1. 09 3月, 2020 1 次提交
  2. 06 3月, 2020 1 次提交
  3. 05 3月, 2020 1 次提交
  4. 03 3月, 2020 1 次提交
  5. 02 3月, 2020 1 次提交
  6. 01 3月, 2020 1 次提交
  7. 28 2月, 2020 1 次提交
  8. 26 2月, 2020 1 次提交
  9. 24 2月, 2020 2 次提交
    • fix data type of asserts, test=develop (#2787) · e4429583
      石晓伟 提交于
      e4429583
    • Y
      [LITE][OPENCL] support fp16 for cl_image_converter, layout, activation all... · 55b45651
      Yuan Shuai 提交于
      [LITE][OPENCL] support fp16 for cl_image_converter, layout, activation all OpenCL image kernel. test=develop (#2964)
      
      * [LITE][OPENCL] support fp16 for cl_image_converter, layout, activation image kernel. test=develop
      
      * add conv, depthwise and UT. test=develop
      
      * add pool, conv, nearest_interp kernel. test=develop
      
      * support fp16 for scale, reshape, concat, fc buffer opencl kernel. test=develop
      
      * refactor for mul opencl buffer kernel. test=develop
      
      * support fp16 for elementwise_mul opecl image kernel. test=develop
      
      * support fp16 for elementwise_mul opencl image kernel. test=develop
      
      * support fp16 for ele_add, fuse_ele_add_act opencl kernel. test=develop
      
      * rename io_copy. test=develop
      
      * mobilenetv1,v2 passed on 855. test=develop
      
      * fix opt for opencl. test=develop
      55b45651
  10. 22 2月, 2020 1 次提交
  11. 21 2月, 2020 1 次提交
  12. 20 2月, 2020 1 次提交
  13. 16 2月, 2020 1 次提交
  14. 14 2月, 2020 1 次提交
  15. 13 2月, 2020 1 次提交
  16. 12 2月, 2020 1 次提交
  17. 06 2月, 2020 1 次提交
    • J
      Support weight quantization (#2791) · 695ca28c
      juncaipeng 提交于
      * optimize quant_dequant_fuse_pass, test=develop
      
      * update, test=develop
      
      * update, test=develop
      
      * fix bug for accessing the removed node, test=develop
      
      * set the bias of int8 conv as float, test=develop
      
      * support weight quantization, test=develop
      
      * up, test=develop
      
      * up, test=develop
      
      * up, test=develop
      695ca28c
  18. 22 1月, 2020 1 次提交
  19. 16 1月, 2020 1 次提交
  20. 14 1月, 2020 1 次提交
  21. 09 1月, 2020 1 次提交
  22. 06 1月, 2020 1 次提交
  23. 03 1月, 2020 2 次提交
  24. 02 1月, 2020 1 次提交
  25. 31 12月, 2019 1 次提交
    • H
      [LITE][NPU][XPU] Refine the registration and implementation of op bridges (#2700) · fb668935
      hong19860320 提交于
      * Fix the compiling error which occurs when specify the ddk_root path and build for huawei NPU.
      
      * Refine the registration of op bridges and make it similar to the registration of op and kernel.
      
      * Refine the interfaces of the graph and node for op bridges, and support creating constant and data node automatically according to the attribute 'persistable' of the target tensor.
      
      * Add the unit test of the scale and softmax op bridge for NPU.
      fb668935
  26. 24 12月, 2019 1 次提交
  27. 23 12月, 2019 1 次提交
  28. 20 12月, 2019 1 次提交
  29. 18 12月, 2019 1 次提交
  30. 17 12月, 2019 2 次提交
    • H
      [lite]add some fusion (#2604) · e5cbdb7b
      HappyAngel 提交于
      * add cv image process
      
      * fix arm liunx build error
      
      * add LITE_WITH_CV defien to make cv, test=develop
      
      * fix cv format, annd add describe in utils/cv
      
      * delete some Meaningless comments, test=develop
      
      * set LITE_WITH_CV=OFF in build.sh, test=develop
      
      * delete cv_enum.h in utils/cv, push the contents in cv_ennum.h to paddle_image_preprocess.h, test=develop
      
      * according to reviews to redefine paddle_image_preprocess.h, test=develop
      
      * add detailed note of flipParam, test=develop
      
      * fix format in paddle_image_preprocess.h, test=develop
      
      * fix error when build x86. test=develop
      
      lite_with_X86 does not contain lite_with_cv
      
      * fix cmake error in llite/CMakeLists.txt, missing mkdir cxx, test=develop
      
      * according to review change, test=develop
      
      * chang grb to rgb, test=develop
      
      * add elemetnwise mul constant elimination and deconv+relu, deconv+batchnorm fusion, test=develop
      
      * fix format, test=develop
      e5cbdb7b
    • G
      [ARMLinux] Fix the error that armlinux can not compile (#2612) · bd9481de
      guofei 提交于
      test=develop
      bd9481de
  31. 13 12月, 2019 1 次提交
  32. 10 12月, 2019 2 次提交
    • W
      fix type_target_cast pass. support only copy once for multiple use arg. test=develop (#2572) · dde80670
      Wilber 提交于
      For multiple-use parameters, only copy once
      dde80670
    • W
      modify static_kernel_pass to support select the kernel according to input type (#2488) · 8b84b728
      Wilber 提交于
      修改了选kernel的逻辑,默认从模型文件中读取出lod_tensor的data type,在static_kernel_pick pass中如果kernel输入输出的类型与读取的data type完全一致,则选择该Kernel的概率增大。
      
      - 增加 从模型文件__model__读取lod_tensor的data type到cpp::vardesc
      
      - program中增加unordered_map<string, type>字段,并在 Program::PrepareWorkspace中对该字段赋值
      
      - 修改了node.h文件,将const Type* 更改为Type*,并在SSAGraph::Build过程中为符合条件的type*赋值
      
      - static_kernel_pick_pass中添加新规则,如果kernel的输入类型输出类型与__model__中存储的类型的一致,则score*=2。
      
      - 支持模型中用到sequence_reverse_float kernel(输入输出均为float)和sequence_reverse_int64 kernel(输入输出均为int64),能够根据输入输出type选kernel
      8b84b728
  33. 03 12月, 2019 1 次提交
  34. 29 11月, 2019 2 次提交
  35. 26 11月, 2019 1 次提交
    • Z
      [XPU][NPU] update conv and conv_transpose padding (#2493) · 7718e665
      zhupengyang 提交于
      * [XPU] update conv padding
      
      test=develop
      
      * [XPU] exclude xpu for passes
      
      test=develop
      
      * fix conv padding compute
      
      test=develop
      
      * [NPU] update 2-pad to 4-pad for conv and conv_transpose
      
      test=develop
      
      * reuse UpdatePadding code
      
      test=develop
      7718e665