zpppy / seq2seq-chinese-textsum Goto Github PK

@zpppy 博客地址打不开 可否写入readme.md 或者给个其他链接～～

作者您好，请问程序报TypeError: object.new(NotImplementedType) is not safe, use NotImplementedType.new()这个错误，是因为版本问题还是gpu的问题？

Traceback (most recent call last):
File "headline.py", line 255, in
tf.app.run()
File "/home/lyy/anaconda3/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "headline.py", line 252, in main
train()
File "headline.py", line 173, in train
model = create_model(sess, False)
File "headline.py", line 147, in create_model
forward_only=forward_only)
File "/data/NLP_projects/textsum_projects/seq2seq-chinese-textsum/seq2seq_model.py", line 180, in init
softmax_loss_function=softmax_loss_function)
File "/home/lyy/anaconda3/lib/python3.6/site-packages/tensorflow/contrib/legacy_seq2seq/python/ops/seq2seq.py", line 1215, in model_with_buckets
decoder_inputs[:bucket[1]])
File "/data/NLP_projects/textsum_projects/seq2seq-chinese-textsum/seq2seq_model.py", line 179, in
lambda x, y: seq2seq_f(x, y, False),
File "/data/NLP_projects/textsum_projects/seq2seq-chinese-textsum/seq2seq_model.py", line 140, in seq2seq_f
dtype=dtype)
File "/home/lyy/anaconda3/lib/python3.6/site-packages/tensorflow/contrib/legacy_seq2seq/python/ops/seq2seq.py", line 857, in embedding_attention_seq2seq
encoder_cell = copy.deepcopy(cell)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 161, in deepcopy
y = copier(memo)
File "/home/lyy/anaconda3/lib/python3.6/site-packages/tensorflow/python/layers/base.py", line 385, in deepcopy
setattr(result, k, copy.deepcopy(v, memo))
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 215, in _deepcopy_list
append(deepcopy(a, memo))
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/home/lyy/anaconda3/lib/python3.6/copy.py", line 169, in deepcopy
rv = reductor(4)
TypeError: can't pickle _thread.RLock objects

大神还有别的博客地址吗

有没有大神的博客地址？？

你好，非常高兴砍刀您的代码，获益很多。我再运行的时候，提示找不到eval模块，eval应该是python的内建函数吧？麻烦您能给一下指导吗？

您好，我运行您的代码时，运行到 model = create_model(sess, False)时，create函数调用seq2seq_model模块时，报错'NoneType' object has no attribute 'update'。我目前没有找到原因，猜想会不会是tensorflow版本的问题，想问一下您用的tensorflow是哪个版本的？或者，您是否知道这个错误的解决方案。谢谢！！！