Commit Graph

21 Commits

Author SHA1 Message Date
Evgeny Lazarev
970b1301b5 Cleanup IR v7 from the MO (#1008)
* Removed back phase transformations related to IRv7

* Fixed setting value for the input port using the 'set_value' method

* Removed front and middle phase transformations related to IRv7

* Cleanup the rest of the Model Optimizer transformations from IRv7 specific transformations

* Final cleanup of the deprecated IR v7 related code

* Removed 'blobs_as_input' usage in the Model Optimizer.

* Removed function '_fuse_add' from the Model Optimizer since it is not used anymore.

* Removed 'keep_in_IR' node attribute for FakeQuantize ops in the MO

* Disabled failing gpu_engine.user_context test
2020-06-22 11:52:00 +03:00
Maxim Vafin
f1811ad060 Implement support for opset3 EmbeddingBag ops (#546)
* [MO] Implement EmbeddingBag_3

* Transform dynamic sub-graph of Wide and Deep into EmbeddingSegmentsSum

- Expressed SparseWeightedSum sub-graph through EmbeddingSegmentsSum
- Removed experimental SparseWeightedSum layer
- Implemented tests for the transformation

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Fix EmbeddingBag shape infer

* Fix EmbeddingSegmentsSum transformation for Wide and Deep

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Fix EmbeddingSegmentSum replacer after ports swap

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Update package_BOM.txt

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Add unit tests for EmbeddingXXX shape infer

* Fix ATen resolver

* Remove deleted files from BOM

* Add opset version to embedding_bag

* Use base class for EmbeddingBag

* Fix per_sample_weights case

* Fix EmbeddingSegmentsSum transformation

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Fix EmbeddingBag checks

* Fix ATen front transformation and merge conflicts

* Fix BOM

* Work around limitation for I64 input of W&D model

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Cleanup where operation to fix affect of WhereDecomposition transform

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Fix BOM

* Correct EmbeddingSegmentSum transform for Wide and Deep

Add casting segment ids to i32 and remove ConstToResult sub-graph.

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Update BOM with RemoveConstToResult transform

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Add more comments for RemoveConstToResult transformation

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Remove useless logging in EmbeddingSegmentsSum transformation

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Small fixes

* Move EmbeddingBag resolving back to front phase

* Improve error messages

* Fix typo in unittests

* Reimplement sparse_reshape middle transform

Avoid deprecated API.

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Clean-up graph after sparse_reshape and ConstToResult transformation

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Fix clean-up for transformations

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Fix clean-up for transformation #2

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2020-06-08 18:06:40 +03:00
Maxim Vafin
c7d130efbe Fix Proposal for the case of 2 outputs (#773) 2020-06-04 20:56:46 +03:00
Evgenya Stepyreva
01e60d057d [ MO ] InterpolateConcat empty sources fix (#764) 2020-06-04 14:18:33 +03:00
Anton Chetverikov
265e3c7cba Remove TopKnormalizer from MO IR Reader transformation_list (#590)
* Remove TopKnormalizer from transformation_list and added call of normalize_outputs to fix read/save of some models
2020-06-02 12:43:41 +03:00
Evgenya Stepyreva
e290b14ab1 [ MO Interpolate ] Fixing broken model reshape-ability (#619) 2020-05-29 09:15:47 +03:00
Maxim Vafin
8c8629a4af Support ONNX Clamp-11 (#538) 2020-05-25 19:59:07 +03:00
Alexey Suhov
ccb7438803 publish master branch snapshot, revision ea98a886d925eb152931aab13856e68037665562 2020-05-22 03:42:00 +03:00
Alexey Suhov
ba0a339888 publish master branch snapshot, revision 59af1853ca21ea08acf17b177da0b239753deb46 2020-05-18 17:21:58 +03:00
Alexey Suhov
5b428f0655 publish master branch snapshot, revision 49482ae3bea0cbaa07474f86f36db11943142687 2020-05-13 21:12:22 +03:00
Alexey Suhov
357cc7eb4c publish master branch snapshot, revision 0110d9c98fd7209589d06344f0d836f61d81f4b3 2020-04-27 21:21:29 +03:00
Alexey Suhov
127cbac5bc publish master branch snapshot, revision cdcab9d7ab48ffb0ee5629fabbfa06cb45debd9b 2020-04-15 19:01:57 +03:00
Alexey Suhov
95a57795dc Publishing 2020.2 content 2020-04-13 21:17:23 +03:00
Alexey Suhov
b2140c083a Publishing 2020.1 content 2020-02-11 22:48:49 +03:00
Alexey Suhov
0923303e02 Publishing 2019 R3 content 2019-10-04 19:26:43 +03:00
Alexey Suhov
ba6e22b1b5 Publishing 2019 R2 content (#223) 2019-08-09 19:02:42 +03:00
Alexey Suhov
72660e9a4d Publishing 2019 R1 content 2019-04-12 18:25:53 +03:00
Alexey Suhov
17e66dc5a6 Added unit tests and readme for model optimizer (#79)
* added unit tests
* added readme for model optimizer
* added a list of supported IE plugins
2019-01-23 20:23:27 +03:00
Alexey Suhov
9de27f16bc Publishing R5 content (#72)
* Publishing R5 content

* Updated ade revision

* updated readme

* add possibility to build CPU plugin with Intel MKL package
2019-01-21 21:31:31 +03:00
Alexey Suhov
55a41d7570 Publishing R4 (#41)
* Publishing R4
2018-11-23 16:19:43 +03:00
openvino-pushbot
866530fb04 Publishing R3 2018-10-16 13:45:03 +03:00