1. 24 7月, 2019 1 次提交
  2. 23 7月, 2019 6 次提交
    • J
      [MKL-DNN] Extended LRN with reusing via Acquire API (#18675) · 95c1816e
      Jacek Czaja 提交于
      test=develop
      
      - compileation fix
      
      - Yet another compilation fix
      
      - Even yet another compilation fix
      
      - Surprise! Again compilation fix
      
      - lint fixes
      
      test=develop
      
      - Fix to workspace acquire of LRN
      
      test=develop
      
      - Fix to hash of BWD LRN
      
      test=develop
      
      - fix to lrn BWD PD acquire
      
      test=develop
      
      - Fixing LRN PD creation
      
      test=develop
      
      - cosmetic fix in comment
      
      test=develop
      
      - Fixes after review
      
      test=develop
      95c1816e
    • T
      remove unused cmake file (#18744) · 0ae45f0b
      Tao Luo 提交于
      test=develop
      0ae45f0b
    • J
      support patch data, add load_one_table, fix bug (#18509) · d18aabb4
      jiaqi 提交于
      (1)support patch data (merge slots of instances of same line id, modify dense layer which
      changes its size)
      (2)add fleet load_one_table interface, support load from paddle model and load from pslib model
      (3)fix push sparse bug which cause push sparse cost more time(about 10% in my testcase)
      (4)when some slots are not in one of your network (join/update, etc.),data feed、collect label info、push/pull sparse will skip these slots, instead of throw error.
      (5)add more debug info in TrainFilesWithProfiler
      d18aabb4
    • C
      Make fuse_optimizer_op_pass also work when the model contains sparse gradients. (#18664) · fd3aad6c
      chengduo 提交于
      * support sparse gradients
      test=develop
      fd3aad6c
    • W
      Cudnn convolution reconstruction (#18284) · 6b78e00d
      wangchaochaohu 提交于
      * rewrite the conv_op using cudnn_conv_helper
      
      * add workspace limit for v7 test=develop
      
      * fix test=develop
      
      * add half float test=develop
      
      * fix test=develop
      
      * fix test=develop
      
      * revise code style test=develop
      
      * fix test=develop
      6b78e00d
    • Y
      supports distributed classification (#18690) · 157211c4
      Yi Liu 提交于
      * supports distributed classification training
      * update API.spec
      * fix evenly division in python3
      * change "index_range" to "index_num" in shard_index operator
      test=document_preview
      test=develop
      157211c4
  3. 22 7月, 2019 11 次提交
  4. 20 7月, 2019 2 次提交
  5. 19 7月, 2019 5 次提交
  6. 18 7月, 2019 6 次提交
  7. 17 7月, 2019 5 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
    • Y
      Add cuda implementation for `prelu` backward pass (#18633) · ce1ec332
      Yang Zhang 提交于
      * Add GPU implementation for `prelu` backward pass
      
      test=develop
      
      * Fix logic error in `prelu` GPU backward and simplify a bit
      
      test=develop
      
      * Fix `prelu` backward CUDA implementation
      
      test=develop
      
      CPU version was not used actually, so test passed
      ce1ec332
    • 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
    • Y
      97549a4f
    • B
      [NGraph] handle dim element 0 of ngraph op (#18568) · 256ba7cb
      baojun 提交于
      256ba7cb
  8. 16 7月, 2019 4 次提交