关于项目的运行

[17385]

我在命令行输入：python run.py HS-B 运行您的代码的时出现错误：
InvalidArgumentError (see above for traceback): indices[29,26,0] = 292 is not in [0, 292)
[[node embedding_lookup_6 (defined at E:\TreeGen-master\code_generate_model.py:677) ]]

code_generate_model.py中
new_m = common_layers.cast_like(new_m, var)报错 Unresolved reference 'common_layers'

（依赖包已经全部装好，我的使用的系统环境是win10。）
想请问您如何解决这个问题，并完整运行整个项目。

[zysszy]

您好，
求问一下详细的报错，我这边运行是没有错误的。
谢谢～

[17385]

详细的报错：
raceback (most recent call last):
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1334, in _do_call
return fn(*args)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1319, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1407, in _call_tf_session
run
run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[22,26,0] = 292 is not in [0, 292)
[[{{node embedding_lookup_6}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "run.py", line 302, in
main()
File "run.py", line 300, in main
run()
File "run.py", line 245, in run
ac1, loss1, _ = g_eval(sess, Code_gen_model, valid_batch[k])
File "run.py", line 207, in g_eval
model.is_train: False
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 929, in run
run_metadata_ptr)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1152, in _run
feed_dict_tensor, options, run_metadata)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1328, in _do_run
run_metadata)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1348, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[22,26,0] = 292 is not in [0, 292)
[[node embedding_lookup_6 (defined at E:\TreeGen-master\code_generate_model.py:677) ]]

Caused by op 'embedding_lookup_6', defined at:
File "run.py", line 302, in
main()
File "run.py", line 300, in main
run()
File "run.py", line 225, in run
batch_size, NL_vocabu_size, Tree_vocabu_size, NL_len, Tree_len, parent_len, learning_rate, keep_prob, len(char_vocabulary), rules_l
en)
File "E:\TreeGen-master\code_generate_model.py", line 677, in init
em_Rule_Son = tf.nn.embedding_lookup(self.Tree_embedding, self.inputrulelistson)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\embedding_ops.py", line 316, in embedding_look
up
transform_fn=None)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\embedding_ops.py", line 133, in _embedding_loo
kup_and_transform
result = _clip(array_ops.gather(params[0], ids, name=name),
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\util\dispatch.py", line 180, in wrapper
return target(*args, **kwargs)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\array_ops.py", line 3273, in gather
return gen_array_ops.gather_v2(params, indices, axis, name=name)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 4390, in gather_v2
"GatherV2", params=params, indices=indices, axis=axis, name=name)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 788, in apply
op_helper
op_def=op_def)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\util\deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py", line 3300, in create_op
op_def=op_def)
File "C:\Users\17385\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py", line 1801, in init
self._traceback = tf_stack.extract_stack()

InvalidArgumentError (see above for traceback): indices[22,26,0] = 292 is not in [0, 292)
[[node embedding_lookup_6 (defined at E:\TreeGen-master\code_generate_model.py:677) ]]

但是我修改run.py中的Tree_vocabu_size = len(tree_vocabulary)+1 #len(tree_vocabulary)后，训练可以继续下去了，这样可以吗？
谢谢您回答我的问题。

[zysszy]

如果训练可以继续，那便是可以的～
我这边再查一下bug，谢谢您的关注～
Zeyu

[boyang9602]

请问关于这个问题有什么进展吗？我也遇到了同样的问题，我觉得是tree的vocabulary有292个，所以embedding取值应该是0-291，但是不知什么原因，代码里某处要给某个矩阵位置赋一个为292的值，所以出现了这个问题。

[boyang9602]

我的环境是python3.6, tensorflow1.12.0, ubuntu20.04, NLTK3.2.1

[boyang9602]

您好，我找到问题了，reslove_data.py的第87行，tree_vocabulary["End"] = len(tree_vocabulary)导致End的值为tree vocabulary的长度(292)，超出了取值范围，我注释掉这一行就不会报这个错了。请问这行有什么特殊的用途吗？可以删掉吗？

[zysszy]

您好，我找到问题了，reslove_data.py的第87行，tree_vocabulary["End"] = len(tree_vocabulary)导致End的值为tree vocabulary的长度(292)，超出了取值范围，我注释掉这一行就不会报这个错了。请问这行有什么特殊的用途吗？可以删掉吗？

您好，谢谢您，您这个修改应该是对的 （虽然我不知道我为什么可以训练，但是我看了数据，我觉得您的修改没问题，直接把这行注释了吧，ATIS我看了数据应该需要这一行）。

感谢您的关注～

Zeyu