1. 05 10月, 2018 1 次提交
  2. 26 9月, 2018 1 次提交
  3. 14 9月, 2018 1 次提交
  4. 11 9月, 2018 1 次提交
  5. 31 8月, 2018 1 次提交
  6. 21 8月, 2018 1 次提交
    • M
      Fuse Convolution and Eltwise Add into MKLDNN's Conv+Bias (#12669) · cd32ddac
      Michał Gallus 提交于
      * Fuse Convolution and Eltwise Add into Conv+Bias
      
      * Reduce bias branching at conv_mkldnn_op
      
      * Add MKLDNN build checks for Conv Bias
      
      * Conv-bias: check if bias input exist befor assignment
      
      * Conv-bias: Remove Bias dim check from infershape
      
      It was causing conv3d test to crash upon\ncalling HasInput(Bias)
      cd32ddac
  7. 15 8月, 2018 1 次提交
  8. 14 8月, 2018 1 次提交
    • W
      hide misc APIs (#12540) · 8b77448d
      Wu Yi 提交于
      * hide misc APIs
      
      * update
      
      * fix transformer test
      
      * update API.spec
      8b77448d
  9. 26 7月, 2018 1 次提交
  10. 17 7月, 2018 1 次提交
    • W
      Remove block api (#12107) · db67d60e
      Wu Yi 提交于
      * remove block api
      
      * remove clone_variable
      
      * hide block inner apis
      
      * update
      
      * fix tests
      db67d60e
  11. 05 7月, 2018 1 次提交
  12. 27 6月, 2018 1 次提交
    • P
      bnorm+relu fuse for mkldnn (inference) (#11434) · 9a15c923
      pzelazko-intel 提交于
      * bnorm+relu fuse for mkldnn
      
      * separate fuse_relu function
      
      * bug fix
      
      * proper while range in inference_transpiler
      
      * description fix
      
      * review fix
      
      * review fix
      
      * unit test for fwd batch norm+relu MKLDNN fuse
      9a15c923
  13. 15 6月, 2018 2 次提交
  14. 07 5月, 2018 1 次提交
  15. 04 5月, 2018 1 次提交
    • K
      Add float16 demo code and put float16 work in contrib/float16 folder (#10331) · 7a860694
      Kexin Zhao 提交于
      * add test float16 inference accuracy example
      
      * complete the test
      
      * clean code
      
      * add argument parse and refine tests
      
      * add shell script
      
      * add float16 benchmark code
      
      * refine code
      
      * prepare for contrib/float16
      
      * put things in contrib float16 folder
      
      * update benchmark result
      
      * further update benchmark report
      
      * add float16 inference report
      
      * update report
      7a860694
  16. 27 4月, 2018 1 次提交
  17. 17 4月, 2018 1 次提交
  18. 13 4月, 2018 2 次提交
  19. 11 4月, 2018 1 次提交
  20. 10 4月, 2018 2 次提交
  21. 09 4月, 2018 1 次提交