def getData(projectname):
x_train, y_train = preprocess.get_xy_train(
projectname,
tokenizer=tokenizer,
mn_maxlen=MAX_SEQUENCE_LENGTH,
embedding_matrix=embedding_matrix)
x_test, y_test = preprocess.get_xy_test(projectname,
tokenizer=tokenizer,
maxlen=MAX_SEQUENCE_LENGTH,
embedding_matrix=embedding_matrix)
return x_train, y_train, x_test, y_test
W2V_MODEL_DIR = '/Users/knight/Desktop/GodClassDetection/embedding_model/new_model6_nltk.bin'
TRAIN_SET_DIR = '/Users/knight/Desktop/GodClassDetection/trainset' # 直接改成自己的路径
FULL_MN_DIR = TRAIN_SET_DIR
tokenizer = preprocess.get_tokenizer(FULL_MN_DIR)
all_word_index = tokenizer.word_index
embedding_matrix = preprocess.get_embedding_matrix(all_word_index,
W2V_MODEL_DIR,
dim=EMBEDDING_DIM)
acc_list = []
loss_list = []
print("11111111111111111")
x_train, y_train = preprocess.get_xy_train(TRAIN_SET_DIR + '/finetune',
tokenizer=tokenizer,
mn_maxlen=MAX_SEQUENCE_LENGTH,
embedding_matrix=embedding_matrix)
print('Fine tune model.')
# 微调
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['acc'])
hist = model.fit(x_train, y_train, nb_epoch=10, batch_size=5, verbose=1)
score = model.evaluate(x_train, y_train, verbose=0)
# 模型保存JSON文件
model_json = model.to_json()
with open(
r'/Users/knight/Desktop/GodClassDetection/trained_model/fine_tune_model.json',
'w') as file:
# with open(r'/Users/knight/Desktop/GodClassDetection-master-mao-new/trained_model/fine_tune_gru_model.json', 'w') as file: