James Reed 9aed89ac88 Allow specification of num_workers in PredictorExportMeta and enable for NMT beam search model ... Summary: The predictor export functions allowed a way to specify a net type, but no way to specify num_workers for when you use net type 'dag'. This adds that option to the PredictorExportMeta named tuple and populates the field in the exported protobuf. Also added parameters to callsites in NMT ensemble model class and model repackager to populate net_type and num_workers. Using DAGNet for our base predictor net (not recurrent stepnets) speeds up our inference by 1.15x, since we can now run encoder forward and backward RecurrentNet's for each model in the ensemble in parallel. Reviewed By: salexspb Differential Revision: D5792203 fbshipit-source-id: cb9a8237a0cbe1a09645d4de051dfbb23f06dcfa		2017-09-07 22:48:45 -07:00
..
mobile_exporter_test.py	Added mobile exporter	2017-05-24 11:36:44 -07:00
mobile_exporter.py	Small fix to exporter to accept net/NetDef both	2017-09-01 13:32:12 -07:00
predictor_exporter_test.py	Dict fixes/improvements and unittest targets for Python 3 in caffe2 core	2017-06-29 17:05:41 -07:00
predictor_exporter.py	Allow specification of num_workers in PredictorExportMeta and enable for NMT beam search model	2017-09-07 22:48:45 -07:00
predictor_py_utils.py	Allow specification of num_workers in PredictorExportMeta and enable for NMT beam search model	2017-09-07 22:48:45 -07:00
serde.py	Re-apply #266	2017-04-25 21:17:04 -07:00