我试过测试一个模型，但是遇到了一个错误。下面是我的代码
Train1 = train1.astype('float32')
test1 = test1.astype('float32')
train1 /= 255.0
test1 /= 255.0
Xtrain = np.concatenate([train1, test1])
X_train, X_test= train_test_split(Xtrain,test_size=0.3)
print(test1)
model = Sequential()
model.add(LSTM(units =100, activation='relu', return_sequences=True, input_shape = (1,X_train.shape[1])))
model.add(Dropout(0.5))
model.add(LSTM(units =50, activation='relu', return_sequences=True))
model.add(Dropout(0.5))
model.add(Dense(units=1, activation='sigmoid')) # Prediction of the next value
model.compile(loss='mse', optimizer='adam', metrics=['accuracy'])
history = model.fit(X_train, X_test, epochs=10, batch_size=200, verbose=1)`我错了：
Data cardinality is ambiguous:
x sizes: 23608
y sizes: 10119
Make sure all arrays contain the same number of samples.
X_train = (26,23608)
X_test = (26,10119)我需要以适当的方式准备我的训练和测试数据集。有什么建议吗？
1条答案
按热度按时间szqfcxe21#
model.fit()将x，y作为前两个参数，同时传递x_train和x_test（大小不同）。x和y的大小应该相同，因为第i个x引用第i个y。通常
train_test_split用作X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.3)然后可以训练模型：
history = model.fit(X_train, y_train, epochs=10, batch_size=200, verbose=1)最后，您可以使用evaluate来评估模型性能：
model.evaluate(X_test, y_test)我建议您阅读有关这些主题的Keras和Sklearn文档。