1. 05 Dec, 2019 1 commit
  2. 02 Dec, 2019 3 commits
    • Yimei Sun's avatar
      3d1335fe
    • Mateusz Bencer's avatar
      [SPEC] Adjust Split (#3943) · 371b47fb
      Mateusz Bencer authored
      * Changed axis to Node
      
      * Added using normalize from validation util
      
      * refactored split
      
      * Added typrop tests to Split
      
      * Added set_input_is_relevant_to_shape for Split
      
      * clang style applied
      
      * Fixed var name
      
      * Code refactor
      
      * mergre from master. part.2
      
      * Constructor to provide CI compatibility
      
      * CI compatibility
      
      * CI compatibility
      
      * Updated get_outputs
      
      * CI compitability
      
      * Fixed get_outputs function
      371b47fb
    • Pruthvi's avatar
      Relax check on LRN for rank requirement to be >=3 (#3952) · f2a8f6e5
      Pruthvi authored
      *  relax check for LRN for requirement rank should be >=3
      
      * rename unit test names
      
      * - Disable lrn unit test with axes for CPU backend
      
      * remove outdated unit test on rank requirement from type_prop
      
      * - disable newly added lrn unit test in plaidMl
      f2a8f6e5
  3. 01 Dec, 2019 2 commits
  4. 28 Nov, 2019 2 commits
    • Tomasz Socha's avatar
      [SPEC] Adjust ConvolutionBackpropData op. (#3935) · 8f999289
      Tomasz Socha authored
      * [SPEC] Adjust ConvolutionBackpropData op.
      
      ```
      inputs:
        1. filters-------+
        2. output_delta  |  -> 1. data
                         +---> 2. filters
        3. data_batch_shape -> 3. output_shape(+optional)
      
      attributes:
        1. strides          -> 1. strides
        2. dilations-----+
        3. pads_begin    |  -> 2. pads_begin
        4. pads_end      |  -> 3. pads_end
                         +---> 4. dilations
      		      -> 5. +auto_pad(optional)[PadType::EXPLICIT]
      		      -> 6. +output_padding(optional)[zeros]
      ```
      
      * Review fix I
      8f999289
    • Mateusz Bencer's avatar
      [SPEC] Add negative axes support for ReverseSequence (#3926) · f3603647
      Mateusz Bencer authored
      * Added negative axes support for ReverseRequence
      
      * code review remarks introduced
      
      * Disable reverse sequence for PlaidMl tests
      
      * Fixed styles
      
      * Fixed axes assignment
      
      * Fixed normalized axes assignment
      f3603647
  5. 26 Nov, 2019 1 commit
    • Pruthvi's avatar
      Cumulative Sum (#3873) · 77a99b30
      Pruthvi authored
      * - Op defination for cummalative sum
      
      * WIP reference kernel for cummulative sum
      
      * - unit test case for default cum_sum
      - addition ctor for cumsum to accept axis as a integer insted of Node
      type
      - style fix
      
      * - add serializer support
      - fix failing unit test case
      - update Op in the interpreter dispatcher
      
      * - CPU builder and DEX support for CumSum
      
      * - implemented mapping tensor elements to corrosponding axis
      
      * - unit test for multiple dims
      - fix axis in the op defination
      - support for reference kernel to compute across all axis
      
      * - added support for exclusive and reverse modes
      - more unit test case for all modes
      
      * - codegen support for CumSum
      - disable CumSum unit test for PlaidML
      
      * -Add missing header to  codegen stream writer
      
      * fixed codegen writer
      
      * change return type of exclusive and reverse to bool
      
      * - support for dynamic shape
      - support to handle all tensor types in CPU builder
      
      * - add support for interpreter to handle different axis types
      
      * Style fix
      77a99b30
  6. 25 Nov, 2019 1 commit
  7. 22 Nov, 2019 3 commits
    • Tomasz Dołbniak's avatar
      [SPEC] HardSigmoid adjustments (#3857) · 28a96f83
      Tomasz Dołbniak authored
      * Construct HardSigmoid with alpha and beta as inputs
      
      * Switch to the new HardSigmoid constructor entirely
      
      * Broadcast with numpy style in hard sigmoid
      
      * Python bindings adjustment to the new constructor
      
      * Different way of creating constants
      
      * Accept scalars instead of 1D vectors for alpha and beta
      
      * Adjust the python tests to the new HardSigmoid constructor
      
      * Use v1 ops in fused HardSigmoid
      
      * Relax the static shape requirement for alpha and beta
      
      * Fix merge
      28a96f83
    • Robert Kimball's avatar
      16e256fa
    • gaurides's avatar
      Fused_op: BatchMatMulTranspose (#3871) · db5b11c8
      gaurides authored
      * Initial commit
      
      * Add decompose_op and unit-test
      
      * Style fix
      
      * Fix CI error
      
      * Address review comments
      
      * Remove CPUBatchFusion
      
      * Address review feedback
      
      * Address review feedback
      
      * Added type_prop tests
      
      * Moved 1 test from cpu to core to keep together
      
      * Address PR comments
      
      * Fix style
      db5b11c8
  8. 20 Nov, 2019 1 commit
    • Pruthvi's avatar
      Implementation of CrossEntropy and CrossEntropyBackprop as fused Op's (#3818) · a1a8a7e3
      Pruthvi authored
      * - Implementaion of CrossEntropy and CrossEntropyBackprop as fused Op's
      
      * - unit test case for CE fprop
      - fix bug in decompose_op
      
      * WIP debug PDPD unit test failure
      
      * fixed broadcasting issue
      
      * -fix bdcast issue for multi dim tensor
      
      * utilities to restore the original tensor shape
      
      * i) style-fix ii) rename variables
      
      * - unit test for multiple dimensions ii) refactor create_mask to seperate function
      
      * - fixed unit tests
      
      * fix style
      
      * set output element type to dynamic in pre_validate and infer shape
      
      * disable ce with one hot unit test on PlaidML
      
      * add CE op to fused_op_tbl
      
      * - add serialzier support for CE and CE Backprop
      a1a8a7e3
  9. 18 Nov, 2019 1 commit
  10. 15 Nov, 2019 1 commit
  11. 08 Nov, 2019 1 commit
  12. 07 Nov, 2019 2 commits
  13. 05 Nov, 2019 1 commit
  14. 04 Nov, 2019 2 commits
    • Nishant Patel's avatar
      Shape as a node in ConvBpropData/Filters (v1) (#3711) · 6e5b4cd0
      Nishant Patel authored
      * Shape as a node in ConvBpropData (v1)
      
      * Fix constant op creation
      
      * Convbpropfilters dynamic shape
      
      * Avgpool bprop dynamic shape
      
      * Add downgrade pass
      
      * Downgrade pass Avgpoolbackprop
      
      * Shape checks and shape relevancy
      
      * Dyn avgpoolbprop test case
      
      * Revert "Dyn avgpoolbprop test case"
      
      This reverts commit b094f2f99d00023593c667ff16cf060a586ad16a.
      
      * Revert "Avgpool bprop dynamic shape"
      
      This reverts commit ef8a4d197577c0d277d634baa9d6d082adcddae0.
      
      * Revert "Downgrade pass Avgpoolbackprop"
      
      This reverts commit 3f31f0fea8fe6e79bd958cbaa7cb8495008a795f.
      
      * Call shape relevancy
      
      * Revert Avgpoolbprop changes
      
      * mark nodes as dynamic
      
      * Add opset transform tests
      
      * Change API
      
      * Adjust strides
      
      * Use size
      
      * Merge PR 3776
      
      * add shape relevance
      
      * Add convbprop_data test case
      
      * Add convbprop_filter test case
      
      * Use is_constant helper
      
      * Remove opset pdpd test case
      
      * resolve conflict
      
      * add checks for validate and infer
      
      * Type prop tests
      6e5b4cd0
    • Ewa Tusień's avatar
      Provide tool to import and run ONNX model via ngraph C++ API. (#3772) · 4cecf6e4
      Ewa Tusień authored
      * Added tool for running Onnx models via nGraph C++ API.
      
      * Code formatting.
      
      * Added option to load inputs from binary files.
      
      * Removed unused variables.
      
      * Changed description.
      
      * Moved read_binary_file function from test_tools to ngraph utils.
      
      * Added option to provide arguments with equals sign.
      
      * Bugfix.
      
      * Changed reading file.
      
      * Code refactoring.
      
      * Added output printing.
      
      * Added comments.
      
      * Undo moved function.
      
      * Removed unused imports.
      
      * Update docstring
      Co-Authored-By: 's avatarMichał Karzyński <postrational@users.noreply.github.com>
      
      * Update docstring
      Co-Authored-By: 's avatarMichał Karzyński <postrational@users.noreply.github.com>
      
      * Added catching exception.
      
      * Code refactoring.
      4cecf6e4
  15. 31 Oct, 2019 1 commit
    • gaurides's avatar
      CPU implementation of Gelu op (#3787) · 73fff9f4
      gaurides authored
      * Initial implementation
      
      * Fixed Gelu
      
      * Gelu backprop initial implementation
      
      * Add GeluBackprop fusion
      
      * Gelu and gelu backprop fusion test cases
      
      * Prevent decompose_op() for Gelu/GeluBackpropFactor for some type
      
      * Fixes and cleanup
      
      * Enabled backprop fusion
      
      * Fixed some issues
      
      * Mostly cleanup
      
      * Some more cleanup
      
      * File permissions
      
      * Remove unused variable
      
      * Style check
      
      * Address PR feedback
      
      * Address PR feedback
      
      * Incorporate changes related to latest master
      
      * Style check
      
      * Some more PR feedback related changes
      
      * Remove comment
      
      * Check for relative error
      
      * Retrigger CI
      
      * corrected syntax
      73fff9f4
  16. 29 Oct, 2019 2 commits
  17. 28 Oct, 2019 1 commit
    • Mateusz Bencer's avatar
      [SPEC] Implement StridedSlice:v1 (#3722) · bb9b5be6
      Mateusz Bencer authored
      * DynSlice was adjusted to specyfication
      
      * Fixed documentation
      
      * Fixed styles
      
      * Fixed clang warning
      
      * Introduced StridedSlice as separate op
      
      * revert dyn_slice
      
      * Fixed StrideSlice implementation
      
      * Enable downgrade pass in dynamic backend
      
      * Implemented upgrade/downgrade pass
      
      * Added serialization
      
      * Styles applied
      
      * Styles applied. Part.2
      
      * Updated dynamic backends list
      
      * Move StridedSlice outside experimental
      
      * Make Slice as v0 of StridedSlice
      
      * Styles applied
      
      * Styles applied
      
      * Fixed clang error
      
      * Code review remarks introduced
      
      * Move GenerateMask up in Opset0Downgrade to keep alphabetical sort
      
      * Style apply
      bb9b5be6
  18. 25 Oct, 2019 2 commits
    • mozga-intel's avatar
      Concat operator, negative indexing support (#3708) · f349593d
      mozga-intel authored
      * Concat operator is updated to support dynamic_shape
      1) Added new concat_negative_indexing test
      2) Replaced size_t -> int64_t
      3) Support for a negative indexing, calculate axis = axis + int64(input_rank)
         if (axis < 0) { axis = axis + int64_t(this_input_rank); }
      
      * Remove unwanted #include "ngraph/op/constant.hpp" header
      
      * Refactoring:
      1) The name of variable is replaced: m_concatenation_axis -> m_axis
      
      * Concat negative indexing test is adjusted to support dynamic_shape tensor
      auto pshape_a = PartialShape::dynamic(); for each tensor {a,b,c} result tensor has dynamic_shape
      
      * The backend supports dynamic shapes
      auto backend = runtime::Backend::create("${BACKEND_NAME}", true);
      
      * Other shape is supported by concat:
      set_output_type(0, inputs_et, PartialShape::dynamic(concatenation_axis_output_dim));
      
      * The NODE_VALIDATION_CHECK was moved up to be for a dynamic_shape
      
      * [Test] The shape of output tensor was changed
      [Concat CPU] Added support for a negative indexing on a cpu
      
      * Review changes:
      1) Added axis re-calculate for a reference version of concat
      2) axis is not replied
      
      * Review changes: support for a negative axis
      
      * Comment about variable is added to concat.hpp file
      Removed unused variable
      f349593d
    • baojun's avatar
      Add partial slice fused op for pdpd use (#3759) · f09b512e
      baojun authored
      * add partial slice op placeholder
      
      * fprop implemented
      
      * add a dynamic ut
      
      * implement bprop
      
      * support decrease axis
      
      * add bprop ut
      
      * address comment
      
      * use descriptive var name
      f09b512e
  19. 24 Oct, 2019 2 commits
  20. 21 Oct, 2019 1 commit
  21. 18 Oct, 2019 1 commit
  22. 17 Oct, 2019 1 commit
    • Jayaram Bobba's avatar
      [SPEC] Added support for v1 Broadcast op specification (#3737) · e741f8f1
      Jayaram Bobba authored
      * - Added support for v1 Broadcast op specification
      - Added upgrade/downgrade conversions between v0 and v1
      
      * Added unit test for pdpd broadcast
      
      * Make numpy default autobroadcast type and some style fixes
      
      * Added support in Dynamic wrapper for dyn elimination and copied over unit tests from DynBroadcast
      
      * Addressed PR feedback
      
      * Addressed PR feedback on documentation
      e741f8f1
  23. 11 Oct, 2019 2 commits
    • baojun's avatar
      Make softmax axes dynamic (#3601) · 47a727a6
      baojun authored
      * make axes dynamic
      
      * add ut
      
      * update softmax deserializer
      
      * check axes to be constant
      
      * remove duplicates
      47a727a6
    • Mateusz Bencer's avatar
      [SPEC] Implement ReduceSum:v1 and ReduceProd:v1 downgrade pass (#3676) · 5a6cf4d0
      Mateusz Bencer authored
      * Implemented downgrade pass
      
      * Using Pad:v1 in onnx_importer
      
      * Downgrade transformation doc fixed
      
      * Added downgrade pass for reduce_prod
      
      * Using ReduceProd:v1 in onnx_importer
      
      * Added ReduceProd:1 downgrade support
      
      * Clang styles applied
      
      * Downgrade pass added for all backends
      
      * Added downgrade pass for reduce_prod
      
      * Using ReduceProd:v1 in onnx_importer
      
      * Added ReduceProd:1 downgrade support
      
      * Clang styles applied
      
      * Apply suggestions from code review
      
      Changed pad_opset_pass to opset_downgrade
      Co-Authored-By: 's avatarTomasz Socha <tomasz.socha@intel.com>
      
      * Fix names
      
      * Apply suggestions from code review
      
      Removed redundant include, renamed tests
      Co-Authored-By: 's avatarTomasz Socha <tomasz.socha@intel.com>
      
      * Changed order of passes
      
      * Changed way of op casting
      
      * Changed order of passes
      
      * Changed downgrade pass order of CPU backend
      
      * Changed downgrade pass order of CPU backend
      
      * styles applied
      
      * [SPEC] Fixed NormalizeL2 (#3695)
      
      * Fixed NormalizeL2
      
      * style applied
      
      * Fixed axes rank checking
      
      * removed redundant comma
      
      * Set keep_dims by function argument
      
      * Improved error message
      
      * Fixed casting method
      
      * fix styles
      
      * styles applied
      
      * Fixed normalize tests
      
      * unit tests names refactor
      Co-Authored-By: 's avatarMichał Karzyński <postrational@users.noreply.github.com>
      
      * Disable not supported PlaidML tests
      
      * Added missing EOF
      5a6cf4d0
  24. 10 Oct, 2019 1 commit
  25. 09 Oct, 2019 1 commit
  26. 04 Oct, 2019 1 commit
    • Scott Cyphers's avatar
      Cyphers/26mig [MLIR] (#3716) · 7cba0d0e
      Scott Cyphers authored
      * Hotfix for negative axes in unsqueeze op (#3705)
      
      * Hotfix for negative axes in unsqueeze op
      
      * Review fix I
      
      * Enable Gather with negative indices. (#3701)
      
      * Enable Gather with negative indices.
      
      * Address PR feedback.
      
      * Remove GOE from Gather unit tests.
      
      * merge error
      
      * Disable test for MLIR
      7cba0d0e
  27. 01 Oct, 2019 2 commits