J'ai du mal à utiliser des godets dans mon modèle Tensorflow. Lorsque je l'exécute avec buckets = [(100, 100)]
, cela fonctionne très bien. Quand je l'exécute avec buckets = [(100, 100), (200, 200)]
cela ne fonctionne pas du tout (stacktrace en bas).
Fait intéressant, l'exécution du didacticiel Seq2Seq de Tensorflow donne le même type de problème avec une trace de pile presque identique. À des fins de test, le lien vers le référentiel est ici .
Je ne sais pas quel est le problème, mais avoir plus d'un compartiment semble toujours le déclencher.
Ce code ne fonctionnera pas de manière autonome, mais c'est la fonction où il plante - rappelez-vous que le changement de buckets
de [(100, 100)]
à [(100, 100), (200, 200)]
déclenche le crash.
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())
Trace de la pile:
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:\Stuff\IdeaProjects\myproject\src\predictor.py", line 88, in make_model
size=cell_size, num_layers=model_layers, batch_size=batch_size, learning_rate=learning_rate)
File "D:\Stuff\IdeaProjects\myproject\src\predictor.py", line 45, in __init__
lambda x, y: seq2seq_f(x, y, False))
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\contrib\legacy_seq2seq\python\ops\seq2seq.py", line 1206, in model_with_buckets
decoder_inputs[:bucket[1]])
File "D:\Stuff\IdeaProjects\myproject\src\predictor.py", line 45, in <lambda>
lambda x, y: seq2seq_f(x, y, False))
File "D:\Stuff\IdeaProjects\myproject\src\predictor.py", line 28, in seq2seq_f
feed_previous=do_decode)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\contrib\legacy_seq2seq\python\ops\seq2seq.py", line 848, in embedding_attention_seq2seq
encoder_cell = copy.deepcopy(cell)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 161, in deepcopy
y = copier(memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\layers\base.py", line 476, in __deepcopy__
setattr(result, k, copy.deepcopy(v, memo))
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 150, in deepcopy
y = copier(x, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 215, in _deepcopy_list
append(deepcopy(a, memo))
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 150, in deepcopy
y = copier(x, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 150, in deepcopy
y = copier(x, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 150, in deepcopy
y = copier(x, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 150, in deepcopy
y = copier(x, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\copy.py", line 169, in deepcopy
rv = reductor(4)
TypeError: can't pickle _thread.lock objects
Le problème vient des dernières modifications de seq2seq.py
. Ajoutez ceci à votre script et cela évitera un coping profond des cellules:
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)
Cette solution ne fonctionne pas pour moi. Une nouvelle solution?
Ces deux solutions fonctionnent pour moi:
changez seq2seq.py sous/yourpath/tensorflow/contrib/legacy_seq2seq/python/ops /
#encoder_cell = copy.deepcopy(cell)
encoder_cell = core_rnn_cell.EmbeddingWrapper(
cell, #encoder_cell,
ou
for nextBatch in tqdm(batches, desc="Training"):
_, step_loss = model.step(...)
nourri un seau à la fois