singa-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "ASF subversion and git services (JIRA)" <>
Subject [jira] [Commented] (SINGA-91) Add SoftmaxLayer and ArgSortLayer
Date Sun, 18 Oct 2015 14:48:05 GMT


ASF subversion and git services commented on SINGA-91:

Commit 0a228c8ccd44a95c58ae0a661966f7acbed2c11d in incubator-singa's branch refs/heads/master
from wang sheng
[;h=0a228c8 ]

SINGA-91 - Add SoftmaxLayer and ArgSortLayer

cpplint checked
make documentation in job.conf more clear

> Add SoftmaxLayer and ArgSortLayer
> ---------------------------------
>                 Key: SINGA-91
>                 URL:
>             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

View raw message