[TIL]Day 70

구글 드라이브 마운트

from google.colab import drive
drive.mount('/content/gdrive')

데이터 분리

from sklearn.model_selection import train_test_split
x_train,x_val,y_train,y_val = train_test_split(x_train_all,y_train_all,stratify=y_train_all,test_size=0.2,random_state=42)

라벨인코딩(one-hot)

y_train_encoded = tf.keras.utils.to_categorical(y_train)
y_val_encoded = tf.keras.utils.to_categorical(y_val)

모델 생성
model = keras.Sequential()

모델 컴파일 및 학습

model_ebd.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
history = model_ebd.fit(x_train_seq,y_train,epochs=10,batch_size=32,validation_data=(x_val_seq,y_val))

# 훈련된 모델을 사용하여 이미지에 대한 예측 만들기
predictions = model.predict(test_images)

훈련 히스토리 보기

plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train_loss','val_loss'])
plt.show()

plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train_accuracy','val_accuracy'])
plt.show()

드롭아웃

# Lab 10 MNIST and NN
import numpy as np
import random
import tensorflow as tf

random.seed(777)  # for reproducibility
learning_rate = 0.001
batch_size = 100
training_epochs = 15
nb_classes = 10
drop_rate = 0.3
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
print(x_train.shape)

x_train = x_train.reshape(x_train.shape[0], 28 * 28)
x_test = x_test.reshape(x_test.shape[0], 28 * 28)

y_train = tf.keras.utils.to_categorical(y_train, nb_classes)
y_test = tf.keras.utils.to_categorical(y_test, nb_classes)

tf.model = tf.keras.Sequential()
# Glorot normal initializer, also called Xavier normal initializer.
# see https://www.tensorflow.org/api_docs/python/tf/initializers

tf.model.add(tf.keras.layers.Dense(input_dim=784, units=512, kernel_initializer='glorot_normal', activation='relu'))
tf.model.add(tf.keras.layers.Dropout(drop_rate))
tf.model.add(tf.keras.layers.Dense(units=512, kernel_initializer='glorot_normal', activation='relu'))
tf.model.add(tf.keras.layers.Dropout(drop_rate))
tf.model.add(tf.keras.layers.Dense(units=512, kernel_initializer='glorot_normal', activation='relu'))
tf.model.add(tf.keras.layers.Dropout(drop_rate))
tf.model.add(tf.keras.layers.Dense(units=512, kernel_initializer='glorot_normal', activation='relu'))
tf.model.add(tf.keras.layers.Dropout(drop_rate))
tf.model.add(tf.keras.layers.Dense(units=nb_classes, kernel_initializer='glorot_normal', activation='softmax'))
tf.model.compile(loss='categorical_crossentropy',
                 optimizer=tf.keras.optimizers.Adam(lr=learning_rate), metrics=['accuracy'])
tf.model.summary()

history = tf.model.fit(x_train, y_train, batch_size=batch_size, epochs=training_epochs)

# predict 10 random hand-writing data
y_predicted = tf.model.predict(x_test)
for x in range(0, 10):
    random_index = random.randint(0, x_test.shape[0]-1)
    print("index: ", random_index,
          "actual y: ", np.argmax(y_test[random_index]),
          "predicted y: ", np.argmax(y_predicted[random_index]))

# evaluate test set
evaluation = tf.model.evaluate(x_test, y_test)
print('loss: ', evaluation[0])
print('accuracy', evaluation[1])