[
https://issues.apache.org/jira/browse/SYSTEMML-1076?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Mike Dusenberry updated SYSTEMML-1076:
--------------------------------------
Description:
Currently, our max pooling built-in operator does not support sparse matrices.
However, sparse matrices are a common possibility in neural nets that make use
of ReLU and Dropout layers, and are likely to happen at random depending on
exact characteristics of intermediate matrices during training. Therefore, we
should accept sparse matrices as input.
{code}
Caused by: org.apache.sysml.runtime.DMLRuntimeException: Sparse
maxpooling_backward is not supported
at
org.apache.sysml.runtime.matrix.data.LibMatrixDNN.maxpooling_backward(LibMatrixDNN.java:526)
at
org.apache.sysml.runtime.instructions.cp.ConvolutionCPInstruction.processInstruction(ConvolutionCPInstruction.java:205)
at
org.apache.sysml.runtime.controlprogram.ProgramBlock.executeSingleInstruction(ProgramBlock.java:305)
... 26 more
{code}
was:
Currently, our max pooling built-in operator does not support sparse matrices.
However, sparse matrices are a common possibility in neural nets that make use
of ReLU and Dropout layers. Therefore, we should accept sparse matrices as
input.
{code}
Caused by: org.apache.sysml.runtime.DMLRuntimeException: Sparse
maxpooling_backward is not supported
at
org.apache.sysml.runtime.matrix.data.LibMatrixDNN.maxpooling_backward(LibMatrixDNN.java:526)
at
org.apache.sysml.runtime.instructions.cp.ConvolutionCPInstruction.processInstruction(ConvolutionCPInstruction.java:205)
at
org.apache.sysml.runtime.controlprogram.ProgramBlock.executeSingleInstruction(ProgramBlock.java:305)
... 26 more
{code}
> Sparse Max Pooling Unsupported
> ------------------------------
>
> Key: SYSTEMML-1076
> URL: https://issues.apache.org/jira/browse/SYSTEMML-1076
> Project: SystemML
> Issue Type: Bug
> Reporter: Mike Dusenberry
>
> Currently, our max pooling built-in operator does not support sparse
> matrices. However, sparse matrices are a common possibility in neural nets
> that make use of ReLU and Dropout layers, and are likely to happen at random
> depending on exact characteristics of intermediate matrices during training.
> Therefore, we should accept sparse matrices as input.
> {code}
> Caused by: org.apache.sysml.runtime.DMLRuntimeException: Sparse
> maxpooling_backward is not supported
> at
> org.apache.sysml.runtime.matrix.data.LibMatrixDNN.maxpooling_backward(LibMatrixDNN.java:526)
> at
> org.apache.sysml.runtime.instructions.cp.ConvolutionCPInstruction.processInstruction(ConvolutionCPInstruction.java:205)
> at
> org.apache.sysml.runtime.controlprogram.ProgramBlock.executeSingleInstruction(ProgramBlock.java:305)
> ... 26 more
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
