1. 31 7月, 2019 2 次提交
    • L
      fix several security bugs reported by security team (#18831) · 0d996908
      liuwei1031 提交于
      * fix security issue, test=develop
      
      * bug fix, test=develop
      
      * throw an exception when null pointer data with non-zero length PaddleBuf is passed, test=develop
      0d996908
    • Z
      Trt fp16 support (#18860) · 61238d31
      Zhaolong Xing 提交于
      * Fix Mask rcnn predictor
          1. refine memory optim algorithm to support the model with the block op.
          2. output diff : modify the affine channel fuse
          3. add condition_block_infer op
      add interface for setting trt calib table dir
      test=develop
      
      * add the missing files.
      test=develop
      
      * 1 add trt fp16 support
      test=develop
      61238d31
  2. 30 7月, 2019 1 次提交
  3. 27 7月, 2019 1 次提交
  4. 24 7月, 2019 1 次提交
    • Z
      Update trt5 for paddle-trt (#18645) · 26ae6d49
      Zhaolong Xing 提交于
      * update paddle-trt for:
          1. fix bug: when batch > 2, core in split plugin.
          2. add leaky_relu trt5.0 support (yolov3 from 65ms to 42ms.)
          3. add new attr to dropout.
          4. shuffle channel, swish, relu6 support
          test=develop
      
      * 1. fix ci
      test=develop
      26ae6d49
  5. 17 7月, 2019 2 次提交
    • G
      remove async executor and add data_feed.proto to the deps of train demo (#18659) · d714bf03
      guru4elephant 提交于
      * remove async executor and add data_feed.proto to the deps of train demo
      d714bf03
    • Fix Bitmain Predictor::Clone() (#18599) · 25d80791
      石晓伟 提交于
      * update anakin-engine interfaces for content-dnn
      
      test=develop
      
      * support only-gpu mode of Anakin
      
      modify eltwise parse
      
      test=develop
      
      * modification for thread-safe
      
      test=develop
      
      * Integrated template instance
      
      test=develop
      
      * increase template parameters
      
      test=develop
      
      * support MLU predictor
      
      test=develop
      
      * update anakin cmake files
      
      test=develop
      
      * update TargetWrapper::set_device
      
      * update the initialization of anakin subgraph
      
      test=develop
      
      * use the default constructor of base class
      
      test=develop
      
      * load model from buffer with length
      
      test=develop
      
      * modify the access level of class
      
      test=develop
      
      * support anakin for bitmain arch
      
      test=develop
      
      * remove files
      
      * checkout cmakelists
      
      test=develop
      
      * modify interfaces
      
      test=develop
      
      * add cmake dependments
      
      test=develop
      
      * enforce the outputs of net
      
      test=develop
      25d80791
  6. 11 7月, 2019 1 次提交
  7. 09 7月, 2019 1 次提交
  8. 08 7月, 2019 4 次提交
    • Z
      Inference: fix mask rcnn model diff, optim memory usage, memory leak. (#18532) · 88b52a27
      Zhaolong Xing 提交于
      * Fix Mask rcnn predictor
          1. refine memory optim algorithm to support the model with the block op.
          2. output diff : modify the affine channel fuse
          3. add condition_block_infer op
      add interface for setting trt calib table dir
      test=develop
      
      * add the missing files.
      test=develop
      88b52a27
    • Support Bitmain Anakin (#18542) · 15291548
      石晓伟 提交于
      * update anakin-engine interfaces for content-dnn
      
      test=develop
      
      * support only-gpu mode of Anakin
      
      modify eltwise parse
      
      test=develop
      
      * modification for thread-safe
      
      test=develop
      
      * Integrated template instance
      
      test=develop
      
      * increase template parameters
      
      test=develop
      
      * support MLU predictor
      
      test=develop
      
      * update anakin cmake files
      
      test=develop
      
      * update TargetWrapper::set_device
      
      * update the initialization of anakin subgraph
      
      test=develop
      
      * use the default constructor of base class
      
      test=develop
      
      * load model from buffer with length
      
      test=develop
      
      * modify the access level of class
      
      test=develop
      
      * support anakin for bitmain arch
      
      test=develop
      
      * remove files
      
      * checkout cmakelists
      
      test=develop
      15291548
    • L
    • T
      add mkldnn shapeblob cache clear strategy (#18513) · fe32879d
      Tao Luo 提交于
      * add mkldnn shapeblob cache clear strategy
      
      test=develop
      
      * refine with comments
      
      test=develop
      
      * make cache clear strategy more safey
      
      test=develop
      
      * add lock for GetShapeBlobSize
      
      test=develop
      fe32879d
  9. 05 7月, 2019 1 次提交
  10. 03 7月, 2019 2 次提交
  11. 02 7月, 2019 1 次提交
  12. 01 7月, 2019 1 次提交
    • M
      Fix Pooling output scale (#18186) · 7023a86c
      Michał Gallus 提交于
      * Int8: Fix Pooling output scale
      
      test=develop
      
      * Update scales quantization for certain operators
      
      These include: concat, transpose, pool and reshape. test=develop
      
      * Move concat minimum scale finding to quantizer
      
      test=develop
      7023a86c
  13. 27 6月, 2019 3 次提交
  14. 21 6月, 2019 1 次提交
  15. 19 6月, 2019 3 次提交
  16. 16 6月, 2019 2 次提交
  17. 14 6月, 2019 1 次提交
    • L
      add Mobilienet ssd int8 analyzer tester (#18075) · 46625415
      lidanqing 提交于
      * add pascalvoc preprocess script and mobilenet-ssd analyzer_tester, wait 17737
      
      * change converting local dataset to downloading and converting tarfile
      test=develop
      
      * change the test data_path
      test=develop
      
      * change copyright (c) 2016 to copyright (c) 2019
      test=develop
      46625415
  18. 13 6月, 2019 2 次提交
  19. 12 6月, 2019 1 次提交
  20. 11 6月, 2019 2 次提交
    • Update the Anakin interfaces for content-dnn and MLU (#17890) · bce259e5
      石晓伟 提交于
      * update anakin-engine interfaces for content-dnn
      
      test=develop
      
      * support only-gpu mode of Anakin
      
      modify eltwise parse
      
      test=develop
      
      * modification for thread-safe
      
      test=develop
      
      * Integrated template instance
      
      test=develop
      
      * increase template parameters
      
      test=develop
      
      * support MLU predictor
      
      test=develop
      
      * update anakin cmake files
      
      test=develop
      
      * update TargetWrapper::set_device
      
      * update the initialization of anakin subgraph
      
      test=develop
      
      * use the default constructor of base class
      
      test=develop
      bce259e5
    • Z
      Light mem reuse strategy for inference. (#17925) · 4e8d5a03
      Zhaolong Xing 提交于
      * fix: when use the load model from memory mode, the RAM occupy is high
      
      test=develop
      
      * ligth mem reuse
      test=develop
      
      * fix cpplint
      test=develop
      4e8d5a03
  21. 06 6月, 2019 4 次提交
  22. 03 6月, 2019 1 次提交
  23. 29 5月, 2019 2 次提交