LSTM 3D输入3D输出尺寸不匹配

时间:2019-06-18 13:36:33

标签: keras

我在Keras中有一个简单的LSTM网络:

def create_model(x):
    lstm_model = Sequential()
    lstm_model.add(LSTM(100, input_dim=x.shape[2], input_length=x.shape[1]))
    lstm_model.add(Dense(1,activation='sigmoid'))
    lstm_model.compile(loss='mean_squared_error', optimizer='adam')
    return lstm_model

我正在尝试对具有以下形状的数据进行训练:

  

训练数据输入:(100,2784,6),训练数据输出:(100,2784,1)
  验证数据输入:(50,27,6),验证数据输出:(50,27,1)
  测试数据输入:(50,27,6),测试数据输出:(50,27,1)

model.fit(train_x, train_y, validation_data=(validation_x, validation_y), epochs=EPOCHS, batch_size=BATCH_SIZE, shuffle=False, callbacks=[...])

我继续在尺寸上失败,或者是因为a)验证数据与训练数据的形状不同,或者b)因为y形状不正确

我在做什么错了?

P.S。方便的独立代码

import numpy as np
import keras
from keras.models import Sequential
from keras.layers import LSTM, Dense

x_train=np.arange(1670400)
x_train=x_train.reshape((100, 2784, 6))
y_train=np.arange(278400)
y_train=y_train.reshape((100, 2784, 1))

x_val=np.arange(8100)
x_val=x_val.reshape((50, 27, 6))
y_val=np.arange(1350)
y_val=y_val.reshape((50, 27, 1))

x_test=np.arange(8100)
x_test=x_test.reshape((50, 27, 6))
y_test=np.arange(1350)
y_test=y_test.reshape((50, 27, 1))


def create_model(x):
    lstm_model = Sequential()
    lstm_model.add(LSTM(100, input_dim=x.shape[2], input_length=x.shape[1]))
    lstm_model.add(Dense(1,activation='sigmoid'))
    lstm_model.compile(loss='mean_squared_error', optimizer='adam')
    return lstm_model

model=create_model(x_train)
model.fit(x_train, y_train, validation_data=(x_val, y_val), epochs=10, batch_size=32, shuffle=False)

1 个答案:

答案 0 :(得分:0)

此修改有效:
更改为 batch_input_shape ,并在LSTM层中添加 return_sequences = True

import numpy as np
import keras
from keras.models import Sequential
from keras.layers import LSTM, Dense

x_train=np.arange(1670400)
x_train=x_train.reshape((100, 2784, 6))
y_train=np.arange(278400)
y_train=y_train.reshape((100, 2784, 1))

x_val=np.arange(8100)
x_val=x_val.reshape((50, 27, 6))
y_val=np.arange(1350)
y_val=y_val.reshape((50, 27, 1))

x_test=np.arange(8100)
x_test=x_test.reshape((50, 27, 6))
y_test=np.arange(1350)
y_test=y_test.reshape((50, 27, 1))

def create_model():
    lstm_model = Sequential()
    lstm_model.add(LSTM(100, batch_input_shape=(None,None,6), return_sequences=True))
    lstm_model.add(Dense(1, activation='sigmoid'))
    lstm_model.compile(loss='mean_squared_error', optimizer='adam')
    return lstm_model

model=create_model()
model.fit(x_train, y_train, validation_data=(x_val, y_val), epochs=10, batch_size=32, shuffle=False)