Keras에서 mnist 핸드 숫자 구현

이전에tensorflow를 사용했는데 학우들의keras를 추천받아 이전 문서의 mnist에서 손으로 쓴 디지털 데이터 집합을 가져와서 연습했습니다. 코드는 다음과 같습니다.

import struct
import numpy as np
import os

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

def load_mnist(path, kind):
    labels_path = os.path.join(path, '%s-labels.idx1-ubyte' % kind)
    images_path = os.path.join(path, '%s-images.idx3-ubyte' % kind)
    with open(labels_path, 'rb') as lbpath:
        magic, n = struct.unpack('>II', lbpath.read(8))
        labels = np.fromfile(lbpath, dtype=np.uint8)
    with open(images_path, 'rb') as imgpath:
        magic, num, rows, cols = struct.unpack(">IIII", imgpath.read(16))
        images = np.fromfile(imgpath, dtype=np.uint8).reshape(len(labels), 784)  #28*28=784
    return images, labels

#loading train and test data
X_train, Y_train = load_mnist('.\\data', kind='train')
X_test, Y_test = load_mnist('.\\data', kind='t10k')

#turn labels to one_hot code
Y_train_ohe = keras.utils.to_categorical(Y_train, num_classes=10)

#define models
model = Sequential()

model.add(Dense(input_dim=X_train.shape[1],output_dim=50,init='uniform',activation='tanh'))
model.add(Dense(input_dim=50,output_dim=50,init='uniform',activation='tanh'))
model.add(Dense(input_dim=50,output_dim=Y_train_ohe.shape[1],init='uniform',activation='softmax')) 

sgd = SGD(lr=0.001, decay=1e-7, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=["accuracy"])

#start training
model.fit(X_train,Y_train_ohe,epochs=50,batch_size=300,shuffle=True,verbose=1,validation_split=0.3)

#count accuracy
y_train_pred = model.predict_classes(X_train, verbose=0)
  
train_acc = np.sum(Y_train == y_train_pred, axis=0) / X_train.shape[0]  
print('Training accuracy: %.2f%%' % (train_acc * 100))
  
y_test_pred = model.predict_classes(X_test, verbose=0)
test_acc = np.sum(Y_test == y_test_pred, axis=0) / X_test.shape[0]  
print('Test accuracy: %.2f%%' % (test_acc * 100))

훈련 결과는 다음과 같다.

Epoch 45/50
42000/42000 [==============================] - 1s 17us/step - loss: 0.2174 - acc: 0.9380 - val_loss: 0.2341 - val_acc: 0.9323
Epoch 46/50
42000/42000 [==============================] - 1s 17us/step - loss: 0.2061 - acc: 0.9404 - val_loss: 0.2244 - val_acc: 0.9358
Epoch 47/50
42000/42000 [==============================] - 1s 17us/step - loss: 0.1994 - acc: 0.9413 - val_loss: 0.2295 - val_acc: 0.9347
Epoch 48/50
42000/42000 [==============================] - 1s 17us/step - loss: 0.2003 - acc: 0.9413 - val_loss: 0.2224 - val_acc: 0.9350
Epoch 49/50
42000/42000 [==============================] - 1s 18us/step - loss: 0.2013 - acc: 0.9417 - val_loss: 0.2248 - val_acc: 0.9359
Epoch 50/50
42000/42000 [==============================] - 1s 17us/step - loss: 0.1960 - acc: 0.9433 - val_loss: 0.2300 - val_acc: 0.9346
Training accuracy: 94.11%
Test accuracy: 93.61%