[ https://issues.apache.org/jira/browse/SYSTEMML1678?page=com.atlassian.jira.plugin.system.issuetabpanels:alltabpanel
]
Mike Dusenberry updated SYSTEMML1678:

Description:
We should add new {{top_k}} and {{top_k2d}} utility functions (in {{nn/util.dml}}) that accept
a matrix {{X}} and return matrices {{values}} and {{indices}} with the top {{k}} values (i.e.
probabilities) and associated indices (i.e. classes) along a certain dimension. For the 1D
case, {{top_k}} will operate on the columns dimension. A typical use case is that in which
{{X}} is the output of a {{softmax}} layer (so each row contains a set of normalized class
probabilities), and {{values}} and {{indices}} will contain rows with the top {{k}} probabilities
and class indices as described above. For the 2D case, {{top_k}} will operate on the channels
dimension. A typical use case here is that in which {{X}} is the output of a {{softmax2d}}
layer (so each channel contains a set of normalized class probabilities), and {{values}} and
{{indices}} will contain the top {{k}} probabilities and indices along the channel axis.
This scenario would be common in an image segmentation problem, in which every pixel of the
output image will have a set of class probabilities along the channel axis.
Having these {{topk}} functions will allow us to extract either predict a single class for
each item, or the top {{k}} classes, and therefore may be more useful that a {{predict_class}}
function.
was:We should add new {{predict_class}} and {{predict_class2d}} utility functions (in {{nn/util.dml}})
that accept a matrix {{X}} and return a matrix {{out}} with the predicted classes based on
the max probability. For the 1D case, {{X}} is the output of a {{softmax}} layer, and thus
each row will contain a set of normalized class probabilities
> Add new 1D & 2D top_k utility functions
> 
>
> Key: SYSTEMML1678
> URL: https://issues.apache.org/jira/browse/SYSTEMML1678
> Project: SystemML
> Issue Type: Subtask
> Reporter: Mike Dusenberry
> Assignee: Mike Dusenberry
>
> We should add new {{top_k}} and {{top_k2d}} utility functions (in {{nn/util.dml}}) that
accept a matrix {{X}} and return matrices {{values}} and {{indices}} with the top {{k}} values
(i.e. probabilities) and associated indices (i.e. classes) along a certain dimension. For
the 1D case, {{top_k}} will operate on the columns dimension. A typical use case is that
in which {{X}} is the output of a {{softmax}} layer (so each row contains a set of normalized
class probabilities), and {{values}} and {{indices}} will contain rows with the top {{k}}
probabilities and class indices as described above. For the 2D case, {{top_k}} will operate
on the channels dimension. A typical use case here is that in which {{X}} is the output of
a {{softmax2d}} layer (so each channel contains a set of normalized class probabilities),
and {{values}} and {{indices}} will contain the top {{k}} probabilities and indices along
the channel axis. This scenario would be common in an image segmentation problem, in which
every pixel of the output image will have a set of class probabilities along the channel axis.
> Having these {{topk}} functions will allow us to extract either predict a single class
for each item, or the top {{k}} classes, and therefore may be more useful that a {{predict_class}}
function.

This message was sent by Atlassian JIRA
(v6.4.14#64029)
