[ https://issues.apache.org/jira/browse/APEXMALHAR-2260?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16204841#comment-16204841 ]
Ananth edited comment on APEXMALHAR-2260 at 10/14/17 10:30 PM: --------------------------------------------------------------- *Tensorflow integration with Keras* as the wrapper gave the following readings: - 2012 Macbook Pro (2.6 GHz Intel Core i7 with 16GB RAM), No GPU was enabled for either modelling or scoring - The model was to perform MNIST digit recognition - The source code for the modelling and the binary version of the model can be located in the resources folder of the git project ( link in the second comment ) - *Readings in microseconds* Result "github.ananthc.sampleapps.apex.keras.KerasMnistJepBenchMark.testMNISTKerasWithTF": *1694.491 ±(99.9%) 25.518 us/op [Average]* (min, avg, max) = (1615.805, 1694.491, 2127.963), stdev = 108.046 CI (99.9%): [1668.973, 1720.009] (assumes normal distribution) # Run complete. Total time: 00:08:31 Benchmark Mode Cnt Score Error Units KerasMnistJepBenchMark.testMNISTKerasWithTF avgt 200 1694.491 ± 25.518 us/op was (Author: ananthg.apex): *Tensorflow integration with Keras* as the wrapper gave the following readings: - 2012 Macbook Pro (2.6 GHz Intel Core i7 with 16GB RAM), No GPU was enabled for either modelling or scoring - The model was to perform MNIST digit recognition - The source code for the modelling and the binary version of the model can be located in the resources model - *Readings in microseconds* Result "github.ananthc.sampleapps.apex.keras.KerasMnistJepBenchMark.testMNISTKerasWithTF": *1694.491 ±(99.9%) 25.518 us/op [Average]* (min, avg, max) = (1615.805, 1694.491, 2127.963), stdev = 108.046 CI (99.9%): [1668.973, 1720.009] (assumes normal distribution) # Run complete. Total time: 00:08:31 Benchmark Mode Cnt Score Error Units KerasMnistJepBenchMark.testMNISTKerasWithTF avgt 200 1694.491 ± 25.518 us/op > Python execution for operator logic > ------------------------------------ > > Key: APEXMALHAR-2260 > URL: https://issues.apache.org/jira/browse/APEXMALHAR-2260 > Project: Apache Apex Malhar > Issue Type: New Feature > Reporter: Thomas Weise > Assignee: Ananth > Labels: roadmap > > Support execution of Python code in an operator. > https://lists.apache.org/thread.html/9837b1dee8f909ed400c6030ce5c6a94a12f43183718019dd0bfd228@%3Cdev.apex.apache.org%3E -- This message was sent by Atlassian JIRA (v6.4.14#64029)