sequences=True,
name='decoder_lstm')
rnn_outputs, *decoder_states = decoder_lstm(
decoder_embedding, initial_state=encoder_states)
decoder_dense = Dense(self.num_decoder_tokens,
activation='softmax',
name='decoder_dense')
decoder_dense.supports_masking = True
decoder_outputs = decoder_dense(
Dropout(rate=0.4, name='dropout1')(rnn_outputs))
basic_model = Model([encoder_inputs, decoder_inputs],
[decoder_outputs])
basic_model.compile(optimizer='Adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
train_data, teach_data, train_data_y, test_data, test_teach_data, test_y = self.train_test_split(
self.encoder_input_data, self.teach_data, self.target_data)
basic_model.fit_generator(
self.generate_batch_data_random(train_data, teach_data,
train_data_y, self.BATCH_SIZE),
validation_data=self.generate_batch_data_random(
test_data, test_teach_data, test_y, self.BATCH_SIZE),
steps_per_epoch=train_data.shape[0] // self.BATCH_SIZE,
validation_steps=test_data.shape[0] // self.BATCH_SIZE,
epochs=10,
workers=5)
# # 回调函数
# callback_list = [callbacks.ModelCheckpoint('C:/Users/user/Desktop/chan-si/QA_Generate/web/chan-si_API_1/basic_model_best_V2.h', save_best_only=True)]
# # 训练
# basic_model_hist = basic_model.fit([self.encoder_input_data, self.decoder_input_data], self.decoder_target_data,
# batch_size=32, epochs=15,
# validation_split=0.2, callbacks=callback_list)
basic_model.save_weights("P1_old.h5")
def creat_model(self):
encoder_inputs = Input(shape=(None, ), name='encoder_inputs')
encoder_embedding = Embedding(self.num_encoder_tokens,
200,
name='encoder_embedding')(encoder_inputs)
encoder_lstm = LSTM(self.latent_dim,
return_state=True,
name='encoder_lstm')
encoder_lstm.supports_masking = True
_, *encoder_states = encoder_lstm(encoder_embedding)
# Decoder
decoder_inputs = Input(shape=(None, ), name='decoder_inputs')
decoder_embedding = Embedding(self.num_decoder_tokens,
200,
name='decoder_embedding')(decoder_inputs)
decoder_lstm = LSTM(self.latent_dim,
return_state=True,
return_sequences=True,
name='decoder_lstm')
rnn_outputs, *decoder_states = decoder_lstm(
decoder_embedding, initial_state=encoder_states)
decoder_dense = Dense(self.num_decoder_tokens,
activation='softmax',
name='decoder_dense')
decoder_dense.supports_masking = True
decoder_outputs = decoder_dense(
Dropout(rate=0.4, name='dropout1')(rnn_outputs))
basic_model = Model([encoder_inputs, decoder_inputs],
[decoder_outputs])
basic_model.compile(optimizer='Adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
for op in tf.get_default_graph().get_operations():
print(op.graph)
break
return basic_model
