1. 22 Feb, 2019 2 commits
    • Nishant Patel's avatar
      Add QuantizedConcat (#2060) · b9ff5d1f
      Nishant Patel authored
      * Add QuantizedConcat
      
      * Remove unused variables and add check for size of mins and maxes vector
      
      * Resolve conflicts
      
      * Merged with master and addressed some PR feedback
      
      * Avoid float comparison
      
      * make min/max vector, add dequant/quanti
      
      * fix dequant/quant scales
      
      * fix CI build issue
      b9ff5d1f
    • Robert Kimball's avatar
      use calls for new backend API in unit tests (#2427) · 26bba737
      Robert Kimball authored
      * use calls for new backend API in unit tests
      
      * fix compile error
      
      * fix compile error
      26bba737
  2. 08 Feb, 2019 1 commit
  3. 08 Jan, 2019 1 commit
    • Nishant Patel's avatar
      Fix signed conv op (#2287) · 259c0a48
      Nishant Patel authored
      * Fix signedconv op
      
      * Add assert and change the dynamic scale test case
      
      * Change assert
      
      * Update quantized_conv_bias.cpp
      
      * Update quantized_conv_bias.cpp
      259c0a48
  4. 03 Jan, 2019 1 commit
  5. 21 Dec, 2018 1 commit
    • Nishant Patel's avatar
      Support dynamic scales for Qconv's and Dequantize (#2171) · 7e310e20
      Nishant Patel authored
      * Support dynamic scales for Qconv's and Dequantize
      
      * Remove constant folding
      
      * add additional dynamic_quantize unittest
      
      * add another mxnet quantize unittest
      
      * add additional dynamic_dequantize tests
      
      * fix shape error
      
      * add dynamic signed_quantize unittest
      
      * Pass correct scale
      
      * Refactoring
      
      * Added dynamic scale support for QCBA and QCBSA
      
      * Refactor to create MKLDNN primitives on the first iteration
      
      * remove stray code
      
      * unused variables
      
      * remove extraneous line
      7e310e20
  6. 19 Dec, 2018 1 commit
  7. 07 Dec, 2018 1 commit
    • Robert Kimball's avatar
      Backend API change pre-work (#2064) · e0933553
      Robert Kimball authored
      * change compile call to return Handle
      
      * make CPU require compile() before call()
      
      * fix unit tests to call compile() before call()
      
      * fix failing ops
      
      * update unit test
      
      * revert some changes
      
      * more fixups
      
      * more diff cleanup
      
      * a few more issues addressed
      
      * more fixes
      
      * update API
      
      * more updates
      
      * fix test_ops.py
      
      * fix
      
      * another attempt to fix
      
      * fix unit test
      
      * fix test error
      e0933553
  8. 06 Dec, 2018 1 commit
    • Nishant Patel's avatar
      QCBiasAdd and QCBiasSignedAdd for mkldnn (#2062) · 1f40160d
      Nishant Patel authored
      * Quantize the bias to int32
      
      * Bias scale fix
      
      * mnist works
      
      * Quantize Bias
      
      * Introduce Quantize op in the graph to quantize bias & feedback
      
      * Add QuantizedConvBiasAdd
      
      * Comments and some refactoring
      
      * Add test case with float bias and enable int32 as quantized type in ngraph
      
      * Change shape of scale from Shape{} to Shape{1} in the backend
      
      * Add QuantizedConvBiasSignedAdd
      
      * Fix Layouts, clean up and a test case for QCBA
      
      * Test case for QCBSA
      
      * cleanup mkldnn_emitter.hpp
      
      * fix build error
      
      * Constant fold
      1f40160d
  9. 27 Nov, 2018 1 commit
  10. 20 Nov, 2018 1 commit
  11. 16 Nov, 2018 1 commit
  12. 12 Nov, 2018 1 commit
    • Nishant Patel's avatar
      Quantize(reorder) bias to int32 (#1933) · 296ee2cf
      Nishant Patel authored
      * Quantize the bias to int32
      
      * Bias scale fix
      
      * mnist works
      
      * Quantize Bias
      
      * Introduce Quantize op in the graph to quantize bias & feedback
      
      * Comments and some refactoring
      
      * Add test case with float bias and enable int32 as quantized type in ngraph
      
      * Change shape of scale from Shape{} to Shape{1} in the backend
      296ee2cf
  13. 26 Oct, 2018 1 commit
    • Nishant Patel's avatar
      Add builder for {de}quantize to make API's consistent and support {de}quantize with mkldnn (#1839) · 6b36a480
      Nishant Patel authored
      * Add builder for {de}quantize
      
      * Add declaration in header
      
      * Add mkldnn support for {de}quantize
      
      * Add support for {de}quantize with mkldnn
      
      * Add Dex support
      
      * Generalizing some api's and adding a test case for DQ in backend_test.in.cpp
      
      * Unify scale between ngraph and mkldnn
      
      * Check for nullptrs
      
      * PR feedback
      
      * fix unit test failure
      
      * Adding tests for builder and deleting the backend tests
      
      * curly braces
      
      * test rename
      6b36a480