def main(_):
model_path = os.path.join('models', Config.file_name)
input_file = 'data/去除2和null.xlsx'
vocab_file = os.path.join(model_path, 'vocab_label.pkl')
# 数据处理
converter = TextConverter(None,
vocab_file,
max_vocab=Config.vocab_max_size,
seq_length=Config.seq_length)
print('vocab size:', converter.vocab_size)
# 加载上一次保存的模型
model = Model(Config, converter.vocab_size)
checkpoint_path = tf.train.latest_checkpoint(model_path)
if checkpoint_path:
model.load(checkpoint_path)
# 获取测试库数据
# test_libs = get_excel_libs('data/tianlong_libs.xlsx') # 用整个库3w+
QAs = get_excel_QAs(input_file)
thres = int(0.8 * len(QAs))
test_QAs = QAs[thres:]
test_libs = [r for q, r, y in test_QAs] # 用QAs
test_libs_arrs = converter.libs_to_arrs(test_libs)
# 产生匹配库向量
save_file = checkpoint_path + '_matul_state_QAs.pkl'
if os.path.exists(save_file) is False:
response_matul_state = model.test_to_matul(test_libs_arrs)
with open(save_file, 'wb') as f:
pickle.dump(response_matul_state, f)
else:
with open(save_file, 'rb') as f:
response_matul_state = pickle.load(f)
# 测试
print('start to testing...')
QAY = []
k, n = 0, 0
for query, y_response, label in test_QAs:
input_arr, input_len = converter.text_to_arr(query)
indexs = model.test(input_arr, input_len, response_matul_state)
responses = converter.index_to_response(indexs, test_libs)
QAY.append((query, y_response, responses))
if responses[0] == y_response:
k += 1
print(k, '/', n)
n += 1
print('accuracy:', k / float(n))
result_xls = checkpoint_path + '_Q_for_QAs.xls'
converter.save_to_excel(QAY, result_xls)
def main(_):
# FLAGS.start_string = FLAGS.start_string#.decode('utf-8')
converter = TextConverter(filename=FLAGS.converter_path)
if os.path.isdir(FLAGS.checkpoint_path):
FLAGS.checkpoint_path =\
tf.train.latest_checkpoint(FLAGS.checkpoint_path)
model = DualLSTM(converter.vocab_size,
test=True,
batch_size=FLAGS.num_seqs,
num_steps=FLAGS.num_steps,
lstm_size=FLAGS.lstm_size,
num_layers=FLAGS.num_layers,
use_embedding=FLAGS.use_embedding,
embedding_size=FLAGS.embedding_size)
model.load(FLAGS.checkpoint_path)
# # ----------test3-------------
# QAs = get_excel_QAs(FLAGS.input_file) # 要求excel文件格式，第一个表，第一列id，第二列query,第三列response
# QA_arrs = converter.QAs_to_arrs(QAs, FLAGS.num_steps)
# all_samples = converter.samples_for_test3(QA_arrs)
# indexs = model.test3(all_samples)
# converter.index_to_QA_and_save(indexs,QAs,FLAGS.checkpoint_path)
# ----------test4-------------
libs = get_excel_libs('data/tianlong_libs.xlsx')
libs_arrs = converter.libs_to_arrs(libs, FLAGS.num_steps)
response_matul_state = model.test4_matul(libs_arrs)
QAs = get_excel_QAs(
FLAGS.input_file) # 要求excel文件格式，第一个表，第一列id，第二列query,第三列response
QAY = []
k, n = 0, 0
for query, y_response in QAs:
input_arr, input_len = converter.Q_to_arr(query, FLAGS.num_steps)
indexs = model.test4(input_arr, input_len, response_matul_state)
responses = converter.index_to_response(indexs, libs)
# print('response:',responses)
QAY.append((query, y_response, responses))
if responses[0] == y_response:
k += 1
# print(k)
n += 1
print('accuracy:', k / float(n))
converter.save_to_excel(QAY, FLAGS.checkpoint_path)
