import tensorflow as tf
import matplotlib.image as img
import matplotlib.pyplot as plt
import numpy as np
sess = tf.InteractiveSession()
image = img.imread('D:/Documents/Pictures/logo7.jpg')
shape = tf.shape(image).eval()
h,w = shape[0],shape[1]
standardization_image = tf.image.per_image_standardization(image)#標準化

fig = plt.figure()
fig1 = plt.figure()
ax = fig.add_subplot(111)
ax.set_title('orginal image')
ax.imshow(image)
ax1 = fig1.add_subplot(311)
ax1.set_title('original hist')
ax1.hist(sess.run(tf.reshape(image,[h*w,-1])))
ax1 = fig1.add_subplot(313)
ax1.set_title('standardization hist')
ax1.hist(sess.run(tf.reshape(standardization_image,[h*w,-1])))
plt.ion()
plt.show()

saver = tf.train.Saver()#聲明saver用來保存模型
with tf.Session() as sess:
 for i in range(train_step):
 #.....訓(xùn)練操作
 if i%100 == 0 && i!= 0:#每間隔訓(xùn)練100次存儲一個模型，默認最多能存5個，如果超過5個先將序號小的覆蓋掉
  saver.save(sess,str(i)+"_"+'model.ckpt',global_step=i)

saver = tf.train.Saver()
with tf.Session() as sess:
 saver.restore(sess, "step_1497batch_64model.ckpt-1497")#加載對應(yīng)的參數(shù)

def read_data(tfrecords_file, batch_size, image_size):#讀取tfrecords文件
 filename_queue = tf.train.string_input_producer([tfrecords_file])
 reader = tf.TFRecordReader()
 _, serialized_example = reader.read(filename_queue)
 
 img_features = tf.parse_single_example(
  serialized_example,
 features={
 'label': tf.FixedLenFeature([], tf.int64),
 'image_raw': tf.FixedLenFeature([], tf.string),
  })
 image = tf.decode_raw(img_features['image_raw'], tf.float32)
 min_after_dequeue = 1000
 image = tf.reshape(image, [image_size, image_size,1])
 image = tf.image.resize_images(image, (32,32),method=3)#縮放成32×32
 image = tf.image.per_image_standardization(image)#圖像標準化
 label = tf.cast(img_features['label'], tf.int32)  
 capacity = min_after_dequeue + 3 * batch_size  
 image_batch, label_batch = tf.train.shuffle_batch([image, label],
       min_after_dequeue = min_after_dequeue)
 return image_batch, tf.one_hot(label_batch,6)#返回的標簽經(jīng)過one_hot編碼

#將得到的圖像數(shù)據(jù)與標簽都是tensor哦，不能輸出的！
read_image_batch,read_label_batch = read_data('train_data\\tfrecord\\TrainC6_95972.tfrecords',batch_size,120)

image = tf.reshape(image, [image_size, image_size,1])#與opencv的reshape結(jié)果一樣
image = tf.image.resize_images(image, (32,32),method=3)#縮放成32×32，與opencv的resize結(jié)果一樣，插值方法要選擇三次立方插值
image = tf.image.per_image_standardization(image)#圖像標準化

with tf.name_scope('inputs'):
 img_raw = tf.placeholder(dtype=tf.float32, shape=[1,120, 120, 1], name='input')#輸入數(shù)據(jù)
 keep_prob = tf.placeholder(tf.float32,name='keep_prob')

with tf.name_scope('preprocess'):#圖中的預(yù)處理函數(shù)，當成節(jié)點順序調(diào)用
 img_120 = tf.reshape(img_raw, [120, 120,1])
 img_norm = tf.cast(img_120, "float32") / 256
 img_32 = tf.image.resize_images(img_norm, (32,32),method=3)
 img_std = tf.image.per_image_standardization(img_32)
 img = tf.reshape(img_std, [1,32, 32,1])

with tf.name_scope('output'):#圖像塞到網(wǎng)絡(luò)中
 output = MyNet(img,keep_prob,n_cls)

ans = tf.argmax(tf.nn.softmax(output),1)#計算模型得到的結(jié)果

init = tf.global_variables_initializer()

saver = tf.train.Saver()


if __name__ == '__main__':

 with tf.Session() as sess:

 sess.run(init)
 saver.restore(sess, "step_1497batch_64model.ckpt-1497")#效果更好
 index = 0
 path = "buffer\\"
 
 while True:
  f = path + str(index)+'.jpg'#從0.jpg、1.jpg、2.jpg.....一直讀
  if os.path.exists(f):
  cv_img = cv.imread(f,0)
  cv_img = OneImgPrepro(cv_img)
  cv_img = cv_img.reshape(1,cv_img.shape[0],cv_img.shape[1],1)#需要reshape成placeholder可接收型
  clas = ans.eval(feed_dict={img_raw:cv_img,keep_prob:1})#feed的速度快！

  print(clas)#輸出分類
  
  index += 1