def __init__(self):
self.config = TCNNConfig()
self.categories, self.cat_to_id = read_category()
self.words, self.word_to_id = read_vocab(vocab_dir)
self.config.vocab_size = len(self.words)
self.model = TextCNN(self.config)
self.session = tf.Session()
self.session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=self.session, save_path=save_path) # 读取保存的模型
print(
metrics.classification_report(y_test_cls,
y_pred_cls,
target_names=categories))
# 混淆矩阵
print('Confusion Matrix...')
cm = metrics.confusion_matrix(y_test_cls, y_pred_cls)
print(cm)
time_dif = get_time_dif(start_time)
print('Time usage:', time_dif)
if __name__ == '__main__':
# if len(sys.argv) != 2 or sys.argv[1] not in ['train','test']:
# raise ValueError('usage:python run_rnn.py [train / test]')
print('Configuring RNN model...')
config = TRNNConfig()
if not os.path.exists(vocab_dir):
build_vocab(train_dir, vocab_dir, config.vocab_size)
categories, cat_to_id = read_category()
words, word_to_id = read_vocab(vocab_dir)
config.vocab_size = len(words)
model = TextRNN(config)
if sys.argv[1] == 'train':
train()
else:
test()
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
if __name__ == '__main__':
if len(sys.argv) != 2 or sys.argv[1] not in ['train', 'test']:
raise ValueError("""usage: python run_cnn.py [train / test]""")
print('Configuring CNN model...')
config = TCNNConfig()
if not os.path.exists(vocab_dir_c): # 如果不存在字表，重建
data_loader.build_vocab(train_dir, vocab_dir_c, config.vocab_size_c)
if not os.path.exists(vocab_dir_w): # 如果不存在词汇表，重建
data_loader_wordlevel.build_vocab(train_dir, vocab_dir_w,
config.vocab_size_w)
categories, cat_to_id = data_loader.read_category()
characters, character_to_id = data_loader.read_vocab(vocab_dir_c)
words, word_to_id = data_loader_wordlevel.read_vocab(vocab_dir_w)
config.vocab_size_c = len(characters)
config.vocab_size_w = len(words)
# max_train = data_loader.get_maxlength(train_dir)
# max_val = data_loader.get_maxlength(val_dir)
# # 用所有集合中最大的序列长度
# temp_val = max(max_train, max_val)
# # 如果有的集合中序列长度超过了1014，就还是用1014吧
# print("最长长度： %i" % temp_val)
# # config.seq_length = min(temp_val, 1500)
config.seq_length_c = 1500
config.seq_length_w = 800
# config.seq_length_c = 1014
# config.seq_length_w = 1014