# -*- coding: utf-8 -*-
import numpy as np
np.random.seed(1337)
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import SimpleRNN,Activation,Dense
from keras.optimizers import Adam
TIME_STEPS = 28 #圖檔的高
INPUT_SIZE = 28 #圖檔的行
BATCH_SIZE = 50 #每批訓練多少圖檔
BATCH_INDEX = 0
OUTPUT_SIZE = 10
CELL_SIZE = 50
LR = 0.001
#下載下傳mnist資料集
# X shape (60000,28*28) ,y shape (10000)
(X_train,y_train),(X_test,y_test) = mnist.load_data()
# 資料預處理
X_train = X_train.reshape(-1,28,28)/255
X_test = X_test.reshape(-1,28,28)/255
y_train = np_utils.to_categorical(y_train,num_classes=10)
y_test = np_utils.to_categorical(y_test,num_classes=10)
# 模組化型
model = Sequential()
# RNN
model.add(SimpleRNN(
batch_input_shape=(None,TIME_STEPS,INPUT_SIZE),# 每次訓練的量(None表示全部)，圖檔大小
output_dim=CELL_SIZE,
))
# 輸出層
model.add(Dense(OUTPUT_SIZE))
model.add(Activation('softmax'))
# 優化器
adam = Adam(LR)
model.compile(optimizer=adam,
loss='categorical_crossentropy',
metrics=['accuracy'])
# 訓練
for step in range(4001):
X_batch=X_train[BATCH_INDEX:BATCH_SIZE+BATCH_INDEX,:,:]
Y_batch=y_train[BATCH_INDEX:BATCH_SIZE+BATCH_INDEX,:]
cost = model.train_on_batch(X_batch,Y_batch)
BATCH_INDEX += BATCH_SIZE
BATCH_INDEX = 0 if BATCH_INDEX>=X_train.shape[0] else BATCH_INDEX
if step % 500 == 0:
cost,accuracy = model.evaluate(X_test,y_test,batch_size=y_test.shape[0],verbose=False)
print('test cost: ',cost,'test accuracy: ',accuracy)