Skip to content

P
Paddle

PaddlePaddle / Paddle
1 年多 前同步成功

通知 2302
Star 20931
Fork 5422
P
Paddle
切换分支/标签
  1. 10 12月, 2019 8 次提交
  3. 09 12月, 2019 3 次提交
    • L
      QAT Int8 document (#21360) · fbf9eca0
      由 lidanqing 提交于 
      * update benchmark for int8v2, QAT1, QAT2 accuracy and performance
test=document_fix

* change according to reviews
test=develop test=document_fix

* improve some descriptions and some models
test=develop test=document_fix

* update models benchmark data
test=develop test=document_fix

* update int8v2 and qat2 performance
test=develop test=document_fix
      fbf9eca0
    • L
      Refine VarBase init function (#21587) · 4f81d1bd
      由 Leo Chen 提交于 
      * refine init function, test=develop

* add tests, test=develop

* remove extern, which may cause symbol error in gcc-4.8, test=develop
      4f81d1bd
    • L
      dygraph_grad_maker supports varbase without grad_var (#21524) · 84b72671
      由 Leo Chen 提交于 
      * dygraph_grad_maker supports varbase without grad_var, test=develop

* fix compile, test=develop

* fix test_tracer, test=develop

* follow comments, test=develop
      84b72671
  5. 07 12月, 2019 1 次提交
  7. 06 12月, 2019 8 次提交
    • Z
      Polish op registry codes (#21561) · 0f888836
      由 Zeng Jinle 提交于 
      * polish infer shape registry, test=develop

* modify some operators registry, test=develop
      0f888836
    • A
      Set lod_level of Out in compile time of sequence_pool_op (#21604) · 3d9dee57
      由 Aurelius84 提交于
      3d9dee57
    • Z
      refine dev_ctx.Wait() exception throw, test=develop (#21600) · 97e76cb9
      由 Zeng Jinle 提交于
      97e76cb9
    • H
      Add Much Complex Test and Fix Bugs for Control Flow cond API (#21532) · 1dcf6a72
      由 Huihuang Zheng 提交于 
      Add tests to use dy/dx to make sure the gradient values calculated by the control flow backward is correct. Also fixed bugs detected by those tests.

Fix bugs:

1. Unlike sum_op, optimizer ops don't allow uninitialized input tensor. But in conditional_block_grad_op, since the conditional_block may not run, the output gradient tensor may be uninitialized, which will cause the optimizer op error. To fix it, we should let optimizer ops support uninitialized input like sum_op or assign the uninitialized gradient to 0 when the conditional_block_grad_op doesn't run. I found there are about 10+ optimizer ops. **To be simpler, I just assign output gradient of the conditional_block_grad_op to 0 in this PR**. But it can be further explored whether we can make optimizer ops like sum_op to support uninitialized input tensor because theoretically we can speed up without the assigning in conditional_block_grad_op.

2. Infer parameter shapes during append_backward. I didn't know that all our parameters are in global block. When op_desc is inferring shapes at the sub-block, it may not know the shape of gradients of parameters whose shape information is at global block. I fixed it by inferring shapes of gradients from forward var.

This PR also did some code clean up:
1. Print the var name when sgd_op catches shape error so that it is easier to debug
2. Fix a typo: dicta -> dict
      1dcf6a72
    • H
      Paddlebox Related to Framework (#21586) · c5aec2fe
      由 hutuxian 提交于 
      * Add a single_process_multi_thread transpiler.
* Add some UTs.
* Fix some API description.
      c5aec2fe
    • L
      add file check_op_desc.py and add interface to get default value. (#21530) · 9da7e6b4
      由 liym27 提交于 
      * add file check_op_desc.py and add interface to get default value. test=develop

* add test for c++ coverage rate. test=develop

* Correct typo. test=develop
      9da7e6b4
    • J
      - Fix to regression in performance of ResNet-50 training (#21588) · 8f5a93a0
      由 Jacek Czaja 提交于 
      test=develop
      8f5a93a0
    • J
      [MKL-DNN] Batch norm mkl-dnn NHWC support (#21553) · 9ce0e29d
      由 Jacek Czaja 提交于 
      * - BAtch norm mkl-dnn NHWC

test=develop

- compilation fix

test=develop

- UT fix

- cosmetics

test=develop

- Fix to Batch Norm MKL-DNN NHWC UT

test=develop

Conflicts:
	paddle/fluid/operators/batch_norm_op.h

* - Lint fixes

test=develop
      9ce0e29d
  9. 05 12月, 2019 5 次提交
    • Z
      add grad maker assert, test=develop (#21564) · 3a7caf48
      由 Zeng Jinle 提交于
      3a7caf48
    • H
      Refine a Warning Which Can Occur Not Only During Init (#21546) · b241c732
      由 Huihuang Zheng 提交于 
      As the title
      b241c732
    • P
      fix glog warning, test=develop (#21573) · 20d61414
      由 Pei Yang 提交于
      20d61414
    • W
      Add Branch to avoid CPU profiler warning print (#21556) · 932aca16
      由 wangchaochaohu 提交于 
      
* fix profiler warning message in cpu profile mode test=develop
      932aca16
    • L
      Split VarBase from Python Variable for Dygraph (#21359) · cdd46d7e
      由 Leo Chen 提交于 
      * test=develop, fix docker with paddle nccl problem

* don't expose numerous Tensor.set(), test=develop

* fix condition, test=develop

* fix float16 bug, test=develop

* feed should be Tensor or np.array, not Variable or number, test=develop

* use forcecast to copy numpy slice to new array, test=develop

* remove float16-uint16 hacking, test=develop

* add variable method to varbase and refactor to_variable to support return varbase

* support kwargs in varbase constructor

* add VarBase constructor to support default python args

* refine varbase initial method

* reset branch

* fix ut for change VarBase error info to PaddleEnforce

* cherry is parameter change before

* overload isinstance to replace too many change of is_variable

* rm useless files

* rm useless code merged by git

* test=develop, fix some ut failed error

* test=develop, fix test_graph_wrapper

* add some tests, test=develop

* refine __getitem__, test=develop

* add tests, test=develop

* fix err_msg, test=develop
      cdd46d7e
  11. 04 12月, 2019 7 次提交
  13. 03 12月, 2019 8 次提交