* [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>
* Azure: Add Ninja
* Fix 'Install Ninja' on Linux
* Fix bin dir path on Windows
* Add -Wno-unused-variable on Mac
* Add -Wno-error=unused-command-line-argument on Mac
* Set CXXFLAGS for Mac
* Improvements
* Fix BIN_DIR on Linux
* [CPU] Updated DepthToSpace and SpaceToDepth layers to be conformant with the specification
The patch also includes n[d]hwc layout support as well as some optimizations
* [CPU][TESTS] Removed old DepthToSpace test since it doesn't corresponds to layer's specification
* [nGraph] Utilize CommonOptimizations pass with custom transformations callback
Implemented three operations: EmbeddingBagPackedSum,
EmbeddingBagOffsetsSum and EmbeddingSegmentsSum. These operations do
the same work but have a different format of inputs.
- change repo name to openvino
- update driver version
- fix path to samples data
- remove section about Movidius driver installation
- change latest release to 2020.3
- merge fixes in install_dependencies.sh from 2020 branch
adds fusing support to all available pooling kernels
tests all possible input type/output type configurations
fixes minor bug in max pooling in pooling_gpu_test.cpp
fixed minor bug with yxbf format in pooling_gpu_ref and pooling_gpu_int8_ref kernels
fixes bug with b_fs_yx_fsv32 format in pooling_gpu kernel
resolves bug with max pooling accuracy missmatch in case of non zero pad end layer parameter
resolves average pooling accuracy missmatch in case of non zero pad end layer parameter
The problem behind this error was in program_impl::init_graph() where in calculate_prior_boxes we are trying to calculate output layout of an entire network recursively which causes stack overflow. Calculating output layouts beforehand in processing order fixes this issue.
