深度学习和Python自动学习

时间:2019-08-15 09:34:44

标签: python

SVM可以完美运行,但LSTM会显示错误,并且任何人也可以协助将代码添加到GRU中

def RandomEnviromentForActive(x_train, x_test,y_train):

   # Randomize a classifier
    Index = np.random.randint(1, 3)
    #print(Index)
    global IndexName
    # Choose to use the SVC classifier
    if Index == 1:
        IndexName = 'Classifiers are:SVC'
        svc_model = svm.SVC(kernel='rbf', C= 1)
        svc_model.fit(x_train, y_train)    
        pred_svc =  svc_model.predict(x_test)
        pred = pred_svc[0]

    #elif Index == 2:
        model = Sequential()
        #model.add(Embedding(max_features, output_dim=256))
        model.add(LSTM(128))
        #model.add(Dropout(0.5))
        model.add(Dense(1, activation='sigmoid'))
        model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])
        model.fit(x_train, y_train)    
        pred_LSTM =  model.predict(x_test)
        pred = pred_lstm[0]

    return pred

0 个答案:

没有答案