1. 20 Aug, 2019 5 commits
    • Nishant Patel's avatar
      Add QuantizedDot to ngraph core (#3235) · 79041d19
      Nishant Patel authored
      * First pass, remove QDot as experimental op, add it as core op, test case failing
      
      * Change QuantizedMatmul API
      
      * Tests for QuantizedDot passing, cleanup required
      
      * Move test cases to backend_test.in.cpp
      
      * Change reference dot API to take scale and zero point
      
      * Onnx matmul integer tests passing
      
      * Add validate_and_infer_types()
      
      * Add more checks for QDot
      
      * Add type prop tests
      
      * Add interpreter support
      
      * Add serializer support
      
      * Disable tests in other backends
      
      * Fix test and add codegen support
      
      * Make axes optional argument
      
      * Change fusion pattern
      
      * Copyright
      
      * merge changes
      
      * more merge changes
      
      * Fix more merge conflicts
      
      * change builders to reflect new changes
      
      * cleanup
      
      * Add reduction_axes to the API
      
      * Fix onnx test cases
      
      * Remove debug comments
      
      * Fix CI
      
      * disable plaidml tests
      
      * Remove comment
      79041d19
    • Adam Procter's avatar
      1bc0a299
    • Nishant Patel's avatar
      Remove quantized pool {avg and max} (#3458) · dc0f0011
      Nishant Patel authored
      * Remove QuantizedMaxPool
      
      * Remove QuantizedAvgPool
      
      * Disable tests for plaidML
      
      * Fix CI
      
      * Add correct casting for int8 type in reference kernel
      
      * Disable tests for GPU
      dc0f0011
    • Robert Kimball's avatar
      Did a batch normalization of the BatchNorm unit test names (#3439) · 152e99d8
      Robert Kimball authored
      * Normalize BatchNorm test names
      
      * unit test renamed so manifest must be updated
      152e99d8
    • Adam Procter's avatar
      Dynamic "flatten" builder (#3448) · 97578988
      Adam Procter authored
      * Dynamic version of builder::flatten
      
      * Remove as_single_output_node (no longer needed)
      
      * Temp fix for dyn elimination
      97578988
  2. 19 Aug, 2019 1 commit
    • Mateusz Bencer's avatar
      [Spec][Fused] Adjust op Normalize (#3406) · 5ed2c588
      Mateusz Bencer authored
      * Changed name from Normalize to Normalize2
      
      * Changed name from Normalize to Normalize2 in tests
      
      * Changed name of normalize source files
      
      * Removed across spatial and channel shared params
      
      * Removed scale and introduced input axes
      
      * Support for axes input was introduced
      
      * Added possibility to choose method of bias using
      
      * Clang style applied
      
      * Code review remarks introduced
      
      * Code review remarks introduced
      
      * Added python script to generate normalize_l2 test data
      5ed2c588
  3. 15 Aug, 2019 3 commits
  4. 13 Aug, 2019 1 commit
  5. 09 Aug, 2019 2 commits
  6. 07 Aug, 2019 3 commits
    • Denise Kutnick's avatar
      PlaidML Grouped Convolution Implementation (#3395) · 37d69cb4
      Denise Kutnick authored
      * adding group convolution implementation for plaidml
      
      * update CMakeLists.txt to include new group convolution files
      
      * adding new ngraph unit tests for grouped convolutions
      
      * adding group conv unit test back in for plaidml backend
      
      * specify group convolution support in plaidml
      
      * add denise as codeowner for plaidml runtime dir
      
      * remove commented-out lines of unit test manifest
      
      * style changes
      
      * resolve all discussions in PR
      
      * skip data dilation unit test on cpu backend
      37d69cb4
    • Denise Kutnick's avatar
      [r0.25] PlaidML Grouped Convolution Implementation (#3399) · 9937f8b5
      Denise Kutnick authored
      * adding group convolution implementation for plaidml
      
      * update CMakeLists.txt to include new group convolution files
      
      * adding new ngraph unit tests for grouped convolutions
      
      * adding group conv unit test back in for plaidml backend
      
      * specify group convolution support in plaidml
      
      * add denise as codeowner for plaidml runtime dir
      
      * remove commented-out lines of unit test manifest
      
      * style changes
      
      * resolve all discussions in PR
      
      * skip data dilation unit test on cpu backend
      9937f8b5
    • Mateusz Bencer's avatar
      [Fused] Remove fused LeakyRelu (#3333) · bf511013
      Mateusz Bencer authored
      bf511013
  7. 06 Aug, 2019 1 commit
  8. 01 Aug, 2019 1 commit
  9. 31 Jul, 2019 2 commits
  10. 29 Jul, 2019 3 commits
  11. 28 Jul, 2019 2 commits
  12. 25 Jul, 2019 1 commit
  13. 24 Jul, 2019 1 commit
  14. 23 Jul, 2019 3 commits
  15. 19 Jul, 2019 1 commit