Hi Prashant

The core features are the "dense" features, stored in a fixed length array. The 
m_features data structure contains the "sparse" features, stored in a map,

Cheers - Barry

Prashant Mathur <[email protected]> wrote:

>Hi Lane,
>
>There is a function called GetSparseWeight(const FName& featureName), 
>maybe it will help, I haven't used it though.
>
>I had one more question
>In Feature Vector class,
>What is the difference between features(m_features) and core features 
>(m_coreFeatures)?
>
>Thanks,
>--
>Prashant
>
>
>On 02/19/2013 06:16 PM, Lane Schwartz wrote:
>> Hi,
>>
>> I'm writing some code where I'd like to extract and print the feature
>> values for each hypothesis. I've run into some trouble in doing this.
>>
>> const Hypothesis* hypo
>> const FeatureFunction* ff
>>
>> Given the above, I can successfully get the hypo to print its information:
>>
>> out<<  hypo;
>>
>> But if I try to extract the features for the given feature function,
>> all of the returned values are always zero:
>>
>> out<<  (hypo->GetScoreBreakdown().GetVectorForProducer(ff));
>>
>> How can I get the feature values for a particular feature function at
>> a hypothesis?
>>
>> Thanks,
>> Lane
>> _______________________________________________
>> Moses-support mailing list
>> [email protected]
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>
>_______________________________________________
>Moses-support mailing list
>[email protected]
>http://mailman.mit.edu/mailman/listinfo/moses-support
>

-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.


_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to