pytorch/caffe2/python/predictor
Andrey Malevich 6c12df3003 Fix export of SparseToDense layer.
Summary:
If there're 2 SparseToDense layers that are densifying same IdList feature
it'll result in the situation, where we might export invalid input for the
prediction in input specs. This diff is changing the behavior to support to use
Alias to a new blob instead of passing things directly.

Reviewed By: dzhulgakov

Differential Revision: D5093754

fbshipit-source-id: ef4fa4ac3722331d6e72716bd0c6363b3a629cf7
2017-05-25 21:46:28 -07:00
..
mobile_exporter_test.py Added mobile exporter 2017-05-24 11:36:44 -07:00
mobile_exporter.py Added mobile exporter 2017-05-24 11:36:44 -07:00
predictor_exporter_test.py Allow specifying net type in predictor_exporter 2017-05-24 11:46:27 -07:00
predictor_exporter.py Fix export of SparseToDense layer. 2017-05-25 21:46:28 -07:00
predictor_py_utils.py Allow specifying net type in predictor_exporter 2017-05-24 11:46:27 -07:00
serde.py Re-apply #266 2017-04-25 21:17:04 -07:00