python - 无法为占位符张量提供值

Question

我写了一个简单版本的双向 lstm 用于句子分类。但它一直给我“你必须为占位符张量'train_x'提供一个值”错误，这似乎来自变量初始化步骤。

data = load_data(FLAGS.data)
model = RNNClassifier(FLAGS)
init = tf.initialize_all_variables()

with tf.Session() as sess:
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(sess=sess, coord=coord)
    sess.run(init)
    print("Graph initialized..")
    print()
    np.random.seed(FLAGS.random_state)
    for epoch in range(FLAGS.max_max_epoch):

        loss = sess.run(model.cost, feed_dict={model.train_x: data.train_x, model.train_y: data.train_y, 
                                        model.embedding_placeholder: data.glove_vec})
        print("Epoch {:2d}: Loss = {:.6f} = {:.5f}".format(epoch+1, loss))
    coord.request_stop()
    coord.join(threads)

和 RNNClassifier 类代码(在不同的目录中):

class RNNClassifier:

    def __init__(self, FLAGS):
        self.params = FLAGS
        with tf.device("/cpu:0"):
            self.train_x = tf.placeholder(tf.int32, [6248, 42], name='train_x')
            self.train_y = tf.placeholder(tf.int32, [6248, 3], name='train_y')
            self.embedding_placeholder = tf.placeholder(tf.float32, [1193515, 100])

        with tf.variable_scope('forward_lstm'):
            lstm_fw_cell = tf.nn.rnn_cell.LSTMCell(num_units=self.params.num_hidden, use_peepholes=False, 
                                                activation=tf.nn.relu, forget_bias=0.0, 
                                                state_is_tuple=True)
        with tf.variable_scope('backward_lstm'):
            lstm_bw_cell = tf.nn.rnn_cell.LSTMCell(num_units=self.params.num_hidden, use_peepholes=False, 
                                                activation=tf.nn.relu, forget_bias=0.0, 
                                                state_is_tuple=True)

        fw_initial_state = lstm_fw_cell.zero_state(self.params.batch_size, tf.float32)
        bw_initial_state = lstm_bw_cell.zero_state(self.params.batch_size, tf.float32)
        self._initial_state = [fw_initial_state, bw_initial_state]

        with tf.device("/cpu:0"), tf.variable_scope('softmax'):
            self.W = tf.get_variable('W', [self.params.num_hidden*2, self.params.num_classes])
            self.b = tf.get_variable('b', [self.params.num_classes], initializer=tf.constant_initializer(0.0))

        batched_inputs, batched_labels = self.batch_data()
        embed_inputs = self.use_embedding(batched_inputs)


        rnn_outputs, output_state_fw, output_state_bw  = tf.nn.bidirectional_rnn(
            cell_fw=lstm_fw_cell,
            cell_bw=lstm_bw_cell,
            inputs=embed_inputs,
            initial_state_fw=fw_initial_state,
            initial_state_bw=bw_initial_state
            )


        logits = tf.matmul(rnn_outputs[-1], self.W) + self.b

        self._cost = cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits, tf.cast(batched_labels, tf.float32)))
        optimizer = tf.train.AdamOptimizer(learning_rate=0.05).minimize(cost)


    def batch_data(self):
        # inputs = tf.convert_to_tensor(train_x, dtype=tf.int32)
        # labels = tf.convert_to_tensor(train_y, dtype=tf.int32)
        batched_inputs, batched_labels = tf.train.batch(
            tensors=[self._train_x, self._train_y],
            batch_size=self.params.batch_size,
            dynamic_pad=True,
            enqueue_many=True,
            name='batching'
    )
    return batched_inputs, batched_labels


    def use_embedding(self, batched_inputs):
        with tf.device("/cpu:0"), tf.name_scope("input_embedding"):
            embedding = tf.get_variable("embedding", shape=[1193515, 100], trainable=False)
            embedding_init = embedding.assign(self.embedding_placeholder)
            embed_inputs = tf.split(1, self.params.seq_len, tf.nn.embedding_lookup(embedding_init, batched_inputs))
            embed_inputs = [tf.squeeze(input_, [1]) for input_ in embed_inputs]
    return embed_inputs

    @property
    def cost(self):
        return self._cost

输出(包括错误):

I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:925] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
I tensorflow/core/common_runtime/gpu/gpu_init.cc:102] Found device 0 with properties: 
name: GeForce GTX 750 Ti
major: 5 minor: 0 memoryClockRate (GHz) 1.0845
pciBusID 0000:01:00.0
Total memory: 2.00GiB
Free memory: 1.41GiB
I tensorflow/core/common_runtime/gpu/gpu_init.cc:126] DMA: 0 
I tensorflow/core/common_runtime/gpu/gpu_init.cc:136] 0:   Y 
I tensorflow/core/common_runtime/gpu/gpu_device.cc:839] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 750 Ti, pci bus id: 0000:01:00.0)
E tensorflow/core/client/tensor_c_api.cc:485] You must feed a value for placeholder tensor 'train_x' with dtype int32 and shape [6248,42]
     [[Node: train_x = Placeholder[dtype=DT_INT32, shape=[6248,42], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

Graph initialized..

W tensorflow/core/framework/op_kernel.cc:936] Out of range: PaddingFIFOQueue '_0_batching/padding_fifo_queue' is closed and has insufficient elements (requested 50, current size 0)
     [[Node: batching = QueueDequeueMany[_class=["loc:@batching/padding_fifo_queue"], component_types=[DT_INT32, DT_INT32], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](batching/padding_fifo_queue, batching/n)]]
W tensorflow/core/framework/op_kernel.cc:936] Out of range: PaddingFIFOQueue '_0_batching/padding_fifo_queue' is closed and has insufficient elements (requested 50, current size 0)
     [[Node: batching = QueueDequeueMany[_class=["loc:@batching/padding_fifo_queue"], component_types=[DT_INT32, DT_INT32], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](batching/padding_fifo_queue, batching/n)]]
E tensorflow/core/client/tensor_c_api.cc:485] PaddingFIFOQueue '_0_batching/padding_fifo_queue' is closed and has insufficient elements (requested 50, current size 0)
     [[Node: batching = QueueDequeueMany[_class=["loc:@batching/padding_fifo_queue"], component_types=[DT_INT32, DT_INT32], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](batching/padding_fifo_queue, batching/n)]]
     [[Node: batching/_9 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_1191_batching", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
Traceback (most recent call last):
  File "train_lstm.py", line 66, in <module>
    model.embedding_placeholder: data.glove_vec})
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 382, in run
    run_metadata_ptr)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 655, in _run
    feed_dict_string, options, run_metadata)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 723, in _do_run
    target_list, options, run_metadata)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 743, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors.OutOfRangeError: PaddingFIFOQueue '_0_batching/padding_fifo_queue' is closed and has insufficient elements (requested 50, current size 0)
     [[Node: batching = QueueDequeueMany[_class=["loc:@batching/padding_fifo_queue"], component_types=[DT_INT32, DT_INT32], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](batching/padding_fifo_queue, batching/n)]]
     [[Node: batching/_9 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_1191_batching", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
Caused by op u'batching', defined at:
  File "train_lstm.py", line 49, in <module>
    model = RNNClassifier(FLAGS)
  File "/home/ccrmad/Code/TDLSTM/models/rnn_classifier.py", line 34, in __init__
    batched_inputs, batched_labels = self.batch_data()
  File "/home/ccrmad/Code/TDLSTM/models/rnn_classifier.py", line 74, in batch_data
    name='batching'
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/input.py", line 595, in batch
    dequeued = queue.dequeue_many(batch_size, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/data_flow_ops.py", line 435, in dequeue_many
    self._queue_ref, n=n, component_types=self._dtypes, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_data_flow_ops.py", line 867, in _queue_dequeue_many
    timeout_ms=timeout_ms, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 703, in apply_op
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2310, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1232, in __init__
    self._traceback = _extract_stack()

我尝试在 init = tf.initialize_all_variables() 之前移动 train_x 和 train_y 占位符初始化并将它们作为 RNNClassifier() 提供两个参数，但它仍然给出相同的错误。为什么？

Answer 1

看起来问题出在这个方法中，在 RNNClassifier 中:

def batch_data(self):
    # ...
    batched_inputs, batched_labels = tf.train.batch(
        tensors=[self._train_x, self._train_y],
        batch_size=self.params.batch_size,
        dynamic_pad=True,
        enqueue_many=True,
        name='batching')

tf.train.batch() 的两个张量参数是 self._train_x 和 self._train_y。在 RNNClassifier 构造函数中，您似乎将它们创建为 tf.placeholder() 张量:

def __init__(self, FLAGS):
    # ...
    with tf.device("/cpu:0"):
        self.train_x = tf.placeholder(tf.int32, [6248, 42], name='train_x')
        self.train_y = tf.placeholder(tf.int32, [6248, 3], name='train_y')

...尽管我假设 self._train_x 和 self.train_x 之间的区别是复制粘贴错误，因为 self._train_x 似乎没有在其他任何地方定义。

现在，关于 tf.train.batch() 的一件令人惊讶的事情是它在一个完全独立的线程中使用其输入，称为“队列运行器”，并在您调用 tf.train.start_queue_runners() 时启动.此线程在依赖于您的占位符的子图上调用 Session.run()，但不知道如何提供这些占位符，因此此调用失败，导致您看到的错误。

那你应该怎么解决呢？一种选择是使用 "feeding queue runner" ，对此有实验支持。一个更简单的选择是使用 tf.train.slice_input_producer() 从您的输入数据中生成切片，如下所示:

def batch_data(self, train_x, train_y):
    input_slice, label_slice = tf.train.slice_input_producer([train_x, train_y])
    batched_inputs, batched_labels = tf.train.batch(
        tensors=[input_slice, label_slice],
        batch_size=self.params.batch_size,
        dynamic_pad=False,   # All rows are the same shape.
        enqueue_many=False,  # tf.train.slice_input_producer() produces one row at a time.
        name='batching')
    return batched_inputs, batched_labels

# ...
# Create batches from the entire training data, where `array_input` and
# `array_labels` are two NumPy arrays.
batched_inputs, batched_labels = model.batch_data(array_input, array_labels)