OutOfRangeError: RandomShuffleQueue '_7_shuffle_batch_1/random_shuffle_queue' 已关闭且元素不足（请求 200，当前大小 0）

Question

非常感谢您阅读我的问题

我的数据集大约有 9779 张图像（.dcm）。有两个标签，一个是1，有5000张训练图片，另一个是0，有4779张图片。

我使用 TFrecords 来合并和构建数据集。然后将其输入 CNN 模型。

writer = tf.python_io.TFRecordWriter("train.tfrecords")
    for idx, img_path in enumerate(all_images):#all_images is a list containing all path of all images
        img = dm.read_file(img_path)

        pixel_bytes = img.PixelData 
        img_raw = pixel_bytes
        if idx < len_all_cancer_images:
            example = tf.train.Example(features=tf.train.Features(feature={
            "label": tf.train.Feature(int64_list = tf.train.Int64List(value = [1])),
            'img_raw': tf.train.Feature(bytes_list = tf.train.BytesList(value = [img_raw]))}))
            writer.write(example.SerializeToString())

        else:
            example = tf.train.Example(features=tf.train.Features(feature={
            "label": tf.train.Feature(int64_list = tf.train.Int64List(value=[0])),
            'img_raw': tf.train.Feature(bytes_list = tf.train.BytesList(value = [img_raw]))}))
            writer.write(example.SerializeToString())

    writer.close()

然后我使用 TFRecordReader 读取它

    filename = '/Users/wuzhenglin/Python_nice/SAL_LUNG/train.tfrecords'
    filename_queue = tf.train.string_input_producer([filename])

    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)   
    features = tf.parse_single_example(serialized_example,
                                       features={
                                           'label': tf.FixedLenFeature([], tf.int64),
                                           'img_raw' : tf.FixedLenFeature([], tf.string),
                                       })

    print features['img_raw']
    print features['label']



    img = tf.decode_raw(features['img_raw'], tf.uint8)
    img = tf.reshape(img, [512, 512, 1])
    img = tf.cast(img, tf.float32) * (1. / 255)
    label = tf.cast(features['label'], tf.int32)

然后当我想读取我的数据时

img_batch, label_batch = tf.train.shuffle_batch([img, label],
                                                batch_size = 200, capacity = 9779,
                                                min_after_dequeue = 2000)
init = tf.global_variables_initializer()

    with tf.Session() as sess:
        sess.run(init)

        coord = tf.train.Coordinator()
        threads = tf.train.start_queue_runners(coord = coord)

        for i in xrange(1):
            a, b = sess.run([img_batch, label_batch])
            a_ = a[0]
            b_ = b[0]
            img_1 = tf.reshape(a_[0, :, :, :], [512, 512])
            print img_1.shape
            print b_.shape
            print b_
            print '********************'
            plt.imshow(sess.run(img_1), cmap='gray')

我想挑选一些数据并打印出来，但是出错了……

第一：

InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 524288 values, but the requested shape has 262144
     [[Node: Reshape = Reshape[T=DT_UINT8, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](DecodeRaw, Reshape/shape)]]

第二：

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 880, in runfile
    execfile(filename, namespace)
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 94, in execfile
    builtins.execfile(filename, *where)
  File "/Users/wuzhenglin/Python_nice/SAL_LUNG/test.py", line 96, in <module>
    read_and_decode()
  File "/Users/wuzhenglin/Python_nice/SAL_LUNG/test.py", line 82, in read_and_decode
    a, b = sess.run([img_batch, label_batch])
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 767, in run
run_metadata_ptr)
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 965, in _run
    feed_dict_string, options, run_metadata)
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1015, in _do_run
target_list, options, run_metadata)
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1035, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.OutOfRangeError: RandomShuffleQueue '_7_shuffle_batch_1/random_shuffle_queue' is closed and has insufficient elements (requested 200, current size 0)
     [[Node: shuffle_batch_1 = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_INT32], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](shuffle_batch_1/random_shuffle_queue, shuffle_batch_1/n)]]

Caused by op u'shuffle_batch_1', defined at:
  File "<stdin>", line 1, in <module>
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 880, in runfile
    execfile(filename, namespace)
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 94, in execfile
    builtins.execfile(filename, *where)
  File "/Users/wuzhenglin/Python_nice/SAL_LUNG/test.py", line 96, in <module>
read_and_decode()
  File "/Users/wuzhenglin/Python_nice/SAL_LUNG/test.py", line 71, in read_and_decode
min_after_dequeue = 2000)
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/tensorflow/python/training/input.py", line 1165, in shuffle_batch
name=name)
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/tensorflow/python/training/input.py", line 739, in _shuffle_batch
dequeued = queue.dequeue_many(batch_size, name=name)
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/data_flow_ops.py", line 458, in dequeue_many
    self._queue_ref, n=n, component_types=self._dtypes, name=name)
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/tensorflow/python/ops/gen_data_flow_ops.py", line 1310, in _queue_dequeue_many_v2
    timeout_ms=timeout_ms, name=name)
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 763, in apply_op
op_def=op_def)
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2327, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/Users/wuzhenglin/anaconda/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1226, in __init__
    self._traceback = _extract_stack()

OutOfRangeError (see above for traceback): RandomShuffleQueue '_7_shuffle_batch_1/random_shuffle_queue' is closed and has insufficient elements (requested 200, current size 0)
     [[Node: shuffle_batch_1 = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_INT32], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](shuffle_batch_1/random_shuffle_queue, shuffle_batch_1/n)]]

还有一些有用的信息，image.dcm是512*512，RGB

真的非常感谢你:-)

Answer 1

1 个错误InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 524288 values, but the requested shape has 262144 表明您的整形操作的输入大小为 [512, 512, 2]

# this line causes the error,, you have to confirm that your image size
img = tf.reshape(img, [512, 512, 1])
# should be
img = tf.reshape(img, [512, 512, 2])
# another line with mkstake; here you dont need to use tensorflow reshape; you can use numpy reshape since a[0] is python object
# img_1 = tf.reshape(a_[0, :, :, :], [512, 512])
img_1 = np.reshape(a_[0, :, :, :], [512, 512, 2])

由于第一个错误而出现第二个错误。所以请确保您在输入图像大小时没有犯任何错误。