类型错误：无法在 Seq2Seq 中腌制_thread.lock 对象

Question

我在Tensorflow模型中使用桶时遇到问题。当我用buckets = [(100, 100)]运行它时，它工作正常。当我用buckets = [(100, 100), (200, 200)]运行它时，它根本不起作用(底部的堆栈跟踪(。

有趣的是，运行Tensorflow的Seq2Seq教程给出了几乎相同的堆栈跟踪相同的问题。出于测试目的，此处提供了指向存储库的链接。

我不确定问题是什么，但拥有多个存储桶似乎总是会触发它。

此代码不能作为独立代码工作，但这是它崩溃的函数 - 请记住，将buckets从[(100, 100)]更改为[(100, 100), (200, 200)]会触发崩溃。

class MySeq2Seq(object):
def __init__(self, source_vocab_size, target_vocab_size, buckets, size, num_layers, batch_size, learning_rate):
self.source_vocab_size = source_vocab_size
self.target_vocab_size = target_vocab_size
self.buckets = buckets
self.batch_size = batch_size
cell = single_cell = tf.nn.rnn_cell.GRUCell(size)
if num_layers > 1:
cell = tf.nn.rnn_cell.MultiRNNCell([single_cell] * num_layers)
# The seq2seq function: we use embedding for the input and attention
def seq2seq_f(encoder_inputs, decoder_inputs, do_decode):
return tf.contrib.legacy_seq2seq.embedding_attention_seq2seq(
encoder_inputs, decoder_inputs, cell,
num_encoder_symbols=source_vocab_size,
num_decoder_symbols=target_vocab_size,
embedding_size=size,
feed_previous=do_decode)
# Feeds for inputs
self.encoder_inputs = []
self.decoder_inputs = []
self.target_weights = []
for i in range(buckets[-1][0]):
self.encoder_inputs.append(tf.placeholder(tf.int32, shape=[None], name="encoder{0}".format(i)))
for i in range(buckets[-1][1] + 1):
self.decoder_inputs.append(tf.placeholder(tf.int32, shape=[None], name="decoder{0}".format(i)))
self.target_weights.append(tf.placeholder(tf.float32, shape=[None], name="weight{0}".format(i)))
# Our targets are decoder inputs shifted by one
targets = [self.decoder_inputs[i + 1] for i in range(len(self.decoder_inputs) - 1)]
self.outputs, self.losses = tf.contrib.legacy_seq2seq.model_with_buckets(
self.encoder_inputs, self.decoder_inputs, targets,
self.target_weights, [(100, 100)],
lambda x, y: seq2seq_f(x, y, False))
# Gradients update operation for training the model
params = tf.trainable_variables()
self.updates = []
for b in range(len(buckets)):
self.updates.append(tf.train.AdamOptimizer(learning_rate).minimize(self.losses[b]))
self.saver = tf.train.Saver(tf.global_variables())

堆栈跟踪：

Traceback (most recent call last):
File "D:/Stuff/IdeaProjects/myproject/src/main.py", line 38, in <module>
model = predict.make_model(input_vocab_size, output_vocab_size, buckets, cell_size, model_layers, batch_size, learning_rate)
File "D:StuffIdeaProjectsmyprojectsrcpredictor.py", line 88, in make_model
size=cell_size, num_layers=model_layers, batch_size=batch_size, learning_rate=learning_rate)
File "D:StuffIdeaProjectsmyprojectsrcpredictor.py", line 45, in __init__
lambda x, y: seq2seq_f(x, y, False))
File "C:UsersuserAppDataLocalProgramsPythonPython36libsite-packagestensorflowcontriblegacy_seq2seqpythonopsseq2seq.py", line 1206, in model_with_buckets
decoder_inputs[:bucket[1]])
File "D:StuffIdeaProjectsmyprojectsrcpredictor.py", line 45, in <lambda>
lambda x, y: seq2seq_f(x, y, False))
File "D:StuffIdeaProjectsmyprojectsrcpredictor.py", line 28, in seq2seq_f
feed_previous=do_decode)
File "C:UsersuserAppDataLocalProgramsPythonPython36libsite-packagestensorflowcontriblegacy_seq2seqpythonopsseq2seq.py", line 848, in embedding_attention_seq2seq
encoder_cell = copy.deepcopy(cell)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 161, in deepcopy
y = copier(memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libsite-packagestensorflowpythonlayersbase.py", line 476, in __deepcopy__
setattr(result, k, copy.deepcopy(v, memo))
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 150, in deepcopy
y = copier(x, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 215, in _deepcopy_list
append(deepcopy(a, memo))
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 150, in deepcopy
y = copier(x, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 150, in deepcopy
y = copier(x, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 150, in deepcopy
y = copier(x, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 150, in deepcopy
y = copier(x, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "C:UsersuserAppDataLocalProgramsPythonPython36libcopy.py", line 169, in deepcopy
rv = reductor(4)
TypeError: can't pickle _thread.lock objects

Answer 1

问题出在seq2seq.py的最新变化上。将其添加到您的脚本中，它将避免对单元格进行深度处理：

setattr(tf.contrib.rnn.GRUCell, '__deepcopy__', lambda self, _: self)
setattr(tf.contrib.rnn.BasicLSTMCell, '__deepcopy__', lambda self, _: self)
setattr(tf.contrib.rnn.MultiRNNCell, '__deepcopy__', lambda self, _: self)

Answer 2

这两个解决方案对我有用：

在/yourpath/tensorflow/contrib/legacy_seq2seq/python/ops/下更改 seq2seq.py

#encoder_cell = copy.deepcopy(cell)
encoder_cell = core_rnn_cell.EmbeddingWrapper(
cell, #encoder_cell,

或

for nextBatch in tqdm(batches, desc="Training"):
_, step_loss = model.step(...)

一步进料一个桶