Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into update_simple_distranspiler

Author: velconia

AUTHORS.md

@@ -4,6 +4,7 @@
 | backyes | Yan-Fei Wang |
 | baiyfbupt | Yi-Fan Bai |
 | beckett1124 | Bin Qi |
+| ChengduoZH | Cheng-Duo Zhao|
 | chengxiaohua1105 | Xiao-Hua Cheng |
 | cxwangyi, yiwangbaidu, wangkuiyi | Yi Wang |
 | cxysteven | Xing-Yi Cheng |

Dockerfile

@@ -29,7 +29,7 @@ RUN apt-get update && \
     wget unzip unrar tar xz-utils bzip2 gzip coreutils ntp \
     curl sed grep graphviz libjpeg-dev zlib1g-dev  \
     python-matplotlib gcc-4.8 g++-4.8 \
-    automake locales clang-format swig doxygen cmake  \
+    automake locales clang-format swig cmake  \
     liblapack-dev liblapacke-dev \
     clang-3.8 llvm-3.8 libclang-3.8-dev \
     net-tools libtool ccache && \

benchmark/fluid/Dockerfile

@@ -0,0 +1,22 @@
+FROM nvidia/cuda:9.0-cudnn7-devel-ubuntu16.04
+RUN apt-get update && apt-get install -y python python-pip iputils-ping libgtk2.0-dev wget vim net-tools iftop
+RUN ln -s /usr/lib/x86_64-linux-gnu/libcudnn.so.7 /usr/lib/libcudnn.so && ln -s /usr/lib/x86_64-linux-gnu/libnccl.so.2 /usr/lib/libnccl.so
+RUN pip install -U pip
+RUN pip install -U kubernetes opencv-python paddlepaddle
+
+# IMPORTANT:
+# Add "ENV http_proxy=http://ip:port" if your download is slow, and don't forget to unset it at runtime.
+
+RUN sh -c 'echo "import paddle.v2 as paddle\npaddle.dataset.cifar.train10()\npaddle.dataset.flowers.fetch()" | python'
+RUN sh -c 'echo "import paddle.v2 as paddle\npaddle.dataset.mnist.train()\npaddle.dataset.mnist.test()\npaddle.dataset.imdb.fetch()" | python'
+RUN sh -c 'echo "import paddle.v2 as paddle\npaddle.dataset.imikolov.fetch()" | python'
+RUN pip uninstall -y paddlepaddle && mkdir /workspace
+
+ADD https://raw.githubusercontent.com/PaddlePaddle/cloud/develop/docker/paddle_k8s /usr/bin
+ADD https://raw.githubusercontent.com/PaddlePaddle/cloud/develop/docker/k8s_tools.py /root
+
+ADD *.whl /
+RUN pip install /*.whl && rm -f /*.whl && chmod +x /usr/bin/paddle_k8s
+
+ENV LD_LIBRARY_PATH=/usr/local/lib
+ADD fluid_benchmark.py dataset.py models/ /workspace/

benchmark/fluid/README.md

@@ -44,11 +44,25 @@ Currently supported `--model` argument include:
 
 ## Run Distributed Benchmark on Kubernetes Cluster
 
+You may need to build a Docker image before submitting a cluster job onto Kubernetes, or you will
+have to start all those processes mannually on each node, which is not recommended.
+
+To build the Docker image, you need to choose a paddle "whl" package to run with, you may either
+download it from
+http://www.paddlepaddle.org/docs/develop/documentation/zh/build_and_install/pip_install_en.html or
+build it by your own. Once you've got the "whl" package, put it under the current directory and run:
+
+```bash
+docker build -t [your docker image name]:[your docker image tag] .
+```
+
+Then push the image to a Docker registry that your Kubernetes cluster can reach.
+
 We provide a script `kube_gen_job.py` to generate Kubernetes yaml files to submit
 distributed benchmark jobs to your cluster. To generate a job yaml, just run:
 
 ```bash
-python kube_gen_job.py --jobname myjob --pscpu 4 --cpu 8 --gpu 8 --psmemory 20 --memory 40 --pservers 4 --trainers 4 --entry "python fluid_benchmark.py --model mnist --parallel 1 --device GPU --update_method pserver " --disttype pserver
+python kube_gen_job.py --jobname myjob --pscpu 4 --cpu 8 --gpu 8 --psmemory 20 --memory 40 --pservers 4 --trainers 4 --entry "python fluid_benchmark.py --model mnist --gpus 8 --device GPU --update_method pserver " --disttype pserver
 ```
 
 Then the yaml files are generated under directory `myjob`, you can run:

benchmark/fluid/kube_gen_job.py

@@ -49,7 +49,7 @@ def parse_args():
     parser.add_argument(
         '--fluid', default=1, type=int, help='whether is fluid job')
     parser.add_argument(
-        '--rdma', action='store_ture', help='whether mount rdma libs')
+        '--rdma', action='store_true', help='whether mount rdma libs')
     parser.add_argument(
         '--disttype',
         default="pserver",

benchmark/fluid/run.sh

@@ -37,7 +37,8 @@ nohup stdbuf -oL nvidia-smi \
       -l 1 &
 # mnist
 # mnist gpu mnist 128
-FLAGS_benchmark=true stdbuf -oL python fluid/mnist.py \
+FLAGS_benchmark=true stdbuf -oL python fluid_benchmark.py \
+               --model=mnist \
                --device=GPU \
                --batch_size=128 \
                --skip_batch_num=5 \
@@ -46,15 +47,17 @@ FLAGS_benchmark=true stdbuf -oL python fluid/mnist.py \
 
 # vgg16
 # gpu cifar10 128
-FLAGS_benchmark=true stdbuf -oL python fluid/vgg16.py \
+FLAGS_benchmark=true stdbuf -oL python fluid_benchmark.py \
+               --model=vgg16 \
                --device=GPU \
                --batch_size=128 \
                --skip_batch_num=5 \
                --iterations=30 \
                2>&1 | tee -a vgg16_gpu_128.log
 
 # flowers gpu  128
-FLAGS_benchmark=true stdbuf -oL python fluid/vgg16.py \
+FLAGS_benchmark=true stdbuf -oL python fluid_benchmark.py \
+               --model=vgg16 \
                --device=GPU \
                --batch_size=32 \
                --data_set=flowers \
@@ -64,40 +67,39 @@ FLAGS_benchmark=true stdbuf -oL python fluid/vgg16.py \
 
 # resnet50
 # resnet50 gpu cifar10 128
-FLAGS_benchmark=true stdbuf -oL python fluid/resnet50.py \
+FLAGS_benchmark=true stdbuf -oL python fluid_benchmark.py \
+               --model=resnet50 \
                --device=GPU \
                --batch_size=128 \
                --data_set=cifar10 \
-               --model=resnet_cifar10 \
                --skip_batch_num=5 \
                --iterations=30 \
                2>&1 | tee -a resnet50_gpu_128.log
 
 # resnet50 gpu flowers 64
-FLAGS_benchmark=true stdbuf -oL python fluid/resnet50.py \
+FLAGS_benchmark=true stdbuf -oL python fluid_benchmark.py \
+               --model=resnet50 \
                --device=GPU \
                --batch_size=64 \
                --data_set=flowers \
-               --model=resnet_imagenet \
                --skip_batch_num=5 \
                --iterations=30 \
                2>&1 | tee -a resnet50_gpu_flowers_64.log
 
 # lstm
 # lstm gpu imdb 32 # tensorflow only support batch=32
-FLAGS_benchmark=true stdbuf -oL python fluid/stacked_dynamic_lstm.py \
+FLAGS_benchmark=true stdbuf -oL python fluid_benchmark.py \
+               --model=stacked_dynamic_lstm \
                --device=GPU \
                --batch_size=32 \
                --skip_batch_num=5 \
                --iterations=30 \
-               --hidden_dim=512 \
-               --emb_dim=512 \
-               --crop_size=1500 \
                2>&1 | tee -a lstm_gpu_32.log
 
 # seq2seq
 # seq2seq gpu wmb 128
-FLAGS_benchmark=true stdbuf -oL python fluid/machine_translation.py \
+FLAGS_benchmark=true stdbuf -oL python fluid_benchmark.py \
+               --model=machine_translation \
                --device=GPU \
                --batch_size=128 \
                --skip_batch_num=5 \

doc/fluid/api/layers.rst

@@ -1003,9 +1003,15 @@ dice_loss
 ..  autofunction:: paddle.fluid.layers.dice_loss
     :noindex:
 
-upsampling_bilinear2d
+resize_bilinear
 ____
 
-..  autofunction:: paddle.fluid.layers.upsampling_bilinear2d
+..  autofunction:: paddle.fluid.layers.resize_bilinear
+    :noindex:
+
+gather
+____
+
+..  autofunction:: paddle.fluid.layers.gather
     :noindex:
 

doc/fluid/howto/index_cn.rst

@@ -4,5 +4,5 @@
 .. toctree::
   :maxdepth: 1
 
+  inference/index_cn.rst
   optimization/index_cn.rst
-  inference/inference_support_in_fluid.md

doc/fluid/howto/index_en.rst

@@ -5,4 +5,3 @@ HOW TO
   :maxdepth: 1
 
   optimization/index_en.rst
-  inference/inference_support_in_fluid.md

doc/fluid/howto/inference/build_and_install_lib_cn.rst

@@ -0,0 +1,96 @@
+安装与编译C++预测库
+===========================
+
+直接下载安装
+-------------
+
+======================   ========================================
+版本说明                            C++预测库   
+======================   ========================================
+cpu_avx_mkl              `fluid.tgz <https://guest:@paddleci.ngrok.io/repository/download/Manylinux1_CpuAvxCp27cp27mu/.lastSuccessful/fluid.tgz>`_ 
+cpu_avx_openblas         `fluid.tgz <https://guest:@paddleci.ngrok.io/repository/download/Manylinux1_CpuAvxOpenblas/.lastSuccessful/fluid.tgz>`_
+cpu_noavx_openblas       `fluid.tgz <https://guest:@paddleci.ngrok.io/repository/download/Manylinux1_CpuNoavxOpenblas/.lastSuccessful/fluid.tgz>`_
+cuda7.5_cudnn5_avx_mkl   `fluid.tgz <https://guest:@paddleci.ngrok.io/repository/download/Manylinux1_Cuda75cudnn5cp27cp27mu/.lastSuccessful/fluid.tgz>`_
+cuda8.0_cudnn5_avx_mkl   `fluid.tgz <https://guest:@paddleci.ngrok.io/repository/download/Manylinux1_Cuda80cudnn5cp27cp27mu/.lastSuccessful/fluid.tgz>`_
+cuda8.0_cudnn7_avx_mkl   `fluid.tgz <https://guest:@paddleci.ngrok.io/repository/download/Manylinux1_Cuda8cudnn7cp27cp27mu/.lastSuccessful/fluid.tgz>`_
+======================   ========================================
+
+从源码编译
+----------
+用户也可以从 PaddlePaddle 核心代码编译C++预测库，只需在编译时配制下面这些编译选项：
+
+=================   =========
+选项                 值   
+=================   =========
+CMAKE_BUILD_TYPE    Release
+FLUID_INSTALL_DIR   安装路径    
+WITH_FLUID_ONLY     ON（推荐）
+WITH_SWIG_PY        OFF（推荐
+WITH_PYTHON         OFF（推荐）
+WITH_GPU            ON/OFF
+WITH_MKL            ON/OFF
+=================   =========
+
+建议按照推荐值设置，以避免链接不必要的库。其它可选编译选项按需进行设定。
+
+下面的代码片段从github拉取最新代码，配制编译选项（需要将PADDLE_ROOT替换为PaddlePaddle预测库的安装路径）：
+
+  .. code-block:: bash
+
+     pip install paddlepaddle-gpu
+     PADDLE_ROOT=/path/of/capi
+     git clone https://github.com/PaddlePaddle/Paddle.git
+     cd Paddle
+     mkdir build
+     cd build
+     cmake -DFLUID_INSTALL_DIR=$PADDLE_ROOT \
+           -DCMAKE_BUILD_TYPE=Release \
+           -DWITH_FLUID_ONLY=ON \
+           -DWITH_SWIG_PY=OFF \
+           -DWITH_PYTHON=OFF \
+           -DWITH_MKL=OFF \
+           -DWITH_GPU=OFF  \
+           ..
+      make
+      make inference_lib_dist
+
+成功编译后，使用C++预测库所需的依赖（包括：（1）编译出的PaddlePaddle预测库和头文件；（2）第三方链接库和头文件；（3）版本信息与编译选项信息）
+均会存放于PADDLE_ROOT目录中。目录结构如下：
+
+  .. code-block:: text
+
+     PaddleRoot/
+     ├── CMakeCache.txt
+     ├── paddle
+     │   └── fluid
+     │       ├── framework
+     │       ├── inference
+     │       ├── memory
+     │       ├── platform
+     │       ├── pybind
+     │       └── string
+     ├── third_party
+     │   ├── boost
+     │   │   └── boost
+     │   ├── eigen3
+     │   │   ├── Eigen
+     │   │   └── unsupported
+     │   └── install
+     │       ├── gflags
+     │       ├── glog
+     │       ├── mklml
+     │       ├── protobuf
+     │       ├── snappy
+     │       ├── snappystream
+     │       └── zlib
+     └── version.txt
+     
+version.txt 中记录了该预测库的版本信息，包括Git Commit ID、使用OpenBlas或MKL数学库、CUDA/CUDNN版本号，如：
+
+  .. code-block:: text
+
+     GIT COMMIT ID: c95cd4742f02bb009e651a00b07b21c979637dc8
+     WITH_MKL: ON
+     WITH_GPU: ON
+     CUDA version: 8.0
+     CUDNN version: v5