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

demo/mnist/api_train_v2.py

@@ -44,6 +44,19 @@ def main():
             batch_size=32),
         event_handler=event_handler)
 
+    # output is a softmax layer. It returns probabilities.
+    # Shape should be (100, 10)
+    probs = paddle.infer(
+        output=inference,
+        parameters=parameters,
+        reader=paddle.reader.batched(
+            paddle.reader.firstn(
+                paddle.reader.map_readers(lambda item: (item[0], ),
+                                          paddle.dataset.mnist.test()),
+                n=100),
+            batch_size=32))
+    print probs.shape
+
 
 if __name__ == '__main__':
     main()

paddle/scripts/docker/Dockerfile

@@ -5,38 +5,50 @@ ARG DEBIAN_FRONTEND=noninteractive
 ARG UBUNTU_MIRROR
 RUN /bin/bash -c 'if [[ -n ${UBUNTU_MIRROR} ]]; then sed -i 's#http://archive.ubuntu.com#${UBUNTU_MIRROR}#g' /etc/apt/sources.list; fi'
 
+# ENV variables
+ARG BUILD_WOBOQ
+ARG BUILD_AND_INSTALL
+ARG WITH_AVX
+ARG WITH_DOC
+ARG WITH_STYLE_CHECK
+
+ENV BUILD_WOBOQ=${BUILD_WOBOQ:-OFF}
+ENV BUILD_AND_INSTALL=${BUILD_AND_INSTALL:-OFF}
+ENV WITH_GPU=OFF
+ENV WITH_AVX=${WITH_AVX:-ON}
+ENV WITH_DOC=${WITH_DOC:-OFF}
+ENV WITH_STYLE_CHECK=${WITH_STYLE_CHECK:-OFF}
+
+ENV HOME /root
+
+# Add bash enhancements
+COPY ./paddle/scripts/docker/root/ /root/
+
 RUN apt-get update && \
     apt-get install -y git python-pip python-dev openssh-server bison && \
     apt-get install -y wget unzip tar xz-utils bzip2 gzip coreutils && \
     apt-get install -y curl sed grep graphviz libjpeg-dev zlib1g-dev && \
     apt-get install -y python-numpy python-matplotlib gcc g++ gfortran && \
-    apt-get install -y automake && \
+    apt-get install -y automake locales clang-format-3.8 && \
     apt-get clean -y
 
+# git credential to skip password typing
+RUN git config --global credential.helper store
+
+# Fix locales to en_US.UTF-8
+RUN localedef -i en_US -f UTF-8 en_US.UTF-8
+
 RUN pip install --upgrade pip && \
-    pip install -U "protobuf==3.1.0" && \
+    pip install -U 'protobuf==3.1.0' && \
     pip install -U wheel pillow BeautifulSoup && \
     pip install -U docopt PyYAML sphinx && \
-    pip install -U sphinx_rtd_theme recommonmark jupyter
+    pip install -U sphinx_rtd_theme recommonmark && \
+    pip install -U pre-commit 'requests==2.9.2' jupyter
 
 RUN curl -sSL https://cmake.org/files/v3.4/cmake-3.4.1.tar.gz | tar -xz && \
     cd cmake-3.4.1 && ./bootstrap && make -j `nproc` && make install && \
     cd .. && rm -rf cmake-3.4.1
 
-ARG BUILD_WOBOQ
-ARG BUILD_AND_INSTALL
-ARG WITH_AVX
-ARG WITH_DOC
-ARG WITH_STYLE_CHECK
-
-ENV BUILD_WOBOQ=${BUILD_WOBOQ:-OFF}
-ENV BUILD_AND_INSTALL=${BUILD_AND_INSTALL:-OFF}
-ENV WITH_GPU=OFF
-ENV WITH_AVX=${WITH_AVX:-ON}
-ENV WITH_DOC=${WITH_DOC:-OFF}
-ENV WITH_STYLE_CHECK=${WITH_STYLE_CHECK:-OFF}
-
-RUN mkdir /paddle
 COPY . /paddle/
 RUN /paddle/paddle/scripts/docker/build.sh
 VOLUME ["/usr/share/nginx/html/data", "/usr/share/nginx/html/paddle"]
@@ -53,7 +65,6 @@ RUN mkdir /notes/
 WORKDIR "/notes"
 EXPOSE 8888
 
-RUN mkdir -p /opt/bin
 COPY ./paddle/scripts/docker/entrypoint /opt/bin/
 
 CMD ["/opt/bin/entrypoint"]

paddle/scripts/docker/Dockerfile.gpu

@@ -5,38 +5,50 @@ ARG DEBIAN_FRONTEND=noninteractive
 ARG UBUNTU_MIRROR
 RUN /bin/bash -c 'if [[ -n ${UBUNTU_MIRROR} ]]; then sed -i 's#http://archive.ubuntu.com#${UBUNTU_MIRROR}#g' /etc/apt/sources.list; fi'
 
+# ENV variables
+ARG BUILD_WOBOQ
+ARG BUILD_AND_INSTALL
+ARG WITH_AVX
+ARG WITH_DOC
+ARG WITH_STYLE_CHECK
+
+ENV BUILD_WOBOQ=${BUILD_WOBOQ:-OFF}
+ENV BUILD_AND_INSTALL=${BUILD_AND_INSTALL:-OFF}
+ENV WITH_GPU=ON
+ENV WITH_AVX=${WITH_AVX:-ON}
+ENV WITH_DOC=${WITH_DOC:-OFF}
+ENV WITH_STYLE_CHECK=${WITH_STYLE_CHECK:-OFF}
+
+ENV HOME /root
+
+# Add bash enhancements
+COPY ./paddle/scripts/docker/root/ /root/
+
 RUN apt-get update && \
     apt-get install -y git python-pip python-dev openssh-server bison && \
     apt-get install -y wget unzip tar xz-utils bzip2 gzip coreutils && \
     apt-get install -y curl sed grep graphviz libjpeg-dev zlib1g-dev && \
     apt-get install -y python-numpy python-matplotlib gcc g++ gfortran && \
-    apt-get install -y automake && \
+    apt-get install -y automake locales clang-format-3.8 && \
     apt-get clean -y
 
+# git credential to skip password typing
+RUN git config --global credential.helper store
+
+# Fix locales to en_US.UTF-8
+RUN localedef -i en_US -f UTF-8 en_US.UTF-8
+
 RUN pip install --upgrade pip && \
-    pip install -U "protobuf==3.1.0" && \
+    pip install -U 'protobuf==3.1.0' && \
     pip install -U wheel pillow BeautifulSoup && \
     pip install -U docopt PyYAML sphinx && \
-    pip install -U sphinx_rtd_theme recommonmark jupyter
+    pip install -U sphinx_rtd_theme recommonmark && \
+    pip install -U pre-commit 'requests==2.9.2' jupyter
 
 RUN curl -sSL https://cmake.org/files/v3.4/cmake-3.4.1.tar.gz | tar -xz && \
     cd cmake-3.4.1 && ./bootstrap && make -j `nproc` && make install && \
     cd .. && rm -rf cmake-3.4.1
 
-ARG BUILD_WOBOQ
-ARG BUILD_AND_INSTALL
-ARG WITH_AVX
-ARG WITH_DOC
-ARG WITH_STYLE_CHECK
-
-ENV BUILD_WOBOQ=${BUILD_WOBOQ:-OFF}
-ENV BUILD_AND_INSTALL=${BUILD_AND_INSTALL:-OFF}
-ENV WITH_GPU=ON
-ENV WITH_AVX=${WITH_AVX:-ON}
-ENV WITH_DOC=${WITH_DOC:-OFF}
-ENV WITH_STYLE_CHECK=${WITH_STYLE_CHECK:-OFF}
-
-RUN mkdir /paddle
 COPY . /paddle/
 RUN /paddle/paddle/scripts/docker/build.sh
 VOLUME ["/usr/share/nginx/html/data", "/usr/share/nginx/html/paddle"]
@@ -53,7 +65,6 @@ RUN mkdir /notes/
 WORKDIR "/notes"
 EXPOSE 8888
 
-RUN mkdir -p /opt/bin
 COPY ./paddle/scripts/docker/entrypoint /opt/bin/
 
 CMD ["/opt/bin/entrypoint"]

paddle/scripts/docker/root/.bashrc

+# Locales
+
+export LC_ALL=en_US.UTF-8
+export LANG=en_US.UTF-8
+export LANGUAGE=en_US.UTF-8
+
+# Aliases
+
+alias rm='rm -i'
+alias cp='cp -i'
+alias mv='mv -i'
+
+alias ls='ls -hFG'
+alias l='ls -lF'
+alias ll='ls -alF'
+alias lt='ls -ltrF'
+alias ll='ls -alF'
+alias lls='ls -alSrF'
+alias llt='ls -altrF'
+
+# Colorize directory listing
+
+alias ls="ls -ph --color=auto"
+
+# Colorize grep
+
+if echo hello|grep --color=auto l >/dev/null 2>&1; then
+  export GREP_OPTIONS="--color=auto" GREP_COLOR="1;31"
+fi
+
+# Shell
+
+export CLICOLOR="1"
+
+YELLOW="\[\033[1;33m\]"
+NO_COLOUR="\[\033[0m\]"
+GREEN="\[\033[1;32m\]"
+WHITE="\[\033[1;37m\]"
+
+source ~/.scripts/git-prompt.sh
+
+export PS1="\[\033[1;33m\]λ $WHITE\h $GREEN\w$YELLOW\$(__git_ps1 \" \[\033[35m\]{\[\033[36m\]%s\[\033[35m\]}\")$NO_COLOUR "
+
+# Git
+
+source ~/.scripts/git-completion.sh

paddle/scripts/docker/root/.gitconfig

+[user]
+  name =
+  email =
+
+[alias]
+  st = status --branch --short
+  ci = commit
+  br = branch
+  co = checkout
+  df = diff
+  l = log --pretty=format:\"%h %ad | %s%d [%an]\" --graph --date=short
+  ll = log --stat
+
+[merge]
+  tool = vimdiff
+
+[core]
+  excludesfile = ~/.gitignore
+  editor = vim
+
+[color]
+  branch = auto
+  diff = auto
+  status = auto
+
+[color "branch"]
+  current = yellow reverse
+  local = yellow
+  remote = green
+
+[color "diff"]
+  meta = yellow bold
+  frag = magenta bold
+  old = red bold
+  new = green bold
+
+[color "status"]
+  added = yellow
+  changed = green
+  untracked = cyan
+
+[push]
+  default = matching
\ No newline at end of file

paddle/scripts/docker/root/.scripts/git-prompt.sh

+# bash/zsh git prompt support
+#
+# Copyright (C) 2006,2007 Shawn O. Pearce <spearce@spearce.org>
+# Distributed under the GNU General Public License, version 2.0.
+#
+# This script allows you to see repository status in your prompt.
+#
+# To enable:
+#
+#    1) Copy this file to somewhere (e.g. ~/.git-prompt.sh).
+#    2) Add the following line to your .bashrc/.zshrc:
+#        source ~/.git-prompt.sh
+#    3a) Change your PS1 to call __git_ps1 as
+#        command-substitution:
+#        Bash: PS1='[\u@\h \W$(__git_ps1 " (%s)")]\$ '
+#        ZSH:  setopt PROMPT_SUBST ; PS1='[%n@%m %c$(__git_ps1 " (%s)")]\$ '
+#        the optional argument will be used as format string.
+#    3b) Alternatively, for a slightly faster prompt, __git_ps1 can
+#        be used for PROMPT_COMMAND in Bash or for precmd() in Zsh
+#        with two parameters, <pre> and <post>, which are strings
+#        you would put in $PS1 before and after the status string
+#        generated by the git-prompt machinery.  e.g.
+#        Bash: PROMPT_COMMAND='__git_ps1 "\u@\h:\w" "\\\$ "'
+#          will show username, at-sign, host, colon, cwd, then
+#          various status string, followed by dollar and SP, as
+#          your prompt.
+#        ZSH:  precmd () { __git_ps1 "%n" ":%~$ " "|%s" }
+#          will show username, pipe, then various status string,
+#          followed by colon, cwd, dollar and SP, as your prompt.
+#        Optionally, you can supply a third argument with a printf
+#        format string to finetune the output of the branch status
+#
+# The repository status will be displayed only if you are currently in a
+# git repository. The %s token is the placeholder for the shown status.
+#
+# The prompt status always includes the current branch name.
+#
+# In addition, if you set GIT_PS1_SHOWDIRTYSTATE to a nonempty value,
+# unstaged (*) and staged (+) changes will be shown next to the branch
+# name.  You can configure this per-repository with the
+# bash.showDirtyState variable, which defaults to true once
+# GIT_PS1_SHOWDIRTYSTATE is enabled.
+#
+# You can also see if currently something is stashed, by setting
+# GIT_PS1_SHOWSTASHSTATE to a nonempty value. If something is stashed,
+# then a '$' will be shown next to the branch name.
+#
+# If you would like to see if there're untracked files, then you can set
+# GIT_PS1_SHOWUNTRACKEDFILES to a nonempty value. If there're untracked
+# files, then a '%' will be shown next to the branch name.  You can
+# configure this per-repository with the bash.showUntrackedFiles
+# variable, which defaults to true once GIT_PS1_SHOWUNTRACKEDFILES is
+# enabled.
+#
+# If you would like to see the difference between HEAD and its upstream,
+# set GIT_PS1_SHOWUPSTREAM="auto".  A "<" indicates you are behind, ">"
+# indicates you are ahead, "<>" indicates you have diverged and "="
+# indicates that there is no difference. You can further control
+# behaviour by setting GIT_PS1_SHOWUPSTREAM to a space-separated list
+# of values:
+#
+#     verbose       show number of commits ahead/behind (+/-) upstream
+#     legacy        don't use the '--count' option available in recent
+#                   versions of git-rev-list
+#     git           always compare HEAD to @{upstream}
+#     svn           always compare HEAD to your SVN upstream
+#
+# By default, __git_ps1 will compare HEAD to your SVN upstream if it can
+# find one, or @{upstream} otherwise.  Once you have set
+# GIT_PS1_SHOWUPSTREAM, you can override it on a per-repository basis by
+# setting the bash.showUpstream config variable.
+#
+# If you would like to see more information about the identity of
+# commits checked out as a detached HEAD, set GIT_PS1_DESCRIBE_STYLE
+# to one of these values:
+#
+#     contains      relative to newer annotated tag (v1.6.3.2~35)
+#     branch        relative to newer tag or branch (master~4)
+#     describe      relative to older annotated tag (v1.6.3.1-13-gdd42c2f)
+#     default       exactly matching tag
+#
+# If you would like a colored hint about the current dirty state, set
+# GIT_PS1_SHOWCOLORHINTS to a nonempty value. The colors are based on
+# the colored output of "git status -sb" and are available only when
+# using __git_ps1 for PROMPT_COMMAND or precmd.
+
+# stores the divergence from upstream in $p
+# used by GIT_PS1_SHOWUPSTREAM
+__git_ps1_show_upstream ()
+{
+  local key value
+  local svn_remote svn_url_pattern count n
+  local upstream=git legacy="" verbose=""
+
+  svn_remote=()
+  # get some config options from git-config
+  local output="$(git config -z --get-regexp '^(svn-remote\..*\.url|bash\.showupstream)$' 2>/dev/null | tr '\0\n' '\n ')"
+  while read -r key value; do
+    case "$key" in
+    bash.showupstream)
+      GIT_PS1_SHOWUPSTREAM="$value"
+      if [[ -z "${GIT_PS1_SHOWUPSTREAM}" ]]; then
+        p=""
+        return
+      fi
+      ;;
+    svn-remote.*.url)
+      svn_remote[$((${#svn_remote[@]} + 1))]="$value"
+      svn_url_pattern+="\\|$value"
+      upstream=svn+git # default upstream is SVN if available, else git
+      ;;
+    esac
+  done <<< "$output"
+
+  # parse configuration values
+  for option in ${GIT_PS1_SHOWUPSTREAM}; do
+    case "$option" in
+    git|svn) upstream="$option" ;;
+    verbose) verbose=1 ;;
+    legacy)  legacy=1  ;;
+    esac
+  done
+
+  # Find our upstream
+  case "$upstream" in
+  git)    upstream="@{upstream}" ;;
+  svn*)
+    # get the upstream from the "git-svn-id: ..." in a commit message
+    # (git-svn uses essentially the same procedure internally)
+    local -a svn_upstream
+    svn_upstream=($(git log --first-parent -1 \
+          --grep="^git-svn-id: \(${svn_url_pattern#??}\)" 2>/dev/null))
+    if [[ 0 -ne ${#svn_upstream[@]} ]]; then
+      svn_upstream=${svn_upstream[${#svn_upstream[@]} - 2]}
+      svn_upstream=${svn_upstream%@*}
+      local n_stop="${#svn_remote[@]}"
+      for ((n=1; n <= n_stop; n++)); do
+        svn_upstream=${svn_upstream#${svn_remote[$n]}}
+      done
+
+      if [[ -z "$svn_upstream" ]]; then
+        # default branch name for checkouts with no layout:
+        upstream=${GIT_SVN_ID:-git-svn}
+      else
+        upstream=${svn_upstream#/}
+      fi
+    elif [[ "svn+git" = "$upstream" ]]; then
+      upstream="@{upstream}"
+    fi
+    ;;
+  esac
+
+  # Find how many commits we are ahead/behind our upstream
+  if [[ -z "$legacy" ]]; then
+    count="$(git rev-list --count --left-right \
+        "$upstream"...HEAD 2>/dev/null)"
+  else
+    # produce equivalent output to --count for older versions of git
+    local commits
+    if commits="$(git rev-list --left-right "$upstream"...HEAD 2>/dev/null)"
+    then
+      local commit behind=0 ahead=0
+      for commit in $commits
+      do
+        case "$commit" in
+        "<"*) ((behind++)) ;;
+        *)    ((ahead++))  ;;
+        esac
+      done
+      count="$behind  $ahead"
+    else
+      count=""
+    fi
+  fi
+
+  # calculate the result
+  if [[ -z "$verbose" ]]; then
+    case "$count" in
+    "") # no upstream
+      p="" ;;
+    "0  0") # equal to upstream
+      p="=" ;;
+    "0  "*) # ahead of upstream
+      p=">" ;;
+    *"  0") # behind upstream
+      p="<" ;;
+    *)      # diverged from upstream
+      p="<>" ;;
+    esac
+  else
+    case "$count" in
+    "") # no upstream
+      p="" ;;
+    "0  0") # equal to upstream
+      p=" u=" ;;
+    "0  "*) # ahead of upstream
+      p=" u+${count#0 }" ;;
+    *"  0") # behind upstream
+      p=" u-${count%  0}" ;;
+    *)      # diverged from upstream
+      p=" u+${count#* }-${count%  *}" ;;
+    esac
+  fi
+
+}
+
+# Helper function that is meant to be called from __git_ps1.  It
+# injects color codes into the appropriate gitstring variables used
+# to build a gitstring.
+__git_ps1_colorize_gitstring ()
+{
+  if [[ -n ${ZSH_VERSION-} ]]; then
+    local c_red='%F{red}'
+    local c_green='%F{green}'
+    local c_lblue='%F{blue}'
+    local c_clear='%f'
+  else
+    # Using \[ and \] around colors is necessary to prevent
+    # issues with command line editing/browsing/completion!
+    local c_red='\[\e[31m\]'
+    local c_green='\[\e[32m\]'
+    local c_lblue='\[\e[1;34m\]'
+    local c_clear='\[\e[0m\]'
+  fi
+  local bad_color=$c_red
+  local ok_color=$c_green
+  local flags_color="$c_lblue"
+
+  local branch_color=""
+  if [ $detached = no ]; then
+    branch_color="$ok_color"
+  else
+    branch_color="$bad_color"
+  fi
+  c="$branch_color$c"
+
+  z="$c_clear$z"
+  if [ "$w" = "*" ]; then
+    w="$bad_color$w"
+  fi
+  if [ -n "$i" ]; then
+    i="$ok_color$i"
+  fi
+  if [ -n "$s" ]; then
+    s="$flags_color$s"
+  fi
+  if [ -n "$u" ]; then
+    u="$bad_color$u"
+  fi
+  r="$c_clear$r"
+}
+
+# __git_ps1 accepts 0 or 1 arguments (i.e., format string)
+# when called from PS1 using command substitution
+# in this mode it prints text to add to bash PS1 prompt (includes branch name)
+#
+# __git_ps1 requires 2 or 3 arguments when called from PROMPT_COMMAND (pc)
+# in that case it _sets_ PS1. The arguments are parts of a PS1 string.
+# when two arguments are given, the first is prepended and the second appended
+# to the state string when assigned to PS1.
+# The optional third parameter will be used as printf format string to further
+# customize the output of the git-status string.
+# In this mode you can request colored hints using GIT_PS1_SHOWCOLORHINTS=true
+__git_ps1 ()
+{
+  local pcmode=no
+  local detached=no
+  local ps1pc_start='\u@\h:\w '
+  local ps1pc_end='\$ '
+  local printf_format=' (%s)'
+
+  case "$#" in
+    2|3)  pcmode=yes
+      ps1pc_start="$1"
+      ps1pc_end="$2"
+      printf_format="${3:-$printf_format}"
+    ;;
+    0|1)  printf_format="${1:-$printf_format}"
+    ;;
+    *)  return
+    ;;
+  esac
+
+  local repo_info rev_parse_exit_code
+  repo_info="$(git rev-parse --git-dir --is-inside-git-dir \
+    --is-bare-repository --is-inside-work-tree \
+    --short HEAD 2>/dev/null)"
+  rev_parse_exit_code="$?"
+
+  if [ -z "$repo_info" ]; then
+    if [ $pcmode = yes ]; then
+      #In PC mode PS1 always needs to be set
+      PS1="$ps1pc_start$ps1pc_end"
+    fi
+    return
+  fi
+
+  local short_sha
+  if [ "$rev_parse_exit_code" = "0" ]; then
+    short_sha="${repo_info##*$'\n'}"
+    repo_info="${repo_info%$'\n'*}"
+  fi
+  local inside_worktree="${repo_info##*$'\n'}"
+  repo_info="${repo_info%$'\n'*}"
+  local bare_repo="${repo_info##*$'\n'}"
+  repo_info="${repo_info%$'\n'*}"
+  local inside_gitdir="${repo_info##*$'\n'}"
+  local g="${repo_info%$'\n'*}"
+
+  local r=""
+  local b=""
+  local step=""
+  local total=""
+  if [ -d "$g/rebase-merge" ]; then
+    read b 2>/dev/null <"$g/rebase-merge/head-name"
+    read step 2>/dev/null <"$g/rebase-merge/msgnum"
+    read total 2>/dev/null <"$g/rebase-merge/end"
+    if [ -f "$g/rebase-merge/interactive" ]; then
+      r="|REBASE-i"
+    else
+      r="|REBASE-m"
+    fi
+  else
+    if [ -d "$g/rebase-apply" ]; then
+      read step 2>/dev/null <"$g/rebase-apply/next"
+      read total 2>/dev/null <"$g/rebase-apply/last"
+      if [ -f "$g/rebase-apply/rebasing" ]; then
+        read b 2>/dev/null <"$g/rebase-apply/head-name"
+        r="|REBASE"
+      elif [ -f "$g/rebase-apply/applying" ]; then
+        r="|AM"
+      else
+        r="|AM/REBASE"
+      fi
+    elif [ -f "$g/MERGE_HEAD" ]; then
+      r="|MERGING"
+    elif [ -f "$g/CHERRY_PICK_HEAD" ]; then
+      r="|CHERRY-PICKING"
+    elif [ -f "$g/REVERT_HEAD" ]; then
+      r="|REVERTING"
+    elif [ -f "$g/BISECT_LOG" ]; then
+      r="|BISECTING"
+    fi
+
+    if [ -n "$b" ]; then
+      :
+    elif [ -h "$g/HEAD" ]; then
+      # symlink symbolic ref
+      b="$(git symbolic-ref HEAD 2>/dev/null)"
+    else
+      local head=""
+      if ! read head 2>/dev/null <"$g/HEAD"; then
+        if [ $pcmode = yes ]; then
+          PS1="$ps1pc_start$ps1pc_end"
+        fi
+        return
+      fi
+      # is it a symbolic ref?
+      b="${head#ref: }"
+      if [ "$head" = "$b" ]; then
+        detached=yes
+        b="$(
+        case "${GIT_PS1_DESCRIBE_STYLE-}" in
+        (contains)
+          git describe --contains HEAD ;;
+        (branch)
+          git describe --contains --all HEAD ;;
+        (describe)
+          git describe HEAD ;;
+        (* | default)
+          git describe --tags --exact-match HEAD ;;
+        esac 2>/dev/null)" ||
+
+        b="$short_sha..."
+        b="($b)"
+      fi
+    fi
+  fi
+
+  if [ -n "$step" ] && [ -n "$total" ]; then
+    r="$r $step/$total"
+  fi
+
+  local w=""
+  local i=""
+  local s=""
+  local u=""
+  local c=""
+  local p=""
+
+  if [ "true" = "$inside_gitdir" ]; then
+    if [ "true" = "$bare_repo" ]; then
+      c="BARE:"
+    else
+      b="GIT_DIR!"
+    fi
+  elif [ "true" = "$inside_worktree" ]; then
+    if [ -n "${GIT_PS1_SHOWDIRTYSTATE-}" ] &&
+       [ "$(git config --bool bash.showDirtyState)" != "false" ]
+    then
+      git diff --no-ext-diff --quiet --exit-code || w="*"
+      if [ -n "$short_sha" ]; then
+        git diff-index --cached --quiet HEAD -- || i="+"
+      else
+        i="#"
+      fi
+    fi
+    if [ -n "${GIT_PS1_SHOWSTASHSTATE-}" ] &&
+       [ -r "$g/refs/stash" ]; then
+      s="$"
+    fi
+
+    if [ -n "${GIT_PS1_SHOWUNTRACKEDFILES-}" ] &&
+       [ "$(git config --bool bash.showUntrackedFiles)" != "false" ] &&
+       git ls-files --others --exclude-standard --error-unmatch -- '*' >/dev/null 2>/dev/null
+    then
+      u="%${ZSH_VERSION+%}"
+    fi
+
+    if [ -n "${GIT_PS1_SHOWUPSTREAM-}" ]; then
+      __git_ps1_show_upstream
+    fi
+  fi
+
+  local z="${GIT_PS1_STATESEPARATOR-" "}"
+
+  # NO color option unless in PROMPT_COMMAND mode
+  if [ $pcmode = yes ] && [ -n "${GIT_PS1_SHOWCOLORHINTS-}" ]; then
+    __git_ps1_colorize_gitstring
+  fi
+
+  local f="$w$i$s$u"
+  local gitstring="$c${b##refs/heads/}${f:+$z$f}$r$p"
+
+  if [ $pcmode = yes ]; then
+    if [[ -n ${ZSH_VERSION-} ]]; then
+      gitstring=$(printf -- "$printf_format" "$gitstring")
+    else
+      printf -v gitstring -- "$printf_format" "$gitstring"
+    fi
+    PS1="$ps1pc_start$gitstring$ps1pc_end"
+  else
+    printf -- "$printf_format" "$gitstring"
+  fi
+}

python/paddle/v2/__init__.py

@@ -24,13 +24,14 @@ from . import dataset
 from . import reader
 import attr
 import pooling
+import inferencer
 import networks
 import py_paddle.swig_paddle as api
 
 __all__ = [
     'optimizer', 'layer', 'activation', 'parameters', 'init', 'trainer',
     'event', 'data_type', 'attr', 'pooling', 'data_feeder', 'dataset', 'reader',
-    'topology', 'networks'
+    'topology', 'networks', 'inferencer', 'infer'
 ]
 
 
@@ -40,3 +41,6 @@ def init(**kwargs):
         args.append('--%s=%s' % (key, str(kwargs[key])))
 
     api.initPaddle(*args)
+
+
+infer = inferencer.infer

python/paddle/v2/dataset/mnist.py

@@ -48,6 +48,7 @@ def reader_creator(image_filename, label_filename, buffer_size):
         l = subprocess.Popen([zcat_cmd, label_filename], stdout=subprocess.PIPE)
         l.stdout.read(8)  # skip some magic bytes
 
+        try:  # reader could be break.
             while True:
                 labels = numpy.fromfile(
                     l.stdout, 'ubyte', count=buffer_size).astype("int")
@@ -63,7 +64,7 @@ def reader_creator(image_filename, label_filename, buffer_size):
 
                 for i in xrange(buffer_size):
                     yield images[i, :], int(labels[i])
-
+        finally:
             m.terminate()
             l.terminate()
 

python/paddle/v2/inferencer.py

+import py_paddle.swig_paddle as api
+
+import topology
+from data_feeder import DataFeeder
+import itertools
+import numpy
+
+__all__ = ['Inference', 'infer']
+
+
+class Inference(object):
+    def __init__(self, output, parameters):
+        topo = topology.Topology(output)
+        gm = api.GradientMachine.createFromConfigProto(
+            topo.proto(), api.CREATE_MODE_TESTING, [api.PARAMETER_VALUE])
+        for param in gm.getParameters():
+            val = param.getBuf(api.PARAMETER_VALUE)
+            name = param.getName()
+            assert isinstance(val, api.Vector)
+            val.copyFromNumpyArray(parameters.get(name).flatten())
+        self.__gradient_machine__ = gm
+        self.__data_types__ = topo.data_type()
+
+    def iter_infer(self, reader, reader_dict=None):
+        if reader_dict is None:
+            reader_dict = self.default_reader_dict()
+        feeder = DataFeeder(self.__data_types__, reader_dict)
+        self.__gradient_machine__.start()
+        for data_batch in reader():
+            yield self.__gradient_machine__.forwardTest(feeder(data_batch))
+        self.__gradient_machine__.finish()
+
+    def iter_infer_field(self, field, **kwargs):
+        for result in self.iter_infer(**kwargs):
+            yield [each_result[field] for each_result in result]
+
+    def infer(self, field='value', **kwargs):
+        retv = None
+        for result in self.iter_infer_field(field=field, **kwargs):
+            if retv is None:
+                retv = [[]] * len(result)
+            for i, item in enumerate(result):
+                retv[i].append(item)
+        retv = [numpy.concatenate(out) for out in retv]
+        if len(retv) == 1:
+            return retv[0]
+        else:
+            return retv
+
+    def default_reader_dict(self):
+        reader_dict = dict()
+        for i, tp in enumerate(self.__data_types__):
+            reader_dict[tp[0]] = i
+        return reader_dict
+
+
+def infer(output, parameters, reader, reader_dict=None, field='value'):
+    inferer = Inference(output=output, parameters=parameters)
+    return inferer.infer(field=field, reader=reader, reader_dict=reader_dict)

python/paddle/v2/reader/decorator.py

@@ -14,13 +14,13 @@
 
 __all__ = [
     'map_readers', 'buffered', 'compose', 'chain', 'shuffle',
-    'ComposeNotAligned', 'batched'
+    'ComposeNotAligned', 'batched', 'firstn'
 ]
 
-from Queue import Queue
-from threading import Thread
 import itertools
 import random
+from Queue import Queue
+from threading import Thread
 
 
 def map_readers(func, *readers):
@@ -213,3 +213,20 @@ def batched(reader, batch_size):
             yield batch
 
     return batched_reader
+
+
+def firstn(reader, n):
+    """
+    Limit the max number of samples that reader could return.
+    """
+
+    # TODO(yuyang18): Check if just drop the reader, could clean the opened
+    # resource or not?
+
+    def firstn_reader():
+        for i, item in enumerate(reader()):
+            if i == n:
+                break
+            yield item
+
+    return firstn_reader