njayaram2 opened a new pull request #377: DL: Do not compile params in predict and add gpu support URL: https://github.com/apache/madlib/pull/377 JIRA: MADLIB-1330 Do not compile params in predict, but instead directly get the model weights and architecture and use it for prediction. Compiling params during predict is not necessary from Keras 1.0.3. Add an optional parameter named use_gpu in predict interface which is set to TRUE by default. If use_gpu is true, then GPU support on predict is enabled.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
