search

lorenlugosch / neural-min-sum-decoding

Neural min-sum decoding in TensorFlow
Other
44 stars 22 forks source link

The NNMS case seems wrong #5

Closed Saitama1024 closed 1 year ago

Saitama1024 commented 1 year ago

Hi, Thanks for the code! I got a seemly right result when the decoder type is OMS. However, when the type is NNMS, I found that the decoding performance is terrible.

Here is the command I ran: python main.py 0 1 8 1 100 10000000000000000 5 BCH_63_36.alist BCH_63_36.gmat laskdjhf 0.5 100 FNNMS

And here are the terrible results: BERs: [0.1279322573687082, 0.10423613490160252, 0.08364134089553754, 0.06601353837564869, 0.05195795744356895, 0.04082400746069811, 0.03281945871873929, 0.027175561138390876] FERs: [0.9998800959232614, 0.9991207034372502, 0.9960531574740208, 0.9864908073541168, 0.9621203037569944, 0.9145283772981615, 0.8490007993605115, 0.7742106314948042]

Saitama1024 commented 1 year ago

Fortunately, the author has explained a problem simular to mine in issue #2. According to the issue, I turned L=0.5 into L=1 and finally got the right result of NNMS. Thanks again for the nice work!