所以我尝试训练Keras模型。在训练和验证时有很高的准确度（我使用f1score，但准确度也很高）。但当我尝试预测一些数据集时，我得到的准确度较低。即使我预测训练集。所以我猜这不是过度拟合问题。那么问题是什么？

import matplotlib.pyplot as plt

skf = StratifiedKFold(n_splits=5)
for train_index, test_index in skf.split(X, y):
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index]
    X_train,x_val,y_train,y_val = train_test_split(X_train, y_train, test_size=0.5,stratify = y_train)
    y_train = encode(y_train)
    y_val = encode(y_val)
    
    model = Sequential()
    model.add(Dense(50,input_dim=X_train.shape[1],activation='tanh'))
    model.add(Dropout(0.5))
    model.add(Dense(25,activation='tanh'))
    model.add(Dropout(0.5))
    model.add(Dense(10,activation='tanh'))
    model.add(Dropout(0.5))
    model.add(Dense(2, activation='softmax'))   
    
    opt = Adam(learning_rate=0.001)
    model.compile(loss='binary_crossentropy', optimizer=opt, metrics=['acc', ta.utils.metrics.f1score])  
    history = model.fit(X_train, y_train, 
                        validation_data=(x_val, y_val),
                        epochs=5000,
                        verbose=0)
    
    plt.plot(history.history['f1score'])
    plt.plot(history.history['val_f1score'])
    plt.title('model accuracy')
    plt.ylabel('f1score')
    plt.xlabel('epoch')
    plt.legend(['train', 'test'], loc='upper left')
    plt.show()
    break

结果是here。如您所见，结果在训练集和验证集中较高。
和预测代码：

from sklearn.metrics import f1_score

y_pred = model.predict(x_train)
y_pred = decode(y_pred)
y_train_t = decode(y_train)
print(f1_score(y_train_t, y_pred))

结果为0.64，低于预期的0.9。
我的解码和编码：

def encode(y):
    Y=np.zeros((y.shape[0],2))
    for i in range(len(y)):
        if y[i]==1:
            Y[i][1]=1
        else :
            Y[i][0]=1
    return Y

def decode(y):
    Y=np.zeros((y.shape[0]))
    for i in range(len(y)):
        if np.argmax(y[i])==1:
            Y[i]=1
        else :
            Y[i]=0
    return Y