search

tjuxiaofeng / A-Model-Driven-Deep-Learning-Method-for-Normalized-Min-Sum-LDPC-Decoding

GNU General Public License v3.0
24 stars 6 forks source link

Error running with provided LDPC code #2

Open mlscsdn opened 1 year ago

mlscsdn commented 1 year ago

使用提供的LDPC码运行出错，大概是某个tensorflow向量维度不一致的错误。而当我使用BCH码或汉明码时成功运行。 There is an error when running with the provided LDPC code, probably because of an inconsistent tensorflow vector dimension. And when I use BCH code or Hamming code it runs successfully. `Traceback (most recent call last):

File "C:/Users/admin/Downloads/A-Model-Driven-Deep-Learning-Method-for-Normalized-Min-Sum-LDPC-Decoding-master/main.py", line 435, in feed_dict=feed_dict) # ,bp_output,syndrome_output,belief_propagation, soft_syndromes

File "F:\anaconda3\envs\TF2.1\lib\site-packages\tensorflow_core\python\client\session.py", line 960, in run run_metadata_ptr)

File "F:\anaconda3\envs\TF2.1\lib\site-packages\tensorflow_core\python\client\session.py", line 1183, in _run feed_dict_tensor, options, run_metadata)

File "F:\anaconda3\envs\TF2.1\lib\site-packages\tensorflow_core\python\client\session.py", line 1361, in _do_run run_metadata)

File "F:\anaconda3\envs\TF2.1\lib\site-packages\tensorflow_core\python\client\session.py", line 1386, in _do_call raise type(e)(node_def, op, message)

tensorflow.python.framework.errors_impl.AlreadyExistsError: Resource __per_step_2/gradients/AddN_2/tmp_var/struct tensorflow::TemporaryVariableOp::TmpVar [[{{node gradients/AddN_2/tmp_var}}]]`

thefirstqi commented 1 year ago

请问你使用的tensorflow和python是什么版本的呢

mlscsdn commented 1 year ago

请问你使用的tensorflow和python是什么版本的呢

tensorflow 2.1 + python 3.7. 这个代码并不灵活，换另一个LDPC码后就出错了。错误大概是在BP算法中计算节点之间传递的信息时出错。

thefirstqi commented 1 year ago

好的好的，我研究下他怎么计算的