我为句子分类编写了一个简单的双向lstm版本。但它一直在给我＆＃34;你必须为占位符张量提供一个价值＆＃39; train_x＆＃39;＆＃34;＆＃34;错误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)
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train_x之前移动train_y和init = tf.initialize_all_variables()占位符初始化，并将它们作为两个args提供给RNNClassifier（），但它仍然会给出相同的错误。为什么呢？
答案 0 :(得分：0)
这就是我所做的..
我可以改变我初始化输入变量的方式：
data = load_data(FLAGS.data)
model = RNNClassifier(FLAGS, data)
init = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
for epoch in range(FLAGS.max_max_epoch):
sess.run(model.train_step)
loss, acc = sess.run([model.mean_cost, model.accuracy])
print("Epoch {:2d}: Loss = {:.6f}; Training Accuracy = {:.5f}".format(epoch+1, loss, acc))
print()
coord.request_stop()
coord.join(threads)
在RNNClassifier类中我可以替换
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])
（并删除use_embedding()）至
def __init__(self, FLAGS, data):
self._train_x = tf.convert_to_tensor(data.train_x, dtype=tf.int32)
self._train_y = tf.convert_to_tensor(data.train_y, dtype=tf.int32)
embedding = tf.get_variable("embedding", shape=self.embedding_shape, trainable=False)
self.embedding_init = embedding.assign(data.glove_vec)
这样，在调用队列运行程序之前，所有内容都使用RNNClassifier(FLAGS, data)初始化。
我仍然不知道为什么之前使用占位符的方式不起作用。我检查了dtype和数据形状，它们都匹配。 This post似乎有类似的问题而且＃34;答案＆＃34;建议用tf.Variable替换占位符。我试过这个 - ＆gt;现在可以输入输入值，但是显示它不像占位符那样工作，只提供初始值..
更新：我认为错误可能是由RNNClassifier类中的操作输入批处理引起的，这会以某种方式影响将输入数据输入到图表中（如果您知道原因，请再次纠正我错误，谢谢！）。在初始化会话之前，我已经将我的批处理和嵌入函数重新定位到我的主代码上，这样我认为它确保所有输入都定义到主管道，并且批处理和预取将在tf图形内部处理（不使用占位符）
这是我的代码：
def batch(x, y):
with tf.device("/cpu:0"):
x = tf.convert_to_tensor(x, dtype=tf.int32)
y = tf.convert_to_tensor(y, dtype=tf.int32)
batched_x, batched_y = tf.train.batch(
tensors=[x, y],
batch_size=50,
dynamic_pad=True,
enqueue_many=True,
name='batching'
)
return (batched_x, batched_y)
def embed(df):
with tf.device("/cpu:0"), tf.variable_scope("embed"):
embedding = tf.get_variable("embedding", shape=df.embed_shape, trainable=False)
embedding_init = embedding.assign(df.embed_vec)
return embedding_init
data = load_data(FLAGS.data)
pretrained_embed = embed(data)
batched_train_x, batched_train_y = batch(data.train_x, data.train_y)
batched_test_x, batched_test_y = batch(data.train_x, data.train_y)
model = RNNClassifier(FLAGS, pretrained_embed)
logits = model.inference(batched_train_x)
test_pred = model.inference(batched_test_x, reuse=True)
loss = model.loss(logits, batched_train_y)
test_loss = model.loss(test_pred, batched_test_y)
train_op = model.training(loss[0])
init = tf.group(tf.initialize_all_variables(),
tf.initialize_local_variables())
with tf.Session() as sess:
t0 = time.time()
sess.run(init)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
np.random.seed(FLAGS.random_state)
for epoch in range(FLAGS.max_max_epoch):
_, output = sess.run([train_op, loss])
loss_value, acc = output
print("Epoch {:2d}: Loss = {:.6f}; Training Accuracy = {:.5f}".format(epoch+1, loss_value, acc))
print()
coord.request_stop()
coord.join(threads)
RNNClassifier：
class RNNClassifier:
def __init__(self, FLAGS, embedding_init):
self.batch_size = FLAGS.batch_size
self.num_hidden = FLAGS.num_hidden
self.num_classes = FLAGS.num_classes
self.seq_len = FLAGS.seq_len
self.embedding_init = embedding_init
def inference(self, batched_inputs, reuse=None):
embed_inputs = tf.nn.embedding_lookup(self.embedding_init, tf.transpose(batched_inputs))
with tf.variable_scope('hidden', reuse=reuse):
with tf.variable_scope('forward_lstm'):
lstm_fw_cell = tf.nn.rnn_cell.LSTMCell(num_units=self.num_hidden, use_peepholes=False,
activation=tf.nn.relu, forget_bias=0.0,
initializer=tf.random_uniform_initializer(-1.0, 1.0),
state_is_tuple=True)
lstm_fw_cell = tf.nn.rnn_cell.DropoutWrapper(cell=lstm_fw_cell, input_keep_prob=0.7)
with tf.variable_scope('backward_lstm'):
lstm_bw_cell = tf.nn.rnn_cell.LSTMCell(num_units=self.num_hidden, use_peepholes=False,
activation=tf.nn.relu, forget_bias=0.0,
initializer=tf.random_uniform_initializer(-1.0, 1.0),
state_is_tuple=True)
lstm_bw_cell = tf.nn.rnn_cell.DropoutWrapper(cell=lstm_bw_cell, input_keep_prob=0.7)
fw_initial_state = lstm_fw_cell.zero_state(self.batch_size, tf.float32)
bw_initial_state = lstm_bw_cell.zero_state(self.batch_size, tf.float32)
rnn_outputs, output_state_fw, output_state_bw = tf.nn.bidirectional_rnn(
cell_fw=lstm_fw_cell,
cell_bw=lstm_bw_cell,
inputs=tf.unpack(embed_inputs),
# sequence_length=self.seq_len,
initial_state_fw=fw_initial_state,
initial_state_bw=bw_initial_state
)
with tf.variable_scope('output', reuse=reuse):
with tf.variable_scope('softmax'):
W = tf.get_variable('W', [self.num_hidden*2, self.num_classes],
initializer=tf.truncated_normal_initializer(stddev=0.1))
b = tf.get_variable('b', [self.num_classes], initializer=tf.constant_initializer(0.1))
logits = tf.matmul(rnn_outputs[-1], W) + b
return logits
def loss(self, logits, labels):
cost = tf.nn.softmax_cross_entropy_with_logits(logits, tf.cast(labels, tf.float32))
# self.total_cost = tf.reduce_sum(self.cost)
mean_cost = tf.reduce_mean(cost)
correct_pred = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
return mean_cost, accuracy
def training(self, cost):
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
train_op = optimizer.minimize(cost)
return train_op
另外，我希望Stackoverflow上的Tensorflow社区更加活跃。
答案 1 :(得分：0)
在RNNClassifier：
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，您似乎将其创建为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')
...虽然我假设self._train_x和self.train_x之间的差异是复制粘贴错误，因为self._train_x似乎没有被定义其他任何地方。
现在，关于tf.train.batch()的一个令人惊讶的事情是它在一个完全独立的线程中消耗它的输入，称为＆＃34;队列运行器＆＃34;，并在你调用tf.train.start_queue_runners()时启动。该线程在依赖于占位符的子图上调用Session.run()，但不知道如何提供这些占位符，因此这次调用失败，导致您看到的错误。
你应该怎么解决它？一种选择是使用"feeding queue runner"，其中有实验支持。一个更简单的选择是使用tf.train.slice_input_producer()从输入数据生成切片，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)