예제 5-2 시계열 데이터를 예측하는 LSTM

In [2]:

    

# %load /home/sjkim/.jupyter/head.py
%matplotlib inline
%load_ext autoreload 
%autoreload 2
from importlib import reload

import matplotlib.pyplot as plt
import numpy as np

import pandas as pd
import os
#os.environ["CUDA_VISIBLE_DEVICES"]="0"

# seaborn
#import seaborn as sns
#sns.set( style = 'white', font_scale = 1.7)
#sns.set_style('ticks')
#plt.rcParams['savefig.dpi'] = 200

# font for matplotlib
#import matplotlib
#import matplotlib.font_manager as fm
#fm.get_fontconfig_fonts()
#font_location = '/usr/share/fonts/truetype/nanum/NanumGothicBold.ttf'
#font_name = fm.FontProperties(fname=font_location).get_name()
#matplotlib.rc('font', family=font_name)


    

    




The autoreload extension is already loaded. To reload it, use:
  %reload_ext autoreload

In [8]:

    

import ex5_2_lstm_airplane as example


    

In [9]:

    

example.main()


    

    













    













    




(131, 12, 1) (131,)
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_3 (InputLayer)         (None, 12, 1)             0         
_________________________________________________________________
lstm_3 (LSTM)                (None, 10)                480       
_________________________________________________________________
dense_3 (Dense)              (None, 1)                 11        
=================================================================
Total params: 491
Trainable params: 491
Non-trainable params: 0
_________________________________________________________________






    













    




27/27 [==============================] - 0s
Loss: 0.00120721315034






    













    




27/27 [==============================] - 0s
Loss: 0.00120721315034
(27,) (27,)






    













    

In [ ]: