multi_seq=True)
print("construct data...finish")
print('test_question_seq.shape: ' + str(dm.data['test_question'].shape))
print('test_option.shape: ' + str(dm.data['test_option'].shape))
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
'''''' '''''' '''''' ''' loading model '''
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
model = load_model(continue_file)
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
'''''' '''''' '''''' ''' print model '''
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
model.summary()
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
'''''' '''''' '''''' ''' decoder '''
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
data_in = dm.wrape_encoder(dm.data['test_question'], voc)
print(data_in.shape)
test_model = dm.construct_seq2seq_test(model, 1024)
data_out = []
#for i in range(len(data_in)):
for i in range(6):
print('\rdecoding... sequence: ' + str(i), end='')
data_out.append(
dm.decode_seq(data_in[i].reshape((1, 14, 300)), test_model, voc))
data_out = np.array(data_out)
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
'''''' '''''' '''''' ''' writing output '''
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
'''
'''
output = dm.output(data_out)
'''
'''
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
'''''' '''''' '''''' ''' print model '''
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
model.summary()
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
'''''' '''''' '''''' ''' fit model '''
'''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''''''
encoder_data = np.concatenate(
(dm.data['train1'][:-1], dm.data['train2'][:-1], dm.data['train3'][:-1],
dm.data['train4'][:-1], dm.data['train5'][:-1]))
decoder_data = np.concatenate(
(dm.data['train1'][1:], dm.data['train2'][1:], dm.data['train3'][1:],
dm.data['train4'][1:], dm.data['train5'][1:]))
encoder_input_data = dm.wrape_encoder(encoder_data, voc)
decoder_input_data = dm.wrape_decoder(decoder_data, voc, decode_in=True)
decoder_target_data = dm.wrape_decoder(decoder_data, voc, decode_in=False)
print('encoder_input_data.shape: ', encoder_input_data.shape)
print('decoder_input_data.shape: ', decoder_input_data.shape)
print('decoder_target_data.shape: ', decoder_target_data.shape)
model.fit([encoder_input_data, decoder_input_data],
decoder_target_data,
batch_size=n_batch,
epochs=n_epoch,
validation_split=0.1,
shuffle=True,
callbacks=callbacks_list,
verbose=1)
'''
'''