1. 14 4月, 2021 1 次提交
  2. 08 4月, 2021 1 次提交
  3. 30 3月, 2021 1 次提交
  4. 26 3月, 2021 1 次提交
  5. 24 3月, 2021 1 次提交
  6. 21 3月, 2021 1 次提交
  7. 19 3月, 2021 1 次提交
  8. 12 3月, 2021 1 次提交
  9. 18 1月, 2021 1 次提交
  10. 13 1月, 2021 2 次提交
    • C
      skip quantizing ops in cpu inference (#30342) · 8e3a2940
      cc 提交于
      * skip quantizing ops in cpu inference, test=develop
      8e3a2940
    • H
      Implemented AddQuantDequantPass in imperative quantization. (#26692) · ee623bff
      huangxu96 提交于
      * Implemented AddQuantDequantPass in imperative quantization.
      
      * Supported LeakyReLU Quantization
      
      * For meeting coverage rate.
      
      * Changed the file name of test of AddQuantDequant
      
      * Implemented more Quantized NoWeightLayers.
      
      * Fix the loss cannot align problem between static and dynamic model quantization, add swish as supported quantized layer in imperative quantization.
      
      * remove noweight_list
      
      * support 2.0 API such as Pool2D and ReLu
      ee623bff
  11. 08 1月, 2021 1 次提交
  12. 05 1月, 2021 1 次提交
    • C
      Support dygraph quant model (#29927) · 1fa863da
      cc 提交于
      * Avoid the scale to be infinity in quant2_int8_mkldnn_pass, test=develop
      * support quantized model for paddle2.0 dygraph, test=develop
      1fa863da
  13. 30 12月, 2020 1 次提交
  14. 29 12月, 2020 1 次提交
  15. 28 12月, 2020 1 次提交
    • X
      clean redundant API alias in 2.0 - part 1 (#29928) · 726c78f2
      XiaoguangHu 提交于
      * rm check_import_scipy, rm chunk_eval and mean_iou in paddle.metric.__init__.py
      
      * Revert "rm check_import_scipy, rm chunk_eval and mean_iou in paddle.metric.__init__.py"
      
      This reverts commit 179ba8c2b22bc31fe8d8a126e31820792cbd0f4e.
      
      * delete paddle.metric.chunk_eval and paddle.metric.mean_iou
      
      * delete paddle.nn.clip and paddle.nn.clip_by_norm
      
      * delete paddle.nn.functional.activation.hard_sigmoid and paddle.nn.functional.activation.hard_swish
      
      * delete paddle.nn.Pool2D, paddle.nn.BilinearTensorProduct, paddle.nn.RowConv, paddle.nn.functional.row_conv
      
      * fix extension import error
      
      * fix unittest for row_conv and Pool2D
      726c78f2
  16. 22 12月, 2020 1 次提交
  17. 08 12月, 2020 1 次提交
  18. 30 11月, 2020 1 次提交
  19. 27 11月, 2020 1 次提交
  20. 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.
      40f54537
  21. 18 11月, 2020 1 次提交
  22. 08 11月, 2020 1 次提交
    • Y
      exec ut no more than 15s 1 (#28439) · ba075632
      YUNSHEN XIE 提交于
      * disable ut test_parallel_executor_fetch_isolated_var,test=document_fix
      
      * test for limiting ut exec time as 15S
      
      * fix an error caused by cannot find ut
      
      * fix some error
      
      * can not find test_transformer
      
      * fix error caused by ut not run in windows
      
      * fix error caused by Compiler Options
      
      * fix error caused by setting timeout value as 15 in python/paddle/tests/CMakeLists.txt
      
      * setting timeout value to 120s for old ut
      
      * add the timeout value setting
      
      * fix error caused by ut only run in coverage_ci
      
      * add analyzer_transformer_profile_tester
      
      * fix some error
      
      * fix some error
      
      * fix error with inference option
      
      * fix error with inference option setting as ON_INFER
      
      * add some ut to set timeout
      
      * modified some option
      
      * fix error
      
      * fix some timeout error
      
      * fix error
      
      * fix error
      
      * fix timeout for test_analyzer_bfloat16_resnet50
      
      * fix error
      
      * setting timeout properity for some ut
      
      * first pr for new ut timeout as 15S
      ba075632
  23. 14 10月, 2020 1 次提交
  24. 11 10月, 2020 1 次提交
  25. 01 10月, 2020 1 次提交
  26. 23 9月, 2020 1 次提交
  27. 22 9月, 2020 1 次提交
    • P
      Use dygraph mode by default (#27443) · 827ac36f
      pangyoki 提交于
      * default open dygraph mode
      
      * fix CI-Mac
      
      * fix Mac-CI other unittest file
      
      * fix CI-Py3
      
      * fix test_communicator_geo and test_buffer_shared_memory_reuse_pass
      
      * add enable_static to fix CI-Py3
      
      * add enable_static to fix CI-coverage
      
      * delete try except
      827ac36f
  28. 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.
      02606d45
  29. 18 9月, 2020 1 次提交
  30. 07 9月, 2020 1 次提交
    • S
      fix dimensions error for mobilenetv1_KL_quant (#26776) · eb65877c
      Sylwester Fraczek 提交于
      * fix dimensions error for mobilenetv1_KL_quant
      
      fixes AssertionError: The size of weight scales vector (1000) does not match the number of output channels (1024) in the weights tensor fc7_weights.
      
      add mul test
      
      * remove comment
      
      * add third case unit test
      eb65877c
  31. 02 9月, 2020 1 次提交
  32. 27 8月, 2020 1 次提交
  33. 25 8月, 2020 1 次提交
  34. 24 8月, 2020 2 次提交
  35. 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
      3f816bc8
  36. 31 7月, 2020 2 次提交
  37. 28 7月, 2020 1 次提交