projects / platform / upstream / dldt.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 18f0486) | patch
ONNX LSTM fix get_shape error (#3033)
authorKatarzyna Mitrus <katarzyna.mitrus@intel.com>
Fri, 13 Nov 2020 14:31:29 +0000 (15:31 +0100)
committerGitHub <noreply@github.com>
Fri, 13 Nov 2020 14:31:29 +0000 (17:31 +0300)
commit8dbff709fbf2b135b0d35deccb16ca97433581f6
tree6cf40248f9172239b59f2d9e130f6f92977c1833tree | snapshot
parent18f04860afe1b7305c66c254873dfad85d54eea3commit | diff
ONNX LSTM fix get_shape error (#3033)

* ONNX LSTM get dimension only if required

* Test dynamic onnx lstm model import

* Enable LSTM_Seq_lens_unpacked_model import test

* Disable model zoo execution test "MSFT_opset9_LSTM_Seq_lens_unpacked"

* Add missed comma in xfail list

* Update error messages

* init xfail issue

* test zoo models import xfail issue

* Fix SEQ_LENGTH init

* Comments update

* Fix usage of v0::Add by overloaded operator
ngraph/frontend/onnx_import/src/op/lstm.cpp diff | blob | history
ngraph/python/tests/__init__.py diff | blob | history
ngraph/python/tests/test_onnx/test_zoo_models.py diff | blob | history
ngraph/test/models/onnx/dynamic_shapes/lstm_dyn_batch_seq.prototxt [new file with mode: 0644] blob
ngraph/test/onnx/onnx_import_rnn.in.cpp diff | blob | history
Domain: Machine Learning / ML Framework;