singa-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "wangwei (JIRA)" <j...@apache.org>
Subject [jira] [Created] (SINGA-91) Add SoftmaxLayer and ArgSortLayer
Date Thu, 15 Oct 2015 14:31:05 GMT
wangwei created SINGA-91:
----------------------------

             Summary: Add SoftmaxLayer and ArgSortLayer
                 Key: SINGA-91
                 URL: https://issues.apache.org/jira/browse/SINGA-91
             Project: Singa
          Issue Type: New Feature
            Reporter: wangwei


These two layers are added to get prediction results (e.g., predicted labels), which can be
output by CSVOutputLayer.

SoftmaxLayer applies the Softmax function against its source layer to compute its probability
distribution over all labels.

ArgSortLayer sorts labels based on their scores (e.g., probability) in descending order. It
has a configuration field *argsort_conf*,
{code}
message ArgSortProto {
optional int32 topk = 1 [default = 1];
}
{code}
Topk labels will be kept.
ArgSortLayer cannot be used in the training phase, because it does not implement the ComputeGradient
function. It is used merely for extracting prediction results. If it connects to a CSVOutputLayer,
then topk labels will be dumped into a csv file, topk labels per line.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message