了解将密集层连接到LSTM

问题描述

我无法正确地将密集层连接到LSTM层.我的Y值范围是0-1，所以S形对我来说似乎是合乎逻辑的.

I am unable to correctly connect my dense layer to my LSTM layers. My Y values range from 0-1 so sigmoid seems logical to me.

我得到了错误:

在我看来，我输入的形状正确的总DF为(350700，2413)，我将其重塑为(1169，300，2413)//不包括Y值.我只是似乎无法弄清楚如何使稠密层起作用并将S形曲线应用于我的Y.

To me it seems i have the input shape correct total DF is (350700 , 2413) which i reshape to a ( 1169 , 300 , 2413 ) // not including Y value. I just can't seem to figure out how to get the dense layer working and apply the sigmoid to my Y.

通过火车测试拆分，我的y_train为(993，300，1)，这是我的错误的主要问题，但我似乎无法理解自己做错了什么. x_train是(933，300，2413)x_test =(176，300，2413)y_test =(176，300，1)

With the train test split i have a y_train of (993, 300, 1) which is the main issue of my error but i can't seem to understand what i have done wrong. x_train is ( 933, 300, 2413) x_test = ( 176, 300 , 2413) y_test= (176, 300, 1)

这是我建立的网络.后端张量流(也使用theano相同的问题)

Here is the network i have set up. backend tensorflow (also used theano same issue)

_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
lstm_21 (LSTM)               (None, 300, 1000)         13656000
_________________________________________________________________
lstm_22 (LSTM)               (None, 300, 500)          3002000
_________________________________________________________________
lstm_23 (LSTM)               (None, 300, 250)          751000
_________________________________________________________________
lstm_24 (LSTM)               (None, 300, 100)          140400
_________________________________________________________________
lstm_25 (LSTM)               (None, 50)                30200
_________________________________________________________________
dense_4 (Dense)              (None, 1)                 51
=================================================================
Total params: 17,579,651
Trainable params: 17,579,651
Non-trainable params: 0
_________________________________________________________________

这是我的代码.

import numpy as np
import pandas as pd
from keras.models import Sequential
from keras.layers.advanced_activations import LeakyReLU
from keras.layers import Dense, Activation, LSTM, Flatten
from keras import backend as K
from sklearn.model_selection import train_test_split

aa = aa[np.isfinite(aa['Y1'])]
aa=aa[-350700:]

Y=aa['Y1'].values.reshape(1169,300,1) #break into 1169 samples @ 300 timestamps
aa.drop(drop1, axis=1, inplace=True) #drop the Y1 feature and others not needed.


features=aa.shape[1]

X=aa.values.reshape(1169,300,features)

seed = 7

X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.15, random_state=seed)

model = Sequential()
model.add(LSTM(1000, input_shape=(300,features),activation='relu',return_sequences=True))
model.add(LSTM(500,activation='relu',return_sequences=True))
model.add(LSTM(250,activation='relu',return_sequences=True))
model.add(LSTM(100, activation='relu',return_sequences=True))
model.add(LSTM(50,activation='relu',return_sequences=False))
model.add(Dense(1,activation='sigmoid'))
model.compile(loss='mae',
              optimizer='adam',
              metrics=['mse', 'mae', 'mape'])

print(model.summary())


# evaluate model with standardized dataset
model.fit(X_train, y_train, validation_data=(X_test,y_test), epochs=15000)

推荐答案

您的数据"与您的最后一层形状"不兼容.

Your "data" is not compatible with your "last layer shape".

• 您需要形状为(993,1)的Y_train-对整个序列进行分类
• 或者您需要将return_sequences=True保留在所有" LSTM层中-对每个时间步进行分类

• Either you need Y_train with shape (993,1) - Classifying the entire sequence
• Or you need to keep return_sequences=True in "all" LSTM layers - Classifying each time step

正确的方法取决于您要执行的操作.

What is correct depends you what you're trying to do.

这篇关于了解将密集层连接到LSTM的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！