1. 25 11月, 2020 1 次提交
    • H
      Quant nn2.0 (#28764) · 40f54537
      huangxu96 提交于
      * Impelement 2.0 API version Conv2d and Linear layer quantization in imperative mode.
      
      * use cudnn softmax in static Lenet
      
      * Modified ChannelwiseQAT Unittest for 2.0 API.
      
      * For CI python coverage.
      未验证
      40f54537
  2. 24 11月, 2020 1 次提交
  3. 18 11月, 2020 1 次提交
  4. 16 11月, 2020 1 次提交
  5. 14 10月, 2020 1 次提交
  6. 12 10月, 2020 1 次提交
  7. 01 10月, 2020 1 次提交
  8. 21 9月, 2020 1 次提交
    • H
      Quant op dev (#25932) · 02606d45
      huangxu96 提交于
      * Finished ChannelWiseQuantDequantAbsMaxOp and Passed unittests.
      
      * Finished channel-wise quantize strategy in imperative quantization.
      
      * Added Cuda code of ChannelWiseQuantDequantMaxAbsOP
      Add Cuda code of ChannelWiseQuantDequantMaxAbsOp
      
      * Add quant_axis for channel_wise quant.
      
      * fixed a bug in unnitests, which will not trigger axis = 1 case and cannot meet the coverage rate requirement.
      
      * Added some assert infomation and fixed some coding style mistakes.
      未验证
      02606d45
  9. 18 9月, 2020 1 次提交
  10. 15 9月, 2020 1 次提交
  11. 10 9月, 2020 1 次提交
  12. 07 9月, 2020 1 次提交
  13. 31 8月, 2020 1 次提交
    • Q
      Move hapi to python/paddle root dir. (#26442) · f7fb4c22
      qingqing01 提交于
      * Move hapi form paddle/incubate to paddle
      
      * Remove vision/datasets/utils.py and clean code
      
      * Add sample code for conll05
      
      * Print pull path when saving model
      
      * Fix sample code after paramter_list of SGD is changed to parameters
      
      * Fix bug in wmt16 datase
      未验证
      f7fb4c22
  14. 28 8月, 2020 1 次提交
  15. 27 8月, 2020 1 次提交
  16. 21 8月, 2020 1 次提交
  17. 19 8月, 2020 1 次提交
    • C
      [Quantization] Conv2d_transpose and mul support channnelwise quantization (#25639) · 3f816bc8
      cc 提交于
      * Conv2d_transpose and mul support channnelwise quantization, test=develop
      * Skip collecting out threshold for output tensor of which the type is not fp32 or fp64, test=develop
      * Fix error in test_user_defined_quantization, test=develop
      * Add depthwise_conv_bn_fuse, test=develop
      * Add conv_transpose_bn_fuse_pass for post_training_quant, test=develop
      未验证
      3f816bc8
  18. 03 8月, 2020 1 次提交
  19. 31 7月, 2020 1 次提交
  20. 29 7月, 2020 2 次提交
  21. 28 7月, 2020 1 次提交
  22. 11 7月, 2020 1 次提交
  23. 07 7月, 2020 2 次提交
  24. 06 7月, 2020 2 次提交
  25. 30 6月, 2020 1 次提交
  26. 29 6月, 2020 1 次提交
  27. 17 6月, 2020 1 次提交
  28. 04 6月, 2020 1 次提交
    • L
      support user defined quantization func and preprocess (#24720) · b174b997
      Liufang Sang 提交于
      * add user defined func test=develop
      
      * update test=develop
      
      * update test=develop
      
      * fix name conflicts test=develop
      
      * add unittest test=develop
      
      * change 2018 to 2020 test=develop
      
      * add comment test=develop
      
      * add comment for function test=develop
      
      * fix details test=develop
      
      * fix details test=develop
      未验证
      b174b997
  29. 02 6月, 2020 2 次提交
  30. 27 5月, 2020 1 次提交
  31. 26 5月, 2020 2 次提交
  32. 13 5月, 2020 1 次提交
  33. 08 5月, 2020 1 次提交
  34. 28 4月, 2020 1 次提交
  35. 24 4月, 2020 1 次提交
反馈
建议
客服 返回
顶部