projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 7203255) | patch
[nnc] Support for LSTM Caffe layer (#2721)
authorСергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 <s.barannikov@samsung.com>
Wed, 9 Jan 2019 16:01:01 +0000 (19:01 +0300)
committerРоман Михайлович Русяев/AI Tools Lab /SRR/Staff Engineer/삼성전자 <r.rusyaev@samsung.com>
Wed, 9 Jan 2019 16:01:01 +0000 (19:01 +0300)
commit55fb185c9804b3c5c090d146d6e60ea75aef864e
tree13ec76a09d39688553c599a0b5c50eaff300a796tree | snapshot
parent72032552b84d538809773dcd3e7c71b33617453dcommit | diff
[nnc] Support for LSTM Caffe layer (#2721)

* Add support for LSTM Caffe layer.
* Rename "SoftmaxLoss" Caffe layer to "SoftmaxWithLoss" as it should be.
* Add support for non-default axis for InnerProduct Caffe layer.

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
contrib/nnc/passes/caffe_frontend/caffe_importer.cpp diff | blob | history
contrib/nnc/passes/caffe_frontend/caffe_op_creator.cpp diff | blob | history
contrib/nnc/passes/caffe_frontend/caffe_op_creator.h diff | blob | history
contrib/nnc/passes/caffe_frontend/caffe_op_types.h diff | blob | history
contrib/nnc/unittests/caffe_frontend/unsupported_caffe_model.cpp diff | blob | history
Domain: Machine Learning / ML Framework;