Merge branch 'wanghaoshuang-fix_seq' into develop

Author: wanghaoshuang

.gitignore

@@ -28,3 +28,4 @@ cmake_install.cmake
 paddle/.timestamp
 python/paddlepaddle.egg-info/
 paddle/pybind/pybind.h
+python/paddle/version.py

CMakeLists.txt

@@ -16,10 +16,14 @@ cmake_minimum_required(VERSION 3.0)
 set(CMAKE_MODULE_PATH ${CMAKE_MODULE_PATH} "${CMAKE_CURRENT_SOURCE_DIR}/cmake")
 set(PADDLE_SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR})
 set(PADDLE_BINARY_DIR ${CMAKE_CURRENT_BINARY_DIR})
+SET(CMAKE_CXX_FLAGS_RELWITHDEBINFO "-O3 -g -DNDEBUG")
+SET(CMAKE_C_FLAGS_RELWITHDEBINFO "-O3 -g -DNDEBUG")
 
 include(system)
 
 project(paddle CXX C Go)
+message(STATUS "CXX compiler: " ${CMAKE_CXX_COMPILER} ", version: " ${CMAKE_CXX_COMPILER_VERSION})
+message(STATUS "C compiler: " ${CMAKE_C_COMPILER} ", version: " ${CMAKE_C_COMPILER_VERSION})
 
 find_package(Sphinx)
 if(NOT CMAKE_CROSSCOMPILING)
@@ -56,6 +60,7 @@ option(GLIDE_INSTALL    "Download and install go dependencies "         ON)
 option(USE_NNPACK       "Compile PaddlePaddle with NNPACK library"      OFF)
 option(WITH_DISTRIBUTE  "Compile with grpc distributed support"         OFF)
 option(USE_EIGEN_FOR_BLAS   "Use matrix multiplication in Eigen"        OFF)
+option(WITH_ARM_FP16    "Use half precision support on armv8.2-a cpu"   OFF)
 
 # CMAKE_BUILD_TYPE
 if(NOT CMAKE_BUILD_TYPE)

README.md

@@ -36,7 +36,7 @@ Please refer to our [release announcement](https://github.com/PaddlePaddle/Paddl
     examples:
 
       - Optimized math operations through SSE/AVX intrinsics, BLAS libraries
-      (e.g. MKL, ATLAS, cuBLAS) or customized CPU/GPU kernels.
+      (e.g. MKL, OpenBLAS, cuBLAS) or customized CPU/GPU kernels.
       - Highly optimized recurrent networks which can handle **variable-length**
       sequence without padding.
       - Optimized local and distributed training for models with high dimensional

RELEASE.cn.md

@@ -1,3 +1,62 @@
+# v0.11.0版本
+
+## PaddlePaddle Fluid
+
+- PaddlePaddle发布版本v0.11.0包含一个新的特性*PaddlePaddle Fluid*. Fluid 是设计用来让用户像Pytorch和Tensorflow Eager Execution一样执行程序。在这些系统中，不再有*模型*这个概念，应用也不再包含一个用于描述Operator图或者一系列层的符号描述，而是像通用程序那样描述训练或者预测的过程。而Fluid与PyTorch或Eager Execution的区别在于Fluid不依赖Python提供的控制流，例如 if-else-then或者for，而是提供了基于C++实现的控制流并暴露了对应的用with语法实现的Python接口。例如：
+
+  https://github.com/PaddlePaddle/Paddle/blob/3df78ed2a98d37f7ae6725894cc7514effd5664b/python/paddle/v2/fluid/tests/test_while_op.py#L36-L44
+
+- 在v0.11.0版本中，我们提供了一个C++类`Executor`用于运行一个Fluid程序。Executor类似一个解释器。在未来的版本中，我们将提升和优化Executor成为一个调试器，就像GDB。并可能提供一些编译器，这个编译器会读取一个上文所描述的应用然后编译成一个等价的
+源代码，这个源代码可以被nvcc编译成可以使用CUDA的二进制，或者被icc编译成可以充分利用Intel CPU的二进制。
+
+
+## 新特点
+
+* 发布 `PaddlePaddle Fluid`。
+* 增加了用于模型预测的C-API。
+* 用Fluid API实现了一个简单的GAN的例子。
+* 增加了关于性能调优的文档。
+* 为`paddle.v2.dataset`下载数据集提供了重试机制.
+* C++中使用protobuf-lite替换protobuf减少了二进制的大小。
+* 发布了新特性 [Elastic Deep Learning (EDL)](https://github.com/PaddlePaddle/cloud/tree/develop/doc/autoscale/experiment).
+* 基于Bazel API利用cmake实现了一个的新的构建系统函数库。
+* 当使用编译选项`WITH_MKL=ON`时自动下载和编译Intel® [MKLML](https://github.com/01org/mkl-dnn/releases/download/v0.11/mklml_lnx_2018.0.1.20171007.tgz) 函数库.
+* [Intel® MKL-DNN on PaddlePaddle](https://github.com/PaddlePaddle/Paddle/tree/develop/doc/design/mkldnn):
+  - 完成了 11个 MKL-DNN 层: Convolution, Fully connectivity, Pooling, ReLU, Tanh, ELU, Softmax, BatchNorm, AddTo, Concat, LRN。
+  - 完成了 3个 MKL-DNN 网络: VGG-19, ResNet-50, GoogleNet
+  - 基于Intel Skylake 6148 CPU的[性能测试](https://github.com/PaddlePaddle/Paddle/blob/develop/benchmark/IntelOptimizedPaddle.md) : 相对于MKLML有2~3倍的训练加速。
+* 增加 [softsign activation](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/activation.html#softsign)
+* 增加 [dot product layer](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/layer.html#dot-prod)
+* 增加 [L2 distance layer](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/layer.html#l2-distance)
+* 增加 [sub-nested sequence layer](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/layer.html#sub-nested-seq)
+* 增加 [kmax sequence score layer](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/layer.html#kmax-sequence-score)
+* 增加 [sequence slice layer](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/layer.html#seq-slice)
+* 增加 [row convolution layer](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/layer.html#row-conv)
+* 增加移动端友好的网页
+
+## 改进
+
+* 使用一个Python`whl`包即可安装.
+* [V2 API可以实现用户定制化评估](https://github.com/PaddlePaddle/models/tree/develop/ltr#训练过程中输出自定义评估指标)。
+* 将 `PADDLE_ONLY_CPU` 改为 `PADDLE_WITH_GPU`, 因为我们会支持多种设备。
+* 删除了有一些bug的BarrierStat。
+* 清理和删除了paddle::Parameter中未使用的函数。
+* 删除了ProtoDataProvider。
+* Huber loss同时支持回归和分类。
+* 为sequence pooling 层增加`stride`参数。
+* v2 API自动使用cudnn batch normalization。
+* 可以使用一个固定的参数名共享BN层的参数。
+* 2D convolution operation支持variable-dimension input特性。
+* 重构cmake中关于CUDA的部分并实现自动检测GPU架构的功能。
+* 优化网页导航。
+
+## 错误修复
+
+* 修复ROI pooling的Bug. cc9a761
+* 修复当label是dense vector是AUC变成0的问题. #5274
+* 修复WarpCTC 层的Bug.
+
+
 # v0.10.0版本
 
 我们非常高兴发布了PaddlePaddle V0.10.0版，并开发了新的[Python API](http://research.baidu.com/paddlepaddles-new-api-simplifies-deep-learning-programs/)。

RELEASE.md

@@ -1,3 +1,75 @@
+# Release v0.11.0
+
+## PaddlePaddle Fluid
+
+- Release 0.11.0 includes a new feature *PaddlePaddle Fluid*.  Fluid is
+  designed to allow users to program like PyTorch and TensorFlow Eager Execution.
+  In these systems, there is no longer the concept *model* and applications
+  do not include a symbolic description of a graph of operators nor a sequence
+  of layers. Instead, applications look exactly like a usual program that
+  describes a process of training or inference.  The difference between
+  Fluid and PyTorch or Eager Execution is that Fluid doesn't rely on Python's
+  control-flow, `if-then-else` nor `for`.  Instead, Fluid provides its
+  C++ implementations and their Python binding using the `with` statement.  For an example
+
+  https://github.com/PaddlePaddle/Paddle/blob/3df78ed2a98d37f7ae6725894cc7514effd5664b/python/paddle/v2/fluid/tests/test_while_op.py#L36-L44
+
+- In 0.11.0, we provides a C++ class `Executor` to run a Fluid program.
+Executor works like an interpreter. In future version, we will improve
+`Executor` into a debugger like GDB, and we might provide some compilers,
+which, for example, takes an application like the above one, and outputs
+an equivalent C++ source program, which can be compiled using
+[`nvcc`](http://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html)
+to generate binaries that use CUDA, or using
+[`icc`](https://software.intel.com/en-us/c-compilers) to generate binaries
+that make full use of Intel CPUs.
+
+## New Features
+
+* Release `PaddlePaddle Fluid`.
+* Add C-API for model inference
+* Use fluid API to create a simple GAN demo.
+* Add develop guide about performance tunning.
+* Add retry when download `paddle.v2.dataset`.
+* Linking protobuf-lite not protobuf in C++. Reduce the binary size.
+* Feature [Elastic Deep Learning (EDL)](https://github.com/PaddlePaddle/cloud/tree/develop/doc/autoscale/experiment) released.
+* A new style cmake functions for Paddle. It is based on Bazel API.
+* Automatically download and compile with Intel® [MKLML](https://github.com/01org/mkl-dnn/releases/download/v0.11/mklml_lnx_2018.0.1.20171007.tgz) library as CBLAS when build `WITH_MKL=ON`.
+* [Intel® MKL-DNN on PaddlePaddle](https://github.com/PaddlePaddle/Paddle/tree/develop/doc/design/mkldnn):
+  - Complete 11 MKL-DNN layers: Convolution, Fully connectivity, Pooling, ReLU, Tanh, ELU, Softmax, BatchNorm, AddTo, Concat, LRN.
+  - Complete 3 MKL-DNN networks: VGG-19, ResNet-50, GoogleNet
+  - [Benchmark](https://github.com/PaddlePaddle/Paddle/blob/develop/benchmark/IntelOptimizedPaddle.md) on Intel Skylake 6148 CPU: 2~3x training speedup compared with MKLML.
+* Add the [`softsign` activation](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/activation.html#softsign).
+* Add the [dot product layer](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/layer.html#dot-prod).
+* Add the [L2 distance layer](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/layer.html#l2-distance).
+* Add the [sub-nested sequence layer](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/layer.html#sub-nested-seq).
+* Add the [kmax sequence score layer](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/layer.html#kmax-sequence-score).
+* Add the [sequence slice layer](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/layer.html#seq-slice).
+* Add the [row convolution layer](http://www.paddlepaddle.org/docs/develop/documentation/zh/api/v2/config/layer.html#row-conv)
+* Add mobile friendly webpages.
+
+## Improvements
+
+* Build and install using a single `whl` package.
+* [Custom evaluating in V2 API](https://github.com/PaddlePaddle/models/tree/develop/ltr#训练过程中输出自定义评估指标).
+* Change `PADDLE_ONLY_CPU` to `PADDLE_WITH_GPU`, since we will support many kinds of devices.
+* Remove buggy BarrierStat.
+* Clean and remove unused functions in paddle::Parameter.
+* Remove ProtoDataProvider.
+* Huber loss supports both regression and classification.
+* Add the `stride` parameter  for sequence pooling layers.
+* Enable v2 API use cudnn batch normalization automatically.
+* The BN layer's parameter can be shared by a fixed the parameter name.
+* Support variable-dimension input feature for 2D convolution operation.
+* Refine cmake about CUDA to automatically detect GPU architecture.
+* Improved website navigation.
+
+## Bug Fixes
+
+* Fix bug in ROI pooling. cc9a761
+* Fix AUC is zero when label is dense vector. #5274
+* Fix bug in WarpCTC layer.
+
 # Release v0.10.0
 
 We are glad to release version 0.10.0.  In this version, we are happy to release the new 

benchmark/IntelOptimizedPaddle.md

@@ -2,27 +2,25 @@
 
 Machine:
 
-- Server
- 	- Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz, 2 Sockets, 20 Cores per socket
-- Laptop
- 	- DELL XPS15-9560-R1745: i7-7700HQ 8G 256GSSD
- 	- i5 MacBook Pro (Retina, 13-inch, Early 2015)
-- Desktop
- 	- i7-6700k
+- Server: Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz, 2 Sockets, 20 Cores per socket
+- Laptop: TBD
 
 System: CentOS release 6.3 (Final), Docker 1.12.1.
 
-PaddlePaddle: paddlepaddle/paddle:latest (for MKLML and MKL-DNN), paddlepaddle/paddle:latest-openblas (for OpenBLAS)
-- MKL-DNN tag v0.11
-- MKLML 2018.0.1.20171007
-- OpenBLAS v0.2.20
-(TODO: will rerun after 0.11.0)
+PaddlePaddle: (TODO: will rerun after 0.11.0)
+- paddlepaddle/paddle:latest (for MKLML and MKL-DNN)
+  - MKL-DNN tag v0.11
+  - MKLML 2018.0.1.20171007
+- paddlepaddle/paddle:latest-openblas (for OpenBLAS)
+  - OpenBLAS v0.2.20
 
 On each machine, we will test and compare the performance of training on single node using MKL-DNN / MKLML / OpenBLAS respectively.
 
 ## Benchmark Model
 
 ### Server
+
+#### Training
 Test on batch size 64, 128, 256 on Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz
 
 Input image size - 3 * 224 * 224, Time: images/second
@@ -35,9 +33,7 @@ Input image size - 3 * 224 * 224, Time: images/second
 | MKLML        | 12.12 | 13.70 | 16.18  |
 | MKL-DNN      | 28.46 | 29.83 | 30.44  |
 
-
-chart on batch size 128
-TBD
+<img src="figs/vgg-cpu-train.png" width="500">
 
  - ResNet-50
 
@@ -47,9 +43,7 @@ TBD
 | MKLML        | 32.52 | 31.89 | 33.12  |
 | MKL-DNN      | 81.69 | 82.35 | 84.08  |
 
-
-chart on batch size 128
-TBD
+<img src="figs/resnet-cpu-train.png" width="500">
 
  - GoogLeNet
 
@@ -59,10 +53,35 @@ TBD
 | MKLML        | 128.46| 137.89| 158.63 |
 | MKL-DNN      | 250.46| 264.83| 269.50 |
 
-chart on batch size 128
-TBD
+<img src="figs/googlenet-cpu-train.png" width="500">
+
+#### Inference
+Test on batch size 1, 2, 4, 8, 16 on Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz
+- VGG-19
+
+| BatchSize | 1     | 2     | 4     | 8     | 16    |
+|-----------|-------|-------|-------|-------|-------|
+| OpenBLAS  | 1.07  | 1.08  | 1.06  | 0.88  | 0.65  |
+| MKLML     | 5.58  | 9.80  | 15.15 | 21.21 | 28.67 |
+| MKL-DNN   | 75.07 | 88.64 | 82.58 | 92.29 | 96.75 |
+
+- ResNet-50
+
+| BatchSize | 1     | 2      | 4      | 8      | 16     |
+|-----------|-------|--------|--------|--------|--------|
+| OpenBLAS  | 3.35  | 3.19   | 3.09   | 2.55   | 1.96   |
+| MKLML     | 6.33  | 12.02  | 22.88  | 40.53  | 63.09  |
+| MKL-DNN   | 107.83| 148.84 | 177.78 | 189.35 | 217.69 |
+
+
+- GoogLeNet
+
+| BatchSize | 1      | 2      | 4      | 8      | 16     |
+|-----------|--------|--------|--------|--------|--------|
+| OpenBLAS  | 12.04  | 11.31  | 10.00  | 9.07   | 4.34   |
+| MKLML     | 22.74  | 41.56  | 81.22  | 133.47 | 210.53 |
+| MKL-DNN   | 175.10 | 272.92 | 450.70 | 512.00 | 600.94 |
+
 
 ### Laptop
 TBD
-### Desktop
-TBD

benchmark/figs/googlenet-cpu-train.png

@@ -4,7 +4,7 @@ function clock_to_seconds() {
   hours=`echo $1 | awk -F ':' '{print $1}'`
   mins=`echo $1 | awk -F ':' '{print $2}'`
   secs=`echo $1 | awk -F ':' '{print $3}'`
-  echo `bc -l <<< "$secs + $mins * 60 + $hours * 3600"`
+  echo `awk 'BEGIN{printf "%.2f",('$secs' + '$mins' * 60 + '$hours' * 3600)}'`
 }
 
 function infer() {
@@ -58,9 +58,9 @@ function infer() {
   end=`tail ${log} -n 2 | head -n 1 | awk -F ' ' '{print $2}' | xargs`
   start_sec=`clock_to_seconds $start`
   end_sec=`clock_to_seconds $end`
-  fps=`bc <<< "scale = 2; 1280 / ($end_sec - $start_sec)"`
+  fps=`awk 'BEGIN{printf "%.2f",(1280 / ('$end_sec' - '$start_sec'))}'`
   echo "Last 1280 samples start: ${start}(${start_sec} sec), end: ${end}(${end_sec} sec;" >> ${log}
-  echo "FPS: $fps images/sec" >> ${log}
+  echo "FPS: $fps images/sec" 2>&1 | tee -a ${log}
 }
 
 if [ ! -f "train.list" ]; then