DEEP LEARNING EXOPLANET ATMOSPHERIC RETRIEVAL WORKFLOW

# 0. 사용할 패키지 불러오기
from keras.utils import np_utils
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Activation
import numpy as np

# 1. 데이터셋 생성하기
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(60000, 784).astype('float32') / 255.0
x_test = x_test.reshape(10000, 784).astype('float32') / 255.0
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)

# 2. 모델 구성하기
model = Sequential()
model.add(Dense(units=64, input_dim=28*28, activation='relu'))
model.add(Dense(units=10, activation='softmax'))

# 3. 모델 학습과정 설정하기
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

# 4. 모델 학습시키기
hist = model.fit(x_train, y_train, epochs=5, batch_size=32)

prob_pred = model.predict(x_test)
prob_label = prob_pred.argmax(axis=-1)
np.savetxt('y_pred.csv', prob_label,fmt='%d')