完美解决TensorFlow和Keras大数据量内存溢出的问题

def get_batch(X_train, y_train, img_w, img_h, color_type, batch_size, capacity):
  '''
  Args:
    X_train: train img path list
    y_train: train labels list
    img_w: image width
    img_h: image height
    batch_size: batch size
    capacity: the maximum elements in queue
  Returns:
    X_train_batch: 4D tensor [batch_size, width, height, chanel],\
            dtype=tf.float32
    y_train_batch: 1D tensor [batch_size], dtype=int32
  '''
  X_train = tf.cast(X_train, tf.string)

  y_train = tf.cast(y_train, tf.int32)
  
  # make an input queue
  input_queue = tf.train.slice_input_producer([X_train, y_train])

  y_train = input_queue[1]
  X_train_contents = tf.read_file(input_queue[0])
  X_train = tf.image.decode_jpeg(X_train_contents, channels=color_type)

  X_train = tf.image.resize_images(X_train, [img_h, img_w], 
                   tf.image.ResizeMethod.NEAREST_NEIGHBOR)

  X_train_batch, y_train_batch = tf.train.batch([X_train, y_train],
                         batch_size=batch_size,
                         num_threads=64,
                         capacity=capacity)
  y_train_batch = tf.one_hot(y_train_batch, 10)

  return X_train_batch, y_train_batch

X_train_batch, y_train_batch = inp.get_batch(X_train, y_train, 
                       img_w, img_h, color_type, 
                       train_batch_size, capacity)
X_valid_batch, y_valid_batch = inp.get_batch(X_valid, y_valid, 
                       img_w, img_h, color_type, 
                       valid_batch_size, capacity)
with tf.Session() as sess:

  coord = tf.train.Coordinator()
  threads = tf.train.start_queue_runners(coord=coord)
  try:
    for step in np.arange(max_step):
      if coord.should_stop() :
        break
      X_train, y_train = sess.run([X_train_batch, 
                       y_train_batch])
      X_valid, y_valid = sess.run([X_valid_batch,
                       y_valid_batch])
       
      ckpt_path = 'log/weights-{val_loss:.4f}.hdf5'
      ckpt = tf.keras.callbacks.ModelCheckpoint(ckpt_path, 
                           monitor='val_loss', 
                           verbose=1, 
                           save_best_only=True, 
                           mode='min')
      model.fit(X_train, y_train, batch_size=64, 
             epochs=50, verbose=1,
             validation_data=(X_valid, y_valid),
             callbacks=[ckpt])
      
      del X_train, y_train, X_valid, y_valid

  except tf.errors.OutOfRangeError:
    print('done!')
  finally:
    coord.request_stop()
  coord.join(threads)
  sess.close()

# 读取图片函数
def get_im_cv2(paths, img_rows, img_cols, color_type=1, normalize=True):
  '''
  参数：
    paths：要读取的图片路径列表
    img_rows:图片行
    img_cols:图片列
    color_type:图片颜色通道
  返回: 
    imgs: 图片数组
  '''
  # Load as grayscale
  imgs = []
  for path in paths:
    if color_type == 1:
      img = cv2.imread(path, 0)
    elif color_type == 3:
      img = cv2.imread(path)
    # Reduce size
    resized = cv2.resize(img, (img_cols, img_rows))
    if normalize:
      resized = resized.astype('float32')
      resized /= 127.5
      resized -= 1. 
    
    imgs.append(resized)
    
  return np.array(imgs).reshape(len(paths), img_rows, img_cols, color_type)

def get_train_batch(X_train, y_train, batch_size, img_w, img_h, color_type, is_argumentation):
  '''
  参数：
    X_train：所有图片路径列表
    y_train: 所有图片对应的标签列表
    batch_size:批次
    img_w:图片宽
    img_h:图片高
    color_type:图片类型
    is_argumentation:是否需要数据增强
  返回: 
    一个generator，x: 获取的批次图片 y: 获取的图片对应的标签
  '''
  while 1:
    for i in range(0, len(X_train), batch_size):
      x = get_im_cv2(X_train[i:i+batch_size], img_w, img_h, color_type)
      y = y_train[i:i+batch_size]
      if is_argumentation:
        # 数据增强
        x, y = img_augmentation(x, y)
      # 最重要的就是这个yield，它代表返回，返回以后循环还是会继续，然后再返回。就比如有一个机器一直在作累加运算，但是会把每次累加中间结果告诉你一样，直到把所有数加完
      yield({'input': x}, {'output': y})

result = model.fit_generator(generator=get_train_batch(X_train, y_train, train_batch_size, img_w, img_h, color_type, True), 
     steps_per_epoch=1351, 
     epochs=50, verbose=1,
     validation_data=get_train_batch(X_valid, y_valid, valid_batch_size,img_w, img_h, color_type, False),
     validation_steps=52,
     callbacks=[ckpt, early_stop],
     max_queue_size=capacity,
     workers=1)