딥러닝 실습

1. 딥러닝 Flow

 

 

 

In [5]:

import numpy as np

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from keras import optimizers

In [17]:

#데이터셋 설정
time = np.array([1,2,3,4,5])
score= np.array([10,20,30,60,66])

In [18]:

#모델구성
model=Sequential()
model.add(Dense(1,input_dim=1, activation='linear')) #선형회귀

In [19]:

#모델컴파일
sgd= optimizers.SGD(lr=0.01)
model.compile(optimizer=sgd,loss='mse', metrics=['accuracy']) #평가기준:정확도

In [20]:

#모델학습
model.fit(time,score,batch_size=1,epochs=5,shuffle=False)

Epoch 1/5
5/5 [==============================] - 0s 2ms/step - loss: 733.3189 - accuracy: 0.0000e+00
Epoch 2/5
5/5 [==============================] - 0s 3ms/step - loss: 83.2137 - accuracy: 0.0000e+00
Epoch 3/5
5/5 [==============================] - 0s 3ms/step - loss: 58.2496 - accuracy: 0.0000e+00
Epoch 4/5
5/5 [==============================] - 0s 3ms/step - loss: 57.9678 - accuracy: 0.0000e+00
Epoch 5/5
5/5 [==============================] - 0s 3ms/step - loss: 57.5347 - accuracy: 0.0000e+00

Out[20]:

<tensorflow.python.keras.callbacks.History at 0x223c3049460>

In [21]:

#모델예측
print(model.predict([7])) #time이 7일때 예상 score?

[[90.83037]]

In [ ]:

 

 

*설명