學習谷歌的深度學習終于有點眉目了，給大家分享我的Tensorflow學習歷程。

tensorflow的官方中文文檔比較生澀，數據集一直采用的MNIST二進制數據集。并沒有過多講述怎么構建自己的圖片數據集tfrecords。

流程是：制作數據集—讀取數據集—-加入隊列

先貼完整的代碼：

#encoding=utf-8import osimport tensorflow as tffrom PIL import Imagecwd = os.getcwd()classes = {'test','test1','test2'}#制作二進制數據def create_record():  writer = tf.python_io.TFRecordWriter("train.tfrecords")  for index, name in enumerate(classes):    class_path = cwd +"/"+ name+"/"    for img_name in os.listdir(class_path):      img_path = class_path + img_name      img = Image.open(img_path)      img = img.resize((64, 64))      img_raw = img.tobytes() #將圖片轉化為原生bytes      print index,img_raw      example = tf.train.Example(        features=tf.train.Features(feature={          "label": tf.train.Feature(int64_list=tf.train.Int64List(value=[index])),          'img_raw': tf.train.Feature(bytes_list=tf.train.BytesList(value=[img_raw]))        }))      writer.write(example.SerializeToString())  writer.close()data = create_record()#讀取二進制數據def read_and_decode(filename):  # 創建文件隊列,不限讀取的數量  filename_queue = tf.train.string_input_producer([filename])  # create a reader from file queue  reader = tf.TFRecordReader()  # reader從文件隊列中讀入一個序列化的樣本  _, serialized_example = reader.read(filename_queue)  # get feature from serialized example  # 解析符號化的樣本  features = tf.parse_single_example(    serialized_example,    features={      'label': tf.FixedLenFeature([], tf.int64),      'img_raw': tf.FixedLenFeature([], tf.string)    }  )  label = features['label']  img = features['img_raw']  img = tf.decode_raw(img, tf.uint8)  img = tf.reshape(img, [64, 64, 3])  img = tf.cast(img, tf.float32) * (1. / 255) - 0.5  label = tf.cast(label, tf.int32)  return img, labelif __name__ == '__main__':  if 0:    data = create_record("train.tfrecords")  else:    img, label = read_and_decode("train.tfrecords")    print "tengxing",img,label    #使用shuffle_batch可以隨機打亂輸入 next_batch挨著往下取    # shuffle_batch才能實現[img,label]的同步,也即特征和label的同步,不然可能輸入的特征和label不匹配    # 比如只有這樣使用,才能使img和label一一對應,每次提取一個image和對應的label    # shuffle_batch返回的值就是RandomShuffleQueue.dequeue_many()的結果    # Shuffle_batch構建了一個RandomShuffleQueue，并不斷地把單個的[img,label],送入隊列中    img_batch, label_batch = tf.train.shuffle_batch([img, label],                          batch_size=4, capacity=2000,                          min_after_dequeue=1000)    # 初始化所有的op    init = tf.initialize_all_variables()    with tf.Session() as sess:      sess.run(init)      # 啟動隊列      threads = tf.train.start_queue_runners(sess=sess)      for i in range(5):        print img_batch.shape,label_batch        val, l = sess.run([img_batch, label_batch])        # l = to_categorical(l, 12)        print(val.shape, l)