Merge develop

Author: sneaxiy

.gitignore

@@ -5,6 +5,7 @@ python/paddle/v2/fluid/tests/book/image_classification_resnet.inference.model/
 python/paddle/v2/fluid/tests/book/image_classification_vgg.inference.model/
 python/paddle/v2/fluid/tests/book/label_semantic_roles.inference.model/
 *.DS_Store
+*.vs
 build/
 build_doc/
 *.user
@@ -15,6 +16,7 @@ build_doc/
 .cproject
 .pydevproject
 .settings/
+CMakeSettings.json
 Makefile
 .test_env/
 third_party/

.travis.yml

@@ -27,15 +27,6 @@ script:
     # 43min timeout
     paddle/scripts/paddle_docker_build.sh ${JOB}
     if [ $? -eq 0 ] || [ $? -eq 142 ]; then true; else exit 1; fi;
-  - |
-    if [[ "$JOB" != "doc" ]]; then exit 0; fi;
-    # For document only
-    if [[ "$TRAVIS_PULL_REQUEST" != "false" ]]; then exit 0; fi;
-    if [[ "$TRAVIS_BRANCH" != "develop"  && ! "$TRAVIS_BRANCH" =~ ^v[[:digit:]]+\.[[:digit:]]+(\.[[:digit:]]+)?(-\S*)?$ ]]; then exit 0; fi;
-    export DEPLOY_DOCS_SH=https://raw.githubusercontent.com/PaddlePaddle/PaddlePaddle.org/master/scripts/deploy/deploy_docs.sh
-    export DOCS_DIR=`pwd`
-    cd ..
-    curl $DEPLOY_DOCS_SH | bash -s $CONTENT_DEC_PASSWD $TRAVIS_BRANCH $DOCS_DIR $DOCS_DIR/build/doc/
 notifications:
   email:
     on_success: change

AUTHORS.md

@@ -46,6 +46,7 @@
 | tianbingsz | Tian-Bing Xu |
 | tpatejko | Tomasz Patejko |
 | typhoonzero | Yi Wu |
+| velconia | Qi-Yang Min |
 | wanghaoshuang | Hao-Shuang Wang |
 | wangyang59 | Yang Wang |
 | wangzhen-nlp | Zhen Wang |

CMakeLists.txt

@@ -24,6 +24,9 @@ message(STATUS "CXX compiler: ${CMAKE_CXX_COMPILER}, version: "
         "${CMAKE_CXX_COMPILER_ID} ${CMAKE_CXX_COMPILER_VERSION}")
 message(STATUS "C compiler: ${CMAKE_C_COMPILER}, version: "
         "${CMAKE_C_COMPILER_ID} ${CMAKE_C_COMPILER_VERSION}")
+if(WIN32)
+    set(CMAKE_STATIC_LIBRARY_PREFIX lib)
+endif(WIN32)
 
 if(NOT CMAKE_CROSSCOMPILING)
     find_package(CUDA QUIET)
@@ -65,7 +68,15 @@ option(REPLACE_ENFORCE_GLOG "Replace PADDLE_ENFORCE with glog/CHECK for better d
 option(WITH_ANAKIN      "Compile with Anakin library"                   OFF)
 option(WITH_GRPC     "Use grpc as the default rpc framework"            ${WITH_DISTRIBUTE})
 option(WITH_BRPC_RDMA     "Use brpc rdma as the rpc protocal"           OFF)
+option(WITH_INFERENCE    "Compile fluid inference library"              ON)
 option(WITH_SYSTEM_BLAS   "Use system blas library"           OFF)
+option(PY_VERSION       "Compile PaddlePaddle with python3 support"     ${PY_VERSION})
+
+# PY_VERSION
+if(NOT PY_VERSION)
+  set(PY_VERSION 2.7)
+endif()
+set(PYBIND11_PYTHON_VERSION ${PY_VERSION})
 
 # CMAKE_BUILD_TYPE
 if(NOT CMAKE_BUILD_TYPE)
@@ -103,6 +114,11 @@ if(ANDROID OR IOS)
     add_definitions(-DPADDLE_MOBILE_INFERENCE)
 endif()
 
+if (APPLE OR WIN32)
+    set(WITH_MKL OFF CACHE STRING
+        "Disable MKL for building on mac and windows" FORCE)
+endif()
+
 set(THIRD_PARTY_PATH "${CMAKE_BINARY_DIR}/third_party" CACHE STRING
   "A path setting third party libraries download & build directories.")
 
@@ -141,6 +157,8 @@ endif()
 ########################################################################################
 
 include(external/mklml)     # download mklml package
+include(external/xbyak)     # download xbyak package
+include(external/libxsmm)   # download, build, install libxsmm
 include(external/zlib)      # download, build, install zlib
 include(external/gflags)    # download, build, install gflags
 include(external/glog)      # download, build, install glog
@@ -150,12 +168,20 @@ include(external/python)    # download, build, install python
 include(external/openblas)  # download, build, install openblas
 include(external/mkldnn)    # download, build, install mkldnn
 include(external/swig)      # download, build, install swig
-include(external/warpctc)   # download, build, install warpctc
 include(external/boost)     # download boost
 include(external/any)       # download libn::any
 include(external/eigen)     # download eigen3
 include(external/pybind11)  # download pybind11
 include(external/cares)
+include(external/cub)
+
+if (NOT WIN32)
+# there is no official support of snappystream, warpctc, nccl, cupti in windows
+include(external/snappy)    # download snappy
+include(external/snappystream) # download snappystream
+include(external/warpctc)   # download, build, install warpctc
+include(cupti)
+endif (NOT WIN32)
 
 if(WITH_DISTRIBUTE)
     if(WITH_GRPC)
@@ -178,19 +204,27 @@ if(WITH_BRPC_RDMA)
     endif()
 endif()
 
-include(external/snappy)    # download snappy
-include(external/snappystream)
-include(external/threadpool)
 
+include(external/threadpool)
+include(flags)              # set paddle compile flags
 include(cudnn)              # set cudnn libraries, must before configure
-include(cupti)
 include(configure)          # add paddle env configuration
+
+if(WITH_GPU)
+    include(cuda)
+    include(tensorrt)
+endif()
+if(WITH_MKL OR WITH_MKLML)
+    include(external/anakin)
+elseif()
+    set(WITH_ANAKIN OFF CACHE STRING "Anakin is used in MKL only now." FORCE)
+endif()
+
 include(generic)            # simplify cmake module
 include(package)            # set paddle packages
 include(ccache)             # set ccache for compilation
 include(util)               # set unittest and link libs
 include(rdma)               # set rdma libraries
-include(flags)              # set paddle compile flags
 include(version)            # set PADDLE_VERSION
 include(coveralls)          # set code coverage
 include(inference_lib)      # add paddle fluid inference libraries
@@ -210,14 +244,6 @@ set(EXTERNAL_LIBS
     ${PYTHON_LIBRARIES}
 )
 
-if(WITH_GPU)
-    include(cuda)
-    include(tensorrt)
-    include(external/anakin)
-else()
-  set(WITH_ANAKIN OFF CACHE STRING "Anakin is valid only when GPU is set." FORCE)
-endif()
-
 if(WITH_AMD_GPU)
     find_package(HIP)
     include(hip)
@@ -227,6 +253,10 @@ if(WITH_MKLML)
     list(APPEND EXTERNAL_LIBS ${MKLML_IOMP_LIB})
 endif()
 
+if(WITH_LIBXSMM)
+    list(APPEND EXTERNAL_LIBS ${LIBXSMM_LIBS})
+endif()
+
 if(WITH_MKLDNN)
     list(APPEND EXTERNAL_LIBS ${MKLDNN_LIB})
 endif()
@@ -266,7 +296,3 @@ if(WITH_DOC)
     find_python_module(recommonmark REQUIRED)
     add_subdirectory(doc)
 endif()
-
-if (WITH_CONTRIB)
-    add_subdirectory(paddle/contrib)
-endif()

Dockerfile

@@ -53,7 +53,7 @@ RUN curl -s -q https://glide.sh/get | sh
 #    and its size is only one-third of the official one.
 # 2. Manually add ~IPluginFactory() in IPluginFactory class of NvInfer.h, otherwise, it couldn't work in paddle.
 #    See https://github.com/PaddlePaddle/Paddle/issues/10129 for details.
-RUN wget -qO- http://paddlepaddledeps.bj.bcebos.com/TensorRT-4.0.0.3.Ubuntu-16.04.4.x86_64-gnu.cuda-8.0.cudnn7.0.tar.gz | \
+RUN wget -qO- http://paddlepaddledeps.cdn.bcebos.com/TensorRT-4.0.0.3.Ubuntu-16.04.4.x86_64-gnu.cuda-8.0.cudnn7.0.tar.gz | \
     tar -xz -C /usr/local && \
     cp -rf /usr/local/TensorRT/include /usr && \
     cp -rf /usr/local/TensorRT/lib /usr
@@ -80,7 +80,7 @@ RUN pip install pre-commit 'ipython==5.3.0' && \
     pip install opencv-python
 
 #For docstring checker
-RUN pip install pylint pytest astroid isort
+RUN pip install pylint pytest astroid isort LinkChecker
 
 COPY ./python/requirements.txt /root/
 RUN pip install -r /root/requirements.txt

README.md

@@ -18,7 +18,21 @@ learning to many products at Baidu.
 Our vision is to enable deep learning for everyone via PaddlePaddle.
 Please refer to our [release announcement](https://github.com/PaddlePaddle/Paddle/releases) to track the latest feature of PaddlePaddle.
 
-### Lastest PaddlePaddle Version: [Fluid](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/fluid)
+
+### Latest PaddlePaddle Release: [Fluid 0.15.0](https://github.com/PaddlePaddle/Paddle/tree/v0.15.0)
+### Install Latest Stable Release:
+```
+# Linux CPU
+pip install paddlepaddle
+# Linux GPU cuda9cudnn7
+pip install paddlepaddle-gpu
+# Linux GPU cuda8cudnn7
+pip install paddlepaddle-gpu==0.14.0.post87
+# Linux GPU cuda8cudnn5
+pip install paddlepaddle-gpu==0.14.0.post85
+
+# For installation on other platform, refer to http://paddlepaddle.org/
+```
 
 ## Features
 
@@ -62,33 +76,26 @@ Please refer to our [release announcement](https://github.com/PaddlePaddle/Paddl
 
 ## Installation
 
-It is recommended to check out the
-[Docker installation guide](http://www.paddlepaddle.org/docs/develop/documentation/fluid/en/build_and_install/docker_install_en.html)
-before looking into the
-[build from source guide](http://www.paddlepaddle.org/docs/develop/documentation/fluid/en/build_and_install/build_from_source_en.html).
+It is recommended to read [this doc](http://paddlepaddle.org/documentation/docs/zh/0.15.0/new_docs/beginners_guide/install/install_doc.html) on our website.
 
 ## Documentation
 
-We provide [English](http://www.paddlepaddle.org/docs/develop/documentation/en/getstarted/index_en.html) and
-[Chinese](http://www.paddlepaddle.org/docs/develop/documentation/zh/getstarted/index_cn.html) documentation.
+We provide [English](http://paddlepaddle.org/documentation/docs/en/0.15.0/getstarted/index_en.html) and
+[Chinese](http://paddlepaddle.org/documentation/docs/zh/0.15.0/new_docs/beginners_guide/index.html) documentation.
 
-- [Deep Learning 101](http://www.paddlepaddle.org/docs/develop/book/01.fit_a_line/index.html)
+- [Deep Learning 101](https://github.com/PaddlePaddle/book)
 
   You might want to start from this online interactive book that can run in a Jupyter Notebook.
 
-- [Distributed Training](http://www.paddlepaddle.org/docs/develop/documentation/en/howto/cluster/index_en.html)
+- [Distributed Training](http://paddlepaddle.org/documentation/docs/zh/0.15.0/new_docs/user_guides/howto/training/cluster_howto.html)
 
   You can run distributed training jobs on MPI clusters.
 
-- [Distributed Training on Kubernetes](http://www.paddlepaddle.org/docs/develop/documentation/en/howto/cluster/multi_cluster/k8s_en.html)
-
-   You can also run distributed training jobs on Kubernetes clusters.
-
-- [Python API](http://www.paddlepaddle.org/docs/develop/api/en/overview.html)
+- [Python API](http://paddlepaddle.org/documentation/api/zh/0.15.0/fluid.html)
 
    Our new API enables much shorter programs.
 
-- [How to Contribute](http://www.paddlepaddle.org/docs/develop/documentation/fluid/en/dev/contribute_to_paddle_en.html)
+- [How to Contribute](http://paddlepaddle.org/documentation/docs/zh/0.15.0/new_docs/advanced_usage/development/contribute_to_paddle.html)
 
    We appreciate your contributions!
 

benchmark/fluid/Dockerfile

@@ -11,6 +11,7 @@ RUN ln -s /usr/lib/x86_64-linux-gnu/libcudnn.so.7 /usr/lib/libcudnn.so && ln -s
 # Add "ENV http_proxy=http://ip:port" if your download is slow, and don't forget to unset it at runtime.
 # exmaple: unset http_proxy && unset https_proxy && python fluid_benchmark.py ...
 
+
 RUN pip install -U pip
 RUN pip install -U kubernetes paddlepaddle
 
@@ -27,5 +28,6 @@ ADD *.whl /
 RUN pip install /*.whl && rm -f /*.whl 
 
 ENV LD_LIBRARY_PATH=/usr/local/lib
-ADD fluid_benchmark.py recordio_converter.py args.py recordio_converter.py run.sh run_fluid_benchmark.sh /workspace/
+ADD fluid_benchmark.py recordio_converter.py args.py recordio_converter.py run.sh run_fluid_benchmark.sh imagenet_reader.py /workspace/
 ADD models/ /workspace/models/
+

benchmark/fluid/args.py

@@ -17,7 +17,8 @@
 __all__ = ['parse_args', ]
 
 BENCHMARK_MODELS = [
-    "machine_translation", "resnet", "vgg", "mnist", "stacked_dynamic_lstm"
+    "machine_translation", "resnet", "se_resnext", "vgg", "mnist",
+    "stacked_dynamic_lstm", "resnet_with_preprocess"
 ]
 
 
@@ -67,12 +68,12 @@ def parse_args():
         '--cpus',
         type=int,
         default=1,
-        help='If cpus > 1, will use ParallelDo to run, else use Executor.')
+        help='If cpus > 1, will set ParallelExecutor to use multiple threads.')
     parser.add_argument(
         '--data_set',
         type=str,
         default='flowers',
-        choices=['cifar10', 'flowers'],
+        choices=['cifar10', 'flowers', 'imagenet'],
         help='Optional dataset for benchmark.')
     parser.add_argument(
         '--infer_only', action='store_true', help='If set, run forward only.')
@@ -122,6 +123,11 @@ def parse_args():
         type=str,
         default="",
         help='Directory that contains all the training recordio files.')
+    parser.add_argument(
+        '--test_data_path',
+        type=str,
+        default="",
+        help='Directory that contains all the test data (NOT recordio).')
     parser.add_argument(
         '--use_inference_transpiler',
         action='store_true',
@@ -130,5 +136,15 @@ def parse_args():
         '--no_random',
         action='store_true',
         help='If set, keep the random seed and do not shuffle the data.')
+    parser.add_argument(
+        '--use_lars',
+        action='store_true',
+        help='If set, use lars for optimizers, ONLY support resnet module.')
+    parser.add_argument(
+        '--reduce_strategy',
+        type=str,
+        choices=['reduce', 'all_reduce'],
+        default='all_reduce',
+        help='Specify the reduce strategy, can be reduce, all_reduce')
     args = parser.parse_args()
     return args