代码之家 › 专栏 › 技术社区 › user1111

Keras模型LSTM预测2个特征

prediction lstm keras tensorflow python

user1111 · 技术社区 · 6 年前

定义模型

def my_model():
    input_x = Input(batch_shape=(batch_size, look_back, x_train.shape[2]), name='input')
    drop = Dropout(0.5)

    lstm_1 = LSTM(100, return_sequences=True, batch_input_shape=(batch_size, look_back, x_train.shape[2]), name='3dLSTM', stateful=True)(input_x)
    lstm_1_drop = drop(lstm_1)
    lstm_2 = LSTM(100, batch_input_shape=(batch_size, look_back, x_train.shape[2]), name='2dLSTM', stateful=True)(lstm_1_drop)
    lstm_2_drop = drop(lstm_2)

    y1 = Dense(1, activation='relu', name='op1')(lstm_2_drop)
    y2 = Dense(1, activation='relu', name='op2')(lstm_2_drop)

    model = Model(inputs=input_x, outputs=[y1,y2])
    optimizer = Adam(lr=0.001, decay=0.00001)
    model.compile(loss='mse', optimizer=optimizer,metrics=['mse'])
    model.summary()
    return model

model = my_model()

for j in range(50):
    start = time.time()
    history = model.fit(x_train, [y_11_train,y_22_train], epochs=1, batch_size=batch_size, verbose=0, shuffle=False)
    model.reset_states()
    print("Epoch",j, time.time()-start,"s")

p = model.predict(x_test, batch_size=batch_size)

x_train (31251, 6, 9)
y_11_train (31251,)
y_22_train (31251,)
x_test (13399, 6, 9)
y_11_test (13399,)
y_22_test (13399,)

我想预测第一个( y_11 y_22 )我的数据集的功能。但我得到的预测只是第一个特征,而不是第二个特征。

有什么能帮我得到两个预测而不是一个?

1 回复 | 直到 6 年前

Ioannis Nasios 6 年前

首先,您应该删除同一事物的多个输入:

(批次大小,向后看,x)_列车形状[2])

此外,请尝试将输出连接到模型中,如下所示:

def my_model():
    from keras.layers import concatenate

    lstm_1 = LSTM(100, return_sequences=True, batch_input_shape=(batch_size, look_back, x_train.shape[2]), name='3dLSTM', stateful=True)
    lstm_1_drop = drop(lstm_1)
    lstm_2 = LSTM(100, name='2dLSTM', stateful=True)(lstm_1_drop)
    lstm_2_drop = drop(lstm_2)

    y1 = Dense(1, activation='linear', name='op1')(lstm_2_drop)
    y2 = Dense(1, activation='linear', name='op2')(lstm_2_drop)

    y= concatenate([y1,y2])

    model = Model(inputs=input_x, outputs=y)
    optimizer = Adam(lr=0.001, decay=0.00001)
    model.compile(loss='mse', optimizer=optimizer,metrics=['mse'])
    model.summary()
    return model

编辑

y_11_train = y_11_train.reshape(y_11_train.shape[0],1)
y_22_train = y_22_train.reshape(y_22_train.shape[0],1)
model = my_model()
model.fit(x_train,np.concatenate((y_11_train,y_22_train),axis=1),...)

推荐文章

CoccoSyn · Keras TypeError:其中一个输入没有可接受的类型。具有参差不齐张量的LSTM

2 年前

cventr · 用于异常检测的递归神经网络

6 年前

Asif Shahriyar Sushmit · tensorflow是否允许LSTM反褶积(convlstm2d),就像它允许2D卷积一样?

6 年前

Aaditya Ura · Tensorflow LSTM:值错误:形状的等级必须至少为3

6 年前

harmegiddo · 如何在Keras中使用卷积LSTM实现位置估计?

6 年前

Roma Jain · 为包含可变长度序列的数组的输出标签创建分类numpy数组[已关闭]

6 年前

user5458635 · 多输出LSTM时间序列预测

6 年前

Manthan mahes wari · 如何将2D pandas阵列适配到Keras LSTM层?

6 年前

Funzo · 如何配置Keras中双向LSTM的输入形状

6 年前

sww · Pytorch隐藏状态LSTM

6 年前