Modified: incubator/singa/site/trunk/en/docs/installation.html URL: http://svn.apache.org/viewvc/incubator/singa/site/trunk/en/docs/installation.html?rev=1779877&r1=1779876&r2=1779877&view=diff ============================================================================== --- incubator/singa/site/trunk/en/docs/installation.html (original) +++ incubator/singa/site/trunk/en/docs/installation.html Mon Jan 23 04:55:46 2017 @@ -92,24 +92,20 @@ <li class="toctree-l1"><a class="reference internal" href="../downloads.html">Download SINGA</a></li> <li class="toctree-l1 current"><a class="reference internal" href="index.html">Documentation</a><ul class="current"> <li class="toctree-l2 current"><a class="current reference internal" href="">Installation</a><ul> -<li class="toctree-l3"><a class="reference internal" href="#install-pysinga">Install PySINGA</a><ul> -<li class="toctree-l4"><a class="reference internal" href="#install-dependent-libraries">Install dependent libraries</a></li> +<li class="toctree-l3"><a class="reference internal" href="#from-wheel">From wheel</a><ul> +<li class="toctree-l4"><a class="reference internal" href="#pre-requisite">Pre-requisite</a></li> <li class="toctree-l4"><a class="reference internal" href="#virtual-environment">Virtual environment</a></li> -<li class="toctree-l4"><a class="reference internal" href="#from-wheel">From wheel</a></li> -<li class="toctree-l4"><a class="reference internal" href="#from-source">From source</a></li> +<li class="toctree-l4"><a class="reference internal" href="#instructions">Instructions</a></li> </ul> </li> -<li class="toctree-l3"><a class="reference internal" href="#install-singa-from-debian-package">Install SINGA from Debian Package</a></li> -<li class="toctree-l3"><a class="reference internal" href="#use-singa-docker-images">Use SINGA Docker Images</a></li> -<li class="toctree-l3"><a class="reference internal" href="#compile-singa-from-source-on-linux-and-mac-os">Compile SINGA from source on Linux and Mac OS</a><ul> -<li class="toctree-l4"><a class="reference internal" href="#compile-singa-together-with-dependent-libraries">Compile SINGA together with dependent libraries</a></li> -<li class="toctree-l4"><a class="reference internal" href="#install-dependent-libraries-and-then-compile-singa">Install dependent libraries and then compile SINGA</a></li> -<li class="toctree-l4"><a class="reference internal" href="#compile-singa-with-cuda-and-cudnn">Compile SINGA with CUDA and CUDNN</a></li> -<li class="toctree-l4"><a class="reference internal" href="#compile-singa-with-opencl-support-linux">Compile SINGA with OpenCL support (Linux)</a></li> +<li class="toctree-l3"><a class="reference internal" href="#from-debian-package">From Debian Package</a></li> +<li class="toctree-l3"><a class="reference internal" href="#from-source">From source</a><ul> +<li class="toctree-l4"><a class="reference internal" href="#pre-requisite">Pre-requisite</a></li> +<li class="toctree-l4"><a class="reference internal" href="#instructions">Instructions</a></li> +<li class="toctree-l4"><a class="reference internal" href="#linux-and-mac-os">Linux and Mac OS</a></li> +<li class="toctree-l4"><a class="reference internal" href="#compile-singa-on-windows">Compile SINGA on Windows</a></li> </ul> </li> -<li class="toctree-l3"><a class="reference internal" href="#build-singa-on-windows">Build SINGA on Windows</a></li> -<li class="toctree-l3"><a class="reference internal" href="#build-the-debian-packages">Build the Debian packages</a></li> <li class="toctree-l3"><a class="reference internal" href="#faq">FAQ</a></li> </ul> </li> @@ -127,7 +123,7 @@ <li class="toctree-l2"><a class="reference internal" href="snapshot.html">Snapshot</a></li> <li class="toctree-l2"><a class="reference internal" href="converter.html">Caffe Converter</a></li> <li class="toctree-l2"><a class="reference internal" href="utils.html">Utils</a></li> -<li class="toctree-l2"><a class="reference internal" href="examples/index.html">Examples</a></li> +<li class="toctree-l2"><a class="reference internal" href="model_zoo/index.html">Model Zoo</a></li> </ul> </li> </ul> @@ -190,12 +186,13 @@ <div class="section" id="installation"> <span id="installation"></span><h1>Installation<a class="headerlink" href="#installation" title="Permalink to this headline">¶</a></h1> -<div class="section" id="install-pysinga"> -<span id="install-pysinga"></span><h2>Install PySINGA<a class="headerlink" href="#install-pysinga" title="Permalink to this headline">¶</a></h2> -<p>PySINGA has been tested on Linux (Ubunu 14.04 and 16.04) and Mac OS (10.11 and 10.12).</p> -<div class="section" id="install-dependent-libraries"> -<span id="install-dependent-libraries"></span><h3>Install dependent libraries<a class="headerlink" href="#install-dependent-libraries" title="Permalink to this headline">¶</a></h3> -<p>Python 2.7 is required to run PySINGA.</p> +<div class="section" id="from-wheel"> +<span id="from-wheel"></span><h2>From wheel<a class="headerlink" href="#from-wheel" title="Permalink to this headline">¶</a></h2> +<p>Users can download the pre-compiled wheel files to install PySINGA. +PySINGA has been tested on Linux (Ubunu 14.04 and 16.04) and Mac OS (10.11 and 10.12).</p> +<div class="section" id="pre-requisite"> +<span id="pre-requisite"></span><h3>Pre-requisite<a class="headerlink" href="#pre-requisite" title="Permalink to this headline">¶</a></h3> +<p>Python 2.7 and pip are required</p> <div class="highlight-python"><div class="highlight"><pre># For Ubuntu $ sudo apt-get install python2.7-dev python-pip @@ -204,6 +201,8 @@ $ brew tap homebrew/python $ brew install python </pre></div> </div> +<p>Note for Mac OS, you need to configure the (python) paths correctly if multiple python versions are installed. +Refer to FAQ for the errors and solutions.</p> </div> <div class="section" id="virtual-environment"> <span id="virtual-environment"></span><h3>Virtual environment<a class="headerlink" href="#virtual-environment" title="Permalink to this headline">¶</a></h3> @@ -223,14 +222,14 @@ $ source activate pysinga <p>Note that in python virtual environment, you may need to reset the <code class="docutils literal"><span class="pre">PYTHONPATH</span></code> to empty to avoid the conflicts of system path and virtual environment path.</p> </div> -<div class="section" id="from-wheel"> -<span id="from-wheel"></span><h3>From wheel<a class="headerlink" href="#from-wheel" title="Permalink to this headline">¶</a></h3> -<p>Currently, we have the following wheel files,</p> +<div class="section" id="instructions"> +<span id="instructions"></span><h3>Instructions<a class="headerlink" href="#instructions" title="Permalink to this headline">¶</a></h3> +<p>Currently, the following wheel files are available,</p> <table border="1"> <tr> <th>OS</th> <th>Device</th> - <th>CUDA/CUDNN</th> + <th>CUDA/cuDNN</th> <th>Link</th> </tr> <tr> @@ -242,13 +241,13 @@ to avoid the conflicts of system path an <tr> <td>Ubuntu14.04</td> <td>GPU</td> - <td>CUDA7.5+CUDNN4</td> + <td>CUDA7.5+cuDNN4</td> <td><a href="http://comp.nus.edu.sg/~dbsystem/singa/assets/file/wheel/linux/latest/ubuntu14.04-cuda7.5-cudnn4/";>latest</a>, <a href="http://www.comp.nus.edu.sg/~dbsystem/singa/assets/file/wheel/linux";>history</a></td> </tr> <tr> <td>Ubuntu14.04</td> <td>GPU</td> - <td>CUDA7.5+CUDNN5</td> + <td>CUDA7.5+cuDNN5</td> <td><a href="http://comp.nus.edu.sg/~dbsystem/singa/assets/file/wheel/linux/latest/ubuntu14.04-cuda7.5-cudnn5/";>latest</a>, <a href="http://www.comp.nus.edu.sg/~dbsystem/singa/assets/file/wheel/linux";>history</a></td> </tr> <tr> @@ -260,7 +259,7 @@ to avoid the conflicts of system path an <tr> <td>Ubuntu16.04</td> <td>GPU</td> - <td>CUDA8.0+CUDNN5</td> + <td>CUDA8.0+cuDNN5</td> <td><a href="http://comp.nus.edu.sg/~dbsystem/singa/assets/file/wheel/linux/latest/ubuntu16.04-cuda8.0-cudnn5/";>latest</a>, <a href="http://www.comp.nus.edu.sg/~dbsystem/singa/assets/file/wheel/linux";>history</a></td> </tr> <tr> @@ -279,138 +278,74 @@ to avoid the conflicts of system path an <div class="highlight-python"><div class="highlight"><pre>$ pip install --upgrade <path to the whel file> </pre></div> </div> -<p>To install the wheel file compiled with CUDA, you need to install CUDA and export the <code class="docutils literal"><span class="pre">LD_LIBRARY_PATH</span></code> to CUDNN before running the above instruction.</p> +<p>To install the wheel file compiled with CUDA, you need to install CUDA and export the <code class="docutils literal"><span class="pre">LD_LIBRARY_PATH</span></code> to cuDNN before running the above instruction.</p> <p>If you have sudo right, you can run the above commands using <code class="docutils literal"><span class="pre">sudo</span> <span class="pre">pip</span> <span class="pre">install</span></code> without python virtual environment. The option <code class="docutils literal"><span class="pre">--upgrade</span></code> may cause errors sometimes, in which case you can ignore it.</p> </div> -<div class="section" id="from-source"> -<span id="from-source"></span><h3>From source<a class="headerlink" href="#from-source" title="Permalink to this headline">¶</a></h3> -<p>To build the PySINGA from source, the following dependent libraries are required,</p> -<ul class="simple"> -<li>swig(>=3.0.10)</li> -<li>numpy(>=1.11.0)</li> -</ul> -<p>They can be installed by</p> -<div class="highlight-python"><div class="highlight"><pre>$ Ubuntu 14.04 and 16.04 -$ sudo apt-get install python-numpy -# Ubuntu 16.04 -$ sudo apt-get install swig -</pre></div> -</div> -<p>Note that swig has to be installed from source on Ubuntu 14.04. -After installing numpy, export the header path of numpy.i as</p> -<div class="highlight-python"><div class="highlight"><pre>$ export CPLUS_INCLUDE_PATH=`python -c "import numpy; print numpy.get_include()"`:$CPLUS_INCLUDE_PATH -</pre></div> -</div> -<p><strong>compile SINGA from source</strong> (see the next section) with <code class="docutils literal"><span class="pre">cmake</span> <span class="pre">-DUSE_PYTHON=ON</span> <span class="pre">..</span></code>, -and then run the following commands,</p> -<div class="highlight-python"><div class="highlight"><pre># under the build directory -$ cd python -$ pip install . -</pre></div> -</div> -<p>Developers can build the wheel file via</p> -<div class="highlight-python"><div class="highlight"><pre># under the build directory -$ cd python -$ python setup.py bdist_wheel -</pre></div> -</div> -<p>The generated wheel file is under “dist” directory.</p> -</div> </div> -<div class="section" id="install-singa-from-debian-package"> -<span id="install-singa-from-debian-package"></span><h2>Install SINGA from Debian Package<a class="headerlink" href="#install-singa-from-debian-package" title="Permalink to this headline">¶</a></h2> -<p>We have prepared the Debian packages (on architecture: amd64) for SINGA as listed below,</p> +<div class="section" id="from-debian-package"> +<span id="from-debian-package"></span><h2>From Debian Package<a class="headerlink" href="#from-debian-package" title="Permalink to this headline">¶</a></h2> +<p>The following Debian packages (on architecture: amd64) are available</p> <table border="1"> <tr> <th>OS</th> <th>Device</th> - <th>CUDA/CUDNN</th> + <th>CUDA/cuDNN</th> <th>Link</th> </tr> <tr> <td>Ubuntu14.04</td> <td>CPU</td> <td>-</td> - <td><a href="http://comp.nus.edu.sg/~dbsystem/singa/assets/file/debian/latest/ubuntu14.04-cpp/";>latest</a>, <a href="http://www.comp.nus.edu.sg/~dbsystem/singa/assets/file/debian";>history</a></td> + <td><a href="http://comp.nus.edu.sg/~dbsystem/singa/assets/file/debian/latest/ubuntu14.04-cpp/python-singa.deb";>latest</a>, <a href="http://www.comp.nus.edu.sg/~dbsystem/singa/assets/file/debian";>history</a></td> </tr> <tr> <td>Ubuntu14.04</td> <td>GPU</td> - <td>CUDA7.5+CUDNN4</td> + <td>CUDA7.5+cuDNN4</td> <td>coming soon</td> </tr> <tr> <td>Ubuntu14.04</td> <td>GPU</td> - <td>CUDA7.5+CUDNN5</td> + <td>CUDA7.5+cuDNN5</td> <td>coming soon</td> </tr> <tr> <td>Ubuntu16.04</td> <td>CPU</td> <td>-</td> - <td><a href="http://comp.nus.edu.sg/~dbsystem/singa/assets/file/debian/latest/ubuntu16.04-cpp/";>latest</a>, <a href="http://www.comp.nus.edu.sg/~dbsystem/singa/assets/file/debian";>history</a></td> + <td><a href="http://comp.nus.edu.sg/~dbsystem/singa/assets/file/debian/latest/ubuntu16.04-cpp/python-singa.deb";>latest</a>, <a href="http://www.comp.nus.edu.sg/~dbsystem/singa/assets/file/debian";>history</a></td> </tr> <tr> <td>Ubuntu16.04</td> <td>GPU</td> - <td>CUDA8.0+CUDNN5</td> + <td>CUDA8.0+cuDNN5</td> <td>coming soon</td> </tr> </table><p>Download the deb file and install it via</p> <div class="highlight-python"><div class="highlight"><pre>apt-get install <path to the deb file, e.g., ./python-singa.deb> </pre></div> </div> -<p>To create the Debian packages, please refer to the README.md file under <code class="docutils literal"><span class="pre">SINGA_ROOT/tool/debian</span></code>.</p> -</div> -<div class="section" id="use-singa-docker-images"> -<span id="use-singa-docker-images"></span><h2>Use SINGA Docker Images<a class="headerlink" href="#use-singa-docker-images" title="Permalink to this headline">¶</a></h2> -<p>A list of Docker images with SINGA installed are available on <a class="reference external" href="https://hub.docker.com/r/nusdbsystem/singa/";>Dockerhub</a>. -To use the image, run</p> -<div class="highlight-python"><div class="highlight"><pre># for images built without CUDA -$ docker run -it nusdbsystem/singa:<tag> /bin/bash -# for images built with CUDA support -$ nvidia-docker run -it nusdbsystem/singa:<tag> /bin/bash -</pre></div> -</div> -<p>All available tags and descriptions are on <a class="reference external" href="https://hub.docker.com/r/nusdbsystem/singa/";>Dockerhub</a> and <a class="reference external" href="https://github.com/apache/incubator-singa/blob/master/tool/docker/README.md";>Github</a></p> +<p>Note that the path must include <code class="docutils literal"><span class="pre">./</span></code> if the file in inside the current folder.</p> </div> -<div class="section" id="compile-singa-from-source-on-linux-and-mac-os"> -<span id="compile-singa-from-source-on-linux-and-mac-os"></span><h2>Compile SINGA from source on Linux and Mac OS<a class="headerlink" href="#compile-singa-from-source-on-linux-and-mac-os" title="Permalink to this headline">¶</a></h2> +<div class="section" id="from-source"> +<span id="from-source"></span><h2>From source<a class="headerlink" href="#from-source" title="Permalink to this headline">¶</a></h2> <p>The source files could be downloaded either as a <a class="reference external" href="https://dist.apache.org/repos/dist/dev/incubator/singa/";>tar.gz file</a>, or as a git repo</p> <div class="highlight-python"><div class="highlight"><pre>$ git clone https://github.com/apache/incubator-singa.git $ cd incubator-singa/ </pre></div> </div> -<p>cmake (>=2.8) is used for compile SINGA, which can be installed by</p> -<div class="highlight-python"><div class="highlight"><pre># For Ubuntu 14.04 and 16.04 -$ sudo apt-get install cmake -</pre></div> -</div> -<p>GCC (>=4.8.1) is required to compile SINGA on Linux. -For Mac OS users, you can use either GCC or Clang.</p> -<div class="section" id="compile-singa-together-with-dependent-libraries"> -<span id="compile-singa-together-with-dependent-libraries"></span><h3>Compile SINGA together with dependent libraries<a class="headerlink" href="#compile-singa-together-with-dependent-libraries" title="Permalink to this headline">¶</a></h3> -<p>SINGA code uses CBLAS and Protobuf (>=2.5, <3). -If they are not installed in your OS, you can compile SINGA together with them</p> -<div class="highlight-python"><div class="highlight"><pre>$ In SINGA ROOT folder -$ mkdir build -$ cd build -$ cmake -DUSE_MODULES=ON .. -$ make -</pre></div> -</div> -<p>cmake would download OpenBlas and Protobuf (2.6.1) and compile them together -with SINGA.</p> -</div> -<div class="section" id="install-dependent-libraries-and-then-compile-singa"> -<span id="install-dependent-libraries-and-then-compile-singa"></span><h3>Install dependent libraries and then compile SINGA<a class="headerlink" href="#install-dependent-libraries-and-then-compile-singa" title="Permalink to this headline">¶</a></h3> -<p>Users can also install the dependent libraries and then link SINGA with them.</p> +<div class="section" id="pre-requisite"> +<span id="id1"></span><h3>Pre-requisite<a class="headerlink" href="#pre-requisite" title="Permalink to this headline">¶</a></h3> <p>The following libraries are required</p> <ul class="simple"> +<li>cmake (>=2.8)</li> +<li>gcc (>=4.8.1) or Clang</li> <li>google protobuf (>=2.5,<3)</li> <li>blas (tested with openblas >=0.2.10)</li> +<li>swig(>=3.0.10) for compiling PySINGA</li> +<li>numpy(>=1.11.0) for compiling PySINGA</li> </ul> <p>The following libraries are optional</p> <ul class="simple"> @@ -418,9 +353,32 @@ with SINGA.</p> <li>lmdb (tested with 0.9)</li> <li>glog</li> </ul> +</div> +<div class="section" id="instructions"> +<span id="id2"></span><h3>Instructions<a class="headerlink" href="#instructions" title="Permalink to this headline">¶</a></h3> +<ol class="simple"> +<li>create a <code class="docutils literal"><span class="pre">build</span></code> folder inside incubator-singa and go into that folder</li> +<li>run <code class="docutils literal"><span class="pre">cmake</span> <span class="pre">[options]</span> <span class="pre">..</span></code> +by default all options are OFF except <code class="docutils literal"><span class="pre">USE_PYTHON</span></code><ul> +<li><code class="docutils literal"><span class="pre">USE_MODUELS=ON</span></code>, used if protobuf and blas are not installed a prior</li> +<li><code class="docutils literal"><span class="pre">USE_CUDA=ON</span></code>, used if CUDA and cuDNN is available</li> +<li><code class="docutils literal"><span class="pre">USE_PYTHON=ON</span></code>, used for compiling PySINGA</li> +<li><code class="docutils literal"><span class="pre">USE_OPENCL=ON</span></code>, used for compiling with OpenCL support</li> +</ul> +</li> +<li>compile the code, e.g., <code class="docutils literal"><span class="pre">make</span></code></li> +<li>goto python folder</li> +<li>run <code class="docutils literal"><span class="pre">pip</span> <span class="pre">install</span> <span class="pre">.</span></code></li> +<li>[optional] run <code class="docutils literal"><span class="pre">python</span> <span class="pre">setup.py</span> <span class="pre">bdist_wheel</span></code> to generate the wheel file</li> +</ol> +<p>Step 4 and 5 are to install PySINGA. +Details on the installation of dependent libraries and the instructions for each OS are given in the following sections.</p> +</div> +<div class="section" id="linux-and-mac-os"> +<span id="linux-and-mac-os"></span><h3>Linux and Mac OS<a class="headerlink" href="#linux-and-mac-os" title="Permalink to this headline">¶</a></h3> <p>Most of the dependent libraries could be installed from source or via package mangers like apt-get, yum, and homebrew. Please refer to FAQ for problems caused by the path setting of the dependent libraries.</p> -<p>The following instructions are tested on Ubuntu 14.04 for installing dependent libraries.</p> +<p>The following instructions are tested on Ubuntu 14.04 and 16.04for installing dependent libraries.</p> <div class="highlight-python"><div class="highlight"><pre># required libraries $ sudo apt-get install libprotobuf-dev libopenblas-dev protobuf-compiler @@ -429,9 +387,7 @@ $ sudo apt-get install python2.7-dev pyt $ sudo apt-get install libopencv-dev libgoogle-glog-dev liblmdb-dev </pre></div> </div> -<p>Note that PySINGA requires swig >=3.0, which could be installed via -apt-get on Ubuntu 16.04; but it has to be installed from source for other Ubuntu versions including 14.04.</p> -<p>The following instructions are tested on Mac OS X Yosemite (10.10.5) for installing dependent libraries.</p> +<p>The following instructions are tested on Mac OS X Yosemite (10.11 and 10.12) for installing dependent libraries.</p> <div class="highlight-python"><div class="highlight"><pre># required libraries $ brew tap homebrew/science $ brew install openblas @@ -454,20 +410,24 @@ $ export CMAKE_LIBRARY_PATH=/usr/local/o <div class="highlight-python"><div class="highlight"><pre>$ export LD_LIBRARY_PATH=/usr/local/opt/openblas/library:$LD_LIBRARY_PATH </pre></div> </div> -<p>With the dependent libraries installed, SINGA can be compiled via</p> -<div class="highlight-python"><div class="highlight"><pre>$ mkdir build +<div class="section" id="compile-with-use-modules-on"> +<span id="compile-with-use-modules-on"></span><h4>Compile with USE_MODULES=ON<a class="headerlink" href="#compile-with-use-modules-on" title="Permalink to this headline">¶</a></h4> +<p>If protobuf and openblas are not installed, you can compile SINGA together with them</p> +<div class="highlight-python"><div class="highlight"><pre>$ In SINGA ROOT folder +$ mkdir build $ cd build -$ cmake .. +$ cmake -DUSE_MODULES=ON .. $ make -$ make install </pre></div> </div> +<p>cmake would download OpenBlas and Protobuf (2.6.1) and compile them together +with SINGA.</p> <p>After compiling SINGA, you can run the unit tests by</p> <div class="highlight-python"><div class="highlight"><pre>$ ./bin/test_singa </pre></div> </div> <p>You can see all the testing cases with testing results. If SINGA passes all -tests, then you have successfully installed SINGA. Please proceed to try the examples!</p> +tests, then you have successfully installed SINGA.</p> <p>You can use <code class="docutils literal"><span class="pre">ccmake</span> <span class="pre">..</span></code> to configure the compilation options. If some dependent libraries are not in the system default paths, you need to export the following environment variables</p> @@ -476,12 +436,40 @@ export CMAKE_LIBRARY_PATH=<path to th </pre></div> </div> </div> -<div class="section" id="compile-singa-with-cuda-and-cudnn"> -<span id="compile-singa-with-cuda-and-cudnn"></span><h3>Compile SINGA with CUDA and CUDNN<a class="headerlink" href="#compile-singa-with-cuda-and-cudnn" title="Permalink to this headline">¶</a></h3> +<div class="section" id="compile-with-use-python-on"> +<span id="compile-with-use-python-on"></span><h4>Compile with USE_PYTHON=ON<a class="headerlink" href="#compile-with-use-python-on" title="Permalink to this headline">¶</a></h4> +<p>swig and numpy can be install by</p> +<div class="highlight-python"><div class="highlight"><pre>$ Ubuntu 14.04 and 16.04 +$ sudo apt-get install python-numpy +# Ubuntu 16.04 +$ sudo apt-get install swig +</pre></div> +</div> +<p>Note that swig has to be installed from source on Ubuntu 14.04. +After installing numpy, export the header path of numpy.i as</p> +<div class="highlight-python"><div class="highlight"><pre>$ export CPLUS_INCLUDE_PATH=`python -c "import numpy; print numpy.get_include()"`:$CPLUS_INCLUDE_PATH +</pre></div> +</div> +<p>Similar to compile CPP code, PySINGA is compiled by</p> +<div class="highlight-python"><div class="highlight"><pre>$ cmake -DUSE_PYTHON=ON .. +$ make +$ cd python +$ pip install . +</pre></div> +</div> +<p>Developers can build the wheel file via</p> +<div class="highlight-python"><div class="highlight"><pre># under the build directory +$ cd python +</pre></div> +</div> +<p>The generated wheel file is under “dist” directory.</p> +</div> +<div class="section" id="compile-singa-with-use-cuda-on"> +<span id="compile-singa-with-use-cuda-on"></span><h4>Compile SINGA with USE_CUDA=ON<a class="headerlink" href="#compile-singa-with-use-cuda-on" title="Permalink to this headline">¶</a></h4> <p>Users are encouraged to install the CUDA and -<a class="reference external" href="https://developer.nvidia.com/cudnn";>CUDNN</a> for running SINGA on GPUs to +<a class="reference external" href="https://developer.nvidia.com/cudnn";>cuDNN</a> for running SINGA on GPUs to get better performance.</p> -<p>SINGA has been tested over CUDA (7, 7.5, 8), and CUDNN (4 and 5). If CUDNN is +<p>SINGA has been tested over CUDA (7, 7.5, 8), and cuDNN (4 and 5). If cuDNN is decompressed into non-system folder, e.g. /home/bob/local/cudnn/, the following commands should be executed for cmake and the runtime to find it</p> <div class="highlight-python"><div class="highlight"><pre>$ export CMAKE_INCLUDE_PATH=/home/bob/local/cudnn/include:$CMAKE_INCLUDE_PATH @@ -489,17 +477,14 @@ $ export CMAKE_LIBRARY_PATH=/home/bob/lo $ export LD_LIBRARY_PATH=/home/bob/local/cudnn/lib64:$LD_LIBRARY_PATH </pre></div> </div> -<p>The cmake options for CUDA and CUDNN should be switched on</p> +<p>The cmake options for CUDA and cuDNN should be switched on</p> <div class="highlight-python"><div class="highlight"><pre># Dependent libs are install already $ cmake -DUSE_CUDA=ON .. - -# Compile dependent libs together with SINGA -$ cmake -DUSE_CUDA=ON -DUSE_MODULES=ON .. </pre></div> </div> </div> -<div class="section" id="compile-singa-with-opencl-support-linux"> -<span id="compile-singa-with-opencl-support-linux"></span><h3>Compile SINGA with OpenCL support (Linux)<a class="headerlink" href="#compile-singa-with-opencl-support-linux" title="Permalink to this headline">¶</a></h3> +<div class="section" id="compile-singa-with-use-opencl-on"> +<span id="compile-singa-with-use-opencl-on"></span><h4>Compile SINGA with USE_OPENCL=ON<a class="headerlink" href="#compile-singa-with-use-opencl-on" title="Permalink to this headline">¶</a></h4> <p>SINGA uses opencl-headers and viennacl (version 1.7.1 or newer) for OpenCL support, which can be installed using via</p> <div class="highlight-python"><div class="highlight"><pre># On Ubuntu 16.04 @@ -525,8 +510,8 @@ Remember to add its directory to <code c </div> </div> </div> -<div class="section" id="build-singa-on-windows"> -<span id="build-singa-on-windows"></span><h2>Build SINGA on Windows<a class="headerlink" href="#build-singa-on-windows" title="Permalink to this headline">¶</a></h2> +<div class="section" id="compile-singa-on-windows"> +<span id="compile-singa-on-windows"></span><h3>Compile SINGA on Windows<a class="headerlink" href="#compile-singa-on-windows" title="Permalink to this headline">¶</a></h3> <p>For the dependent library installation, please refer to <a class="reference external" href="dependencies.md">Dependencies</a>. After all the dependencies are successfully installed, just run the following commands to generate the VS solution in cmd under singa folder:</p> @@ -561,12 +546,6 @@ unit tests file named “test_singa& If you get errors when running test_singa.exe due to libglog.dll/libopenblas.dll missing, just copy the dll files into the same folder as test_singa.exe</p> </div> -<div class="section" id="build-the-debian-packages"> -<span id="build-the-debian-packages"></span><h2>Build the Debian packages<a class="headerlink" href="#build-the-debian-packages" title="Permalink to this headline">¶</a></h2> -<div class="highlight-python"><div class="highlight"><pre>$ cd debian -$ ./build.sh -</pre></div> -</div> </div> <div class="section" id="faq"> <span id="faq"></span><h2>FAQ<a class="headerlink" href="#faq" title="Permalink to this headline">¶</a></h2>
Modified: incubator/singa/site/trunk/en/docs/layer.html URL: http://svn.apache.org/viewvc/incubator/singa/site/trunk/en/docs/layer.html?rev=1779877&r1=1779876&r2=1779877&view=diff ============================================================================== --- incubator/singa/site/trunk/en/docs/layer.html (original) +++ incubator/singa/site/trunk/en/docs/layer.html Mon Jan 23 04:55:46 2017 @@ -110,7 +110,7 @@ <li class="toctree-l2"><a class="reference internal" href="snapshot.html">Snapshot</a></li> <li class="toctree-l2"><a class="reference internal" href="converter.html">Caffe Converter</a></li> <li class="toctree-l2"><a class="reference internal" href="utils.html">Utils</a></li> -<li class="toctree-l2"><a class="reference internal" href="examples/index.html">Examples</a></li> +<li class="toctree-l2"><a class="reference internal" href="model_zoo/index.html">Model Zoo</a></li> </ul> </li> </ul> Modified: incubator/singa/site/trunk/en/docs/loss.html URL: http://svn.apache.org/viewvc/incubator/singa/site/trunk/en/docs/loss.html?rev=1779877&r1=1779876&r2=1779877&view=diff ============================================================================== --- incubator/singa/site/trunk/en/docs/loss.html (original) +++ incubator/singa/site/trunk/en/docs/loss.html Mon Jan 23 04:55:46 2017 @@ -106,7 +106,7 @@ <li class="toctree-l2"><a class="reference internal" href="snapshot.html">Snapshot</a></li> <li class="toctree-l2"><a class="reference internal" href="converter.html">Caffe Converter</a></li> <li class="toctree-l2"><a class="reference internal" href="utils.html">Utils</a></li> -<li class="toctree-l2"><a class="reference internal" href="examples/index.html">Examples</a></li> +<li class="toctree-l2"><a class="reference internal" href="model_zoo/index.html">Model Zoo</a></li> </ul> </li> </ul> Modified: incubator/singa/site/trunk/en/docs/metric.html URL: http://svn.apache.org/viewvc/incubator/singa/site/trunk/en/docs/metric.html?rev=1779877&r1=1779876&r2=1779877&view=diff ============================================================================== --- incubator/singa/site/trunk/en/docs/metric.html (original) +++ incubator/singa/site/trunk/en/docs/metric.html Mon Jan 23 04:55:46 2017 @@ -106,7 +106,7 @@ <li class="toctree-l2"><a class="reference internal" href="snapshot.html">Snapshot</a></li> <li class="toctree-l2"><a class="reference internal" href="converter.html">Caffe Converter</a></li> <li class="toctree-l2"><a class="reference internal" href="utils.html">Utils</a></li> -<li class="toctree-l2"><a class="reference internal" href="examples/index.html">Examples</a></li> +<li class="toctree-l2"><a class="reference internal" href="model_zoo/index.html">Model Zoo</a></li> </ul> </li> </ul> Added: incubator/singa/site/trunk/en/docs/model_zoo/caffe/README.html URL: http://svn.apache.org/viewvc/incubator/singa/site/trunk/en/docs/model_zoo/caffe/README.html?rev=1779877&view=auto ============================================================================== --- incubator/singa/site/trunk/en/docs/model_zoo/caffe/README.html (added) +++ incubator/singa/site/trunk/en/docs/model_zoo/caffe/README.html Mon Jan 23 04:55:46 2017 @@ -0,0 +1,278 @@ + + + +<!DOCTYPE html> +<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> +<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> +<head> + <meta charset="utf-8"> + + <meta name="viewport" content="width=device-width, initial-scale=1.0"> + + <title>Use parameters pre-trained from Caffe in SINGA — incubator-singa 1.0.1 documentation</title> + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="top" title="incubator-singa 1.0.1 documentation" href="../../../index.html"/> + <link href="../../../_static/style.css" rel="stylesheet" type="text/css"> + + + + <script src="../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + <div class="wy-grid-for-nav"> + + + <nav data-toggle="wy-nav-shift" class="wy-nav-side"> + <div class="wy-side-scroll"> + <div class="wy-side-nav-search"> + + + + <a href="../../../index.html" class="icon icon-home"> incubator-singa + + + + + <img src="../../../_static/singa.png" class="logo" /> + + </a> + + + + + <div class="version"> + 1.0 + </div> + + + + +<div role="search"> + <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get"> + <input type="text" name="q" placeholder="Search docs" /> + <input type="hidden" name="check_keywords" value="yes" /> + <input type="hidden" name="area" value="default" /> + </form> +</div> + + + </div> + + <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> + + + + <ul> +<li class="toctree-l1"><a class="reference internal" href="../../../downloads.html">Download SINGA</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../index.html">Documentation</a></li> +</ul> +<p class="caption"><span class="caption-text">Development</span></p> +<ul> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/schedule.html">Development Schedule</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/how-contribute.html">How to Contribute to SINGA</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/contribute-code.html">How to Contribute Code</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/contribute-docs.html">How to Contribute to Documentation</a></li> +</ul> +<p class="caption"><span class="caption-text">Community</span></p> +<ul> +<li class="toctree-l1"><a class="reference internal" href="../../../community/source-repository.html">Source Repository</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../community/mail-lists.html">Project Mailing Lists</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../community/issue-tracking.html">Issue Tracking</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../community/team-list.html">The SINGA Team</a></li> +</ul> + + + + </div> + </div> + </nav> + + <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> + + + <nav class="wy-nav-top" role="navigation" aria-label="top navigation"> + <i data-toggle="wy-nav-top" class="fa fa-bars"></i> + <a href="../../../index.html">incubator-singa</a> + </nav> + + + + <div class="wy-nav-content"> + <div class="rst-content"> + + + + + + +<div role="navigation" aria-label="breadcrumbs navigation"> + <ul class="wy-breadcrumbs"> + <li><a href="../../../index.html">Docs</a> »</li> + + <li>Use parameters pre-trained from Caffe in SINGA</li> + <li class="wy-breadcrumbs-aside"> + + + + </li> + </ul> + <hr/> +</div> + <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article";> + <div itemprop="articleBody"> + + <div class="section" id="use-parameters-pre-trained-from-caffe-in-singa"> +<span id="use-parameters-pre-trained-from-caffe-in-singa"></span><h1>Use parameters pre-trained from Caffe in SINGA<a class="headerlink" href="#use-parameters-pre-trained-from-caffe-in-singa" title="Permalink to this headline">¶</a></h1> +<p>In this example, we use SINGA to load the VGG parameters trained by Caffe to do image classification.</p> +<div class="section" id="run-this-example"> +<span id="run-this-example"></span><h2>Run this example<a class="headerlink" href="#run-this-example" title="Permalink to this headline">¶</a></h2> +<p>You can run this example by simply executing <code class="docutils literal"><span class="pre">run.sh</span> <span class="pre">vgg16</span></code> or <code class="docutils literal"><span class="pre">run.sh</span> <span class="pre">vgg19</span></code> +The script does the following work.</p> +<div class="section" id="obtain-the-caffe-model"> +<span id="obtain-the-caffe-model"></span><h3>Obtain the Caffe model<a class="headerlink" href="#obtain-the-caffe-model" title="Permalink to this headline">¶</a></h3> +<ul class="simple"> +<li>Download caffe model prototxt and parameter binary file.</li> +<li>Currently we only support the latest caffe format, if your model is in +previous version of caffe, please update it to current format.(This is +supported by caffe)</li> +<li>After updating, we can obtain two files, i.e., the prototxt and parameter +binary file.</li> +</ul> +</div> +<div class="section" id="prepare-test-images"> +<span id="prepare-test-images"></span><h3>Prepare test images<a class="headerlink" href="#prepare-test-images" title="Permalink to this headline">¶</a></h3> +<p>A few sample images are downloaded into the <code class="docutils literal"><span class="pre">test</span></code> folder.</p> +</div> +<div class="section" id="predict"> +<span id="predict"></span><h3>Predict<a class="headerlink" href="#predict" title="Permalink to this headline">¶</a></h3> +<p>The <code class="docutils literal"><span class="pre">predict.py</span></code> script creates the VGG model and read the parameters,</p> +<div class="highlight-python"><div class="highlight"><pre>usage: predict.py [-h] model_txt model_bin imgclass +</pre></div> +</div> +<p>where <code class="docutils literal"><span class="pre">imgclass</span></code> refers to the synsets of imagenet dataset for vgg models. +You can start the prediction program by executing the following command:</p> +<div class="highlight-python"><div class="highlight"><pre>python predict.py vgg16.prototxt vgg16.caffemodel synset_words.txt +</pre></div> +</div> +<p>Then you type in the image path, and the program would output the top-5 labels.</p> +<p>More Caffe models would be tested soon.</p> +</div> +</div> +</div> + + + </div> + </div> + <footer> + + + <hr/> + + <div role="contentinfo"> + <p> + © Copyright 2016 The Apache Software Foundation. All rights reserved. Apache Singa, Apache, the Apache feather logo, and the Apache Singa project logos are trademarks of The Apache Software Foundation. All other marks mentioned may be trademarks or registered trademarks of their respective owners.. + + </p> + </div> + Built with <a href="http://sphinx-doc.org/";>Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme";>theme</a> provided by <a href="https://readthedocs.org";>Read the Docs</a>. + +</footer> + + </div> + </div> + + </section> + + </div> + + + + + + <script type="text/javascript"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../', + VERSION:'1.0.1', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true + }; + </script> + <script type="text/javascript" src="../../../_static/jquery.js"></script> + <script type="text/javascript" src="../../../_static/underscore.js"></script> + <script type="text/javascript" src="../../../_static/doctools.js"></script> + + + + + + <script type="text/javascript" src="../../../_static/js/theme.js"></script> + + + + + <script type="text/javascript"> + jQuery(function () { + SphinxRtdTheme.StickyNav.enable(); + }); + </script> + + +<div class="rst-versions shift-up" data-toggle="rst-versions" role="note" aria-label="versions"> +<a href="http://incubator.apache.org/";> +<img src= "../../../_static/apache.jpg"> +</a> + + <span class="rst-current-version" data-toggle="rst-current-version"> + <span class="fa fa-book"> incubator-singa </span> + v: 1.0 + <span class="fa fa-caret-down"></span> + </span> + <div class="rst-other-versions"> + <dl> + <dt>Languages</dt> + <dd><a href="../../../../en/index.html">English</a></dd> + <dd><a href="../../../../zh/index.html">ä¸æ</a></dd> + </dl> + <dl> + <dt>Versions</dt> + <dd><a href="http://singa.apache.org/v0.3.0/";>0.3</a></dd> + </dl> + + </div> +</div> + + <a href="https://github.com/apache/incubator-singa";> + <img style="position: absolute; top: 0; right: 0; border: 0; z-index: 10000;" + src="https://s3.amazonaws.com/github/ribbons/forkme_right_orange_ff7600.png"; + alt="Fork me on GitHub"> +</a> + + + + +</body> +</html> \ No newline at end of file Added: incubator/singa/site/trunk/en/docs/model_zoo/char-rnn/README.html URL: http://svn.apache.org/viewvc/incubator/singa/site/trunk/en/docs/model_zoo/char-rnn/README.html?rev=1779877&view=auto ============================================================================== --- incubator/singa/site/trunk/en/docs/model_zoo/char-rnn/README.html (added) +++ incubator/singa/site/trunk/en/docs/model_zoo/char-rnn/README.html Mon Jan 23 04:55:46 2017 @@ -0,0 +1,318 @@ + + + +<!DOCTYPE html> +<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> +<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> +<head> + <meta charset="utf-8"> + + <meta name="viewport" content="width=device-width, initial-scale=1.0"> + + <title>Train Char-RNN over plain text — incubator-singa 1.0.1 documentation</title> + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="top" title="incubator-singa 1.0.1 documentation" href="../../../index.html"/> + <link rel="up" title="Model Zoo" href="../index.html"/> + <link rel="next" title="Train AlexNet over ImageNet" href="../imagenet/README.html"/> + <link rel="prev" title="Train CNN over Cifar-10" href="../cifar10/README.html"/> + <link href="../../../_static/style.css" rel="stylesheet" type="text/css"> + + + + <script src="../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + <div class="wy-grid-for-nav"> + + + <nav data-toggle="wy-nav-shift" class="wy-nav-side"> + <div class="wy-side-scroll"> + <div class="wy-side-nav-search"> + + + + <a href="../../../index.html" class="icon icon-home"> incubator-singa + + + + + <img src="../../../_static/singa.png" class="logo" /> + + </a> + + + + + <div class="version"> + 1.0 + </div> + + + + +<div role="search"> + <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get"> + <input type="text" name="q" placeholder="Search docs" /> + <input type="hidden" name="check_keywords" value="yes" /> + <input type="hidden" name="area" value="default" /> + </form> +</div> + + + </div> + + <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> + + + + <ul class="current"> +<li class="toctree-l1"><a class="reference internal" href="../../../downloads.html">Download SINGA</a></li> +<li class="toctree-l1 current"><a class="reference internal" href="../../index.html">Documentation</a><ul class="current"> +<li class="toctree-l2"><a class="reference internal" href="../../installation.html">Installation</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../software_stack.html">Software Stack</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../device.html">Device</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../tensor.html">Tensor</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../layer.html">Layer</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../net.html">FeedForward Net</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../initializer.html">Initializer</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../loss.html">Loss</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../metric.html">Metric</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../optimizer.html">Optimizer</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../data.html">Data</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../image_tool.html">Image Tool</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../snapshot.html">Snapshot</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../converter.html">Caffe Converter</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../utils.html">Utils</a></li> +<li class="toctree-l2 current"><a class="reference internal" href="../index.html">Model Zoo</a><ul class="current"> +<li class="toctree-l3"><a class="reference internal" href="../cifar10/README.html">Train CNN over Cifar-10</a></li> +<li class="toctree-l3 current"><a class="current reference internal" href="">Train Char-RNN over plain text</a><ul> +<li class="toctree-l4"><a class="reference internal" href="#instructions">Instructions</a></li> +</ul> +</li> +<li class="toctree-l3"><a class="reference internal" href="../imagenet/README.html">Train AlexNet over ImageNet</a></li> +</ul> +</li> +</ul> +</li> +</ul> +<p class="caption"><span class="caption-text">Development</span></p> +<ul> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/schedule.html">Development Schedule</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/how-contribute.html">How to Contribute to SINGA</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/contribute-code.html">How to Contribute Code</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/contribute-docs.html">How to Contribute to Documentation</a></li> +</ul> +<p class="caption"><span class="caption-text">Community</span></p> +<ul> +<li class="toctree-l1"><a class="reference internal" href="../../../community/source-repository.html">Source Repository</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../community/mail-lists.html">Project Mailing Lists</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../community/issue-tracking.html">Issue Tracking</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../community/team-list.html">The SINGA Team</a></li> +</ul> + + + + </div> + </div> + </nav> + + <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> + + + <nav class="wy-nav-top" role="navigation" aria-label="top navigation"> + <i data-toggle="wy-nav-top" class="fa fa-bars"></i> + <a href="../../../index.html">incubator-singa</a> + </nav> + + + + <div class="wy-nav-content"> + <div class="rst-content"> + + + + + + +<div role="navigation" aria-label="breadcrumbs navigation"> + <ul class="wy-breadcrumbs"> + <li><a href="../../../index.html">Docs</a> »</li> + + <li><a href="../../index.html">Documentation</a> »</li> + + <li><a href="../index.html">Model Zoo</a> »</li> + + <li>Train Char-RNN over plain text</li> + <li class="wy-breadcrumbs-aside"> + + + + </li> + </ul> + <hr/> +</div> + <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article";> + <div itemprop="articleBody"> + + <div class="section" id="train-char-rnn-over-plain-text"> +<span id="train-char-rnn-over-plain-text"></span><h1>Train Char-RNN over plain text<a class="headerlink" href="#train-char-rnn-over-plain-text" title="Permalink to this headline">¶</a></h1> +<p>Recurrent neural networks (RNN) are widely used for modelling sequential data, +e.g., natural language sentences. This example describes how to implement a RNN +application (or model) using SINGA’s RNN layers. +We will use the <a class="reference external" href="https://github.com/karpathy/char-rnn";>char-rnn</a> model as an +example, which trains over sentences or +source code, with each character as an input unit. Particularly, we will train +a RNN using GRU over Linux kernel source code. After training, we expect to +generate meaningful code from the model.</p> +<div class="section" id="instructions"> +<span id="instructions"></span><h2>Instructions<a class="headerlink" href="#instructions" title="Permalink to this headline">¶</a></h2> +<ul> +<li><p class="first">Compile and install SINGA. Currently the RNN implementation depends on Cudnn with version >= 5.05.</p> +</li> +<li><p class="first">Prepare the dataset. Download the <a class="reference external" href="http://cs.stanford.edu/people/karpathy/char-rnn/";>kernel source code</a>. +Other plain text files can also be used.</p> +</li> +<li><p class="first">Start the training,</p> +<div class="highlight-python"><div class="highlight"><pre> python train.py linux_input.txt +</pre></div> +</div> +<p>Some hyper-parameters could be set through command line,</p> +<div class="highlight-python"><div class="highlight"><pre> python train.py -h +</pre></div> +</div> +</li> +<li><p class="first">Sample characters from the model by providing the number of characters to sample and the seed string.</p> +<div class="highlight-python"><div class="highlight"><pre> python sample.py 'model.bin' 100 --seed '#include <std' +</pre></div> +</div> +<p>Please replace ‘model.bin’ with the path to one of the checkpoint paths.</p> +</li> +</ul> +</div> +</div> + + + </div> + </div> + <footer> + + <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> + + <a href="../imagenet/README.html" class="btn btn-neutral float-right" title="Train AlexNet over ImageNet" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a> + + + <a href="../cifar10/README.html" class="btn btn-neutral" title="Train CNN over Cifar-10" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a> + + </div> + + + <hr/> + + <div role="contentinfo"> + <p> + © Copyright 2016 The Apache Software Foundation. All rights reserved. Apache Singa, Apache, the Apache feather logo, and the Apache Singa project logos are trademarks of The Apache Software Foundation. All other marks mentioned may be trademarks or registered trademarks of their respective owners.. + + </p> + </div> + Built with <a href="http://sphinx-doc.org/";>Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme";>theme</a> provided by <a href="https://readthedocs.org";>Read the Docs</a>. + +</footer> + + </div> + </div> + + </section> + + </div> + + + + + + <script type="text/javascript"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../', + VERSION:'1.0.1', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true + }; + </script> + <script type="text/javascript" src="../../../_static/jquery.js"></script> + <script type="text/javascript" src="../../../_static/underscore.js"></script> + <script type="text/javascript" src="../../../_static/doctools.js"></script> + + + + + + <script type="text/javascript" src="../../../_static/js/theme.js"></script> + + + + + <script type="text/javascript"> + jQuery(function () { + SphinxRtdTheme.StickyNav.enable(); + }); + </script> + + +<div class="rst-versions shift-up" data-toggle="rst-versions" role="note" aria-label="versions"> +<a href="http://incubator.apache.org/";> +<img src= "../../../_static/apache.jpg"> +</a> + + <span class="rst-current-version" data-toggle="rst-current-version"> + <span class="fa fa-book"> incubator-singa </span> + v: 1.0 + <span class="fa fa-caret-down"></span> + </span> + <div class="rst-other-versions"> + <dl> + <dt>Languages</dt> + <dd><a href="../../../../en/index.html">English</a></dd> + <dd><a href="../../../../zh/index.html">ä¸æ</a></dd> + </dl> + <dl> + <dt>Versions</dt> + <dd><a href="http://singa.apache.org/v0.3.0/";>0.3</a></dd> + </dl> + + </div> +</div> + + <a href="https://github.com/apache/incubator-singa";> + <img style="position: absolute; top: 0; right: 0; border: 0; z-index: 10000;" + src="https://s3.amazonaws.com/github/ribbons/forkme_right_orange_ff7600.png"; + alt="Fork me on GitHub"> +</a> + + + + +</body> +</html> \ No newline at end of file Added: incubator/singa/site/trunk/en/docs/model_zoo/cifar10/README.html URL: http://svn.apache.org/viewvc/incubator/singa/site/trunk/en/docs/model_zoo/cifar10/README.html?rev=1779877&view=auto ============================================================================== --- incubator/singa/site/trunk/en/docs/model_zoo/cifar10/README.html (added) +++ incubator/singa/site/trunk/en/docs/model_zoo/cifar10/README.html Mon Jan 23 04:55:46 2017 @@ -0,0 +1,363 @@ + + + +<!DOCTYPE html> +<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> +<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> +<head> + <meta charset="utf-8"> + + <meta name="viewport" content="width=device-width, initial-scale=1.0"> + + <title>Train CNN over Cifar-10 — incubator-singa 1.0.1 documentation</title> + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="top" title="incubator-singa 1.0.1 documentation" href="../../../index.html"/> + <link rel="up" title="Model Zoo" href="../index.html"/> + <link rel="next" title="Train Char-RNN over plain text" href="../char-rnn/README.html"/> + <link rel="prev" title="Model Zoo" href="../index.html"/> + <link href="../../../_static/style.css" rel="stylesheet" type="text/css"> + + + + <script src="../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + <div class="wy-grid-for-nav"> + + + <nav data-toggle="wy-nav-shift" class="wy-nav-side"> + <div class="wy-side-scroll"> + <div class="wy-side-nav-search"> + + + + <a href="../../../index.html" class="icon icon-home"> incubator-singa + + + + + <img src="../../../_static/singa.png" class="logo" /> + + </a> + + + + + <div class="version"> + 1.0 + </div> + + + + +<div role="search"> + <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get"> + <input type="text" name="q" placeholder="Search docs" /> + <input type="hidden" name="check_keywords" value="yes" /> + <input type="hidden" name="area" value="default" /> + </form> +</div> + + + </div> + + <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> + + + + <ul class="current"> +<li class="toctree-l1"><a class="reference internal" href="../../../downloads.html">Download SINGA</a></li> +<li class="toctree-l1 current"><a class="reference internal" href="../../index.html">Documentation</a><ul class="current"> +<li class="toctree-l2"><a class="reference internal" href="../../installation.html">Installation</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../software_stack.html">Software Stack</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../device.html">Device</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../tensor.html">Tensor</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../layer.html">Layer</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../net.html">FeedForward Net</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../initializer.html">Initializer</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../loss.html">Loss</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../metric.html">Metric</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../optimizer.html">Optimizer</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../data.html">Data</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../image_tool.html">Image Tool</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../snapshot.html">Snapshot</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../converter.html">Caffe Converter</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../utils.html">Utils</a></li> +<li class="toctree-l2 current"><a class="reference internal" href="../index.html">Model Zoo</a><ul class="current"> +<li class="toctree-l3 current"><a class="current reference internal" href="">Train CNN over Cifar-10</a><ul> +<li class="toctree-l4"><a class="reference internal" href="#instructions">Instructions</a></li> +</ul> +</li> +<li class="toctree-l3"><a class="reference internal" href="../char-rnn/README.html">Train Char-RNN over plain text</a></li> +<li class="toctree-l3"><a class="reference internal" href="../imagenet/README.html">Train AlexNet over ImageNet</a></li> +</ul> +</li> +</ul> +</li> +</ul> +<p class="caption"><span class="caption-text">Development</span></p> +<ul> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/schedule.html">Development Schedule</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/how-contribute.html">How to Contribute to SINGA</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/contribute-code.html">How to Contribute Code</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/contribute-docs.html">How to Contribute to Documentation</a></li> +</ul> +<p class="caption"><span class="caption-text">Community</span></p> +<ul> +<li class="toctree-l1"><a class="reference internal" href="../../../community/source-repository.html">Source Repository</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../community/mail-lists.html">Project Mailing Lists</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../community/issue-tracking.html">Issue Tracking</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../community/team-list.html">The SINGA Team</a></li> +</ul> + + + + </div> + </div> + </nav> + + <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> + + + <nav class="wy-nav-top" role="navigation" aria-label="top navigation"> + <i data-toggle="wy-nav-top" class="fa fa-bars"></i> + <a href="../../../index.html">incubator-singa</a> + </nav> + + + + <div class="wy-nav-content"> + <div class="rst-content"> + + + + + + +<div role="navigation" aria-label="breadcrumbs navigation"> + <ul class="wy-breadcrumbs"> + <li><a href="../../../index.html">Docs</a> »</li> + + <li><a href="../../index.html">Documentation</a> »</li> + + <li><a href="../index.html">Model Zoo</a> »</li> + + <li>Train CNN over Cifar-10</li> + <li class="wy-breadcrumbs-aside"> + + + + </li> + </ul> + <hr/> +</div> + <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article";> + <div itemprop="articleBody"> + + <div class="section" id="train-cnn-over-cifar-10"> +<span id="train-cnn-over-cifar-10"></span><h1>Train CNN over Cifar-10<a class="headerlink" href="#train-cnn-over-cifar-10" title="Permalink to this headline">¶</a></h1> +<p>Convolution neural network (CNN) is a type of feed-forward artificial neural +network widely used for image and video classification. In this example, we +will train three deep CNN models to do image classification for the CIFAR-10 dataset,</p> +<ol class="simple"> +<li><a class="reference external" href="https://code.google.com/p/cuda-convnet/source/browse/trunk/example-layers/layers-18pct.cfg";>AlexNet</a> +the best validation accuracy (without data augmentation) we achieved was about 82%.</li> +<li><a class="reference external" href="http://torch.ch/blog/2015/07/30/cifar.html";>VGGNet</a>, the best validation accuracy (without data augmentation) we achieved was about 89%.</li> +<li><a class="reference external" href="https://github.com/facebook/fb.resnet.torch";>ResNet</a>, the best validation accuracy (without data augmentation) we achieved was about 83%.</li> +<li><a class="reference external" href="https://github.com/BVLC/caffe/tree/master/examples/cifar10";>Alexnet from Caffe</a>, SINGA is able to convert model from Caffe seamlessly.</li> +</ol> +<div class="section" id="instructions"> +<span id="instructions"></span><h2>Instructions<a class="headerlink" href="#instructions" title="Permalink to this headline">¶</a></h2> +<div class="section" id="singa-installation"> +<span id="singa-installation"></span><h3>SINGA installation<a class="headerlink" href="#singa-installation" title="Permalink to this headline">¶</a></h3> +<p>Users can compile and install SINGA from source or install the Python version. +The code can ran on both CPU and GPU. For GPU training, CUDA and CUDNN (V4 or V5) +are required. Please refer to the installation page for detailed instructions.</p> +</div> +<div class="section" id="data-preparation"> +<span id="data-preparation"></span><h3>Data preparation<a class="headerlink" href="#data-preparation" title="Permalink to this headline">¶</a></h3> +<p>The binary Cifar-10 dataset could be downloaded by</p> +<div class="highlight-python"><div class="highlight"><pre>python download_data.py bin +</pre></div> +</div> +<p>The Python version could be downloaded by</p> +<div class="highlight-python"><div class="highlight"><pre>python download_data.py py +</pre></div> +</div> +</div> +<div class="section" id="training"> +<span id="training"></span><h3>Training<a class="headerlink" href="#training" title="Permalink to this headline">¶</a></h3> +<p>There are four training programs</p> +<ol> +<li><p class="first">train.py. The following command would train the VGG model using the python +version of the Cifar-10 dataset in ‘cifar-10-batches-py’ folder.</p> +<div class="highlight-python"><div class="highlight"><pre> python train.py vgg cifar-10-batches-py +</pre></div> +</div> +<p>To train other models, please replace ‘vgg’ to ‘alexnet’, ‘resnet’ or ‘caffe’, +where ‘caffe’ refers to the alexnet model converted from Caffe. By default +the training would run on a CudaGPU device, to run it on CppCPU, add an additional +argument</p> +<div class="highlight-python"><div class="highlight"><pre> python train.py vgg cifar-10-batches-py --use_cpu +</pre></div> +</div> +</li> +<li><p class="first">alexnet.cc. It trains the AlexNet model using the CPP APIs on a CudaGPU,</p> +<div class="highlight-python"><div class="highlight"><pre> ./run.sh +</pre></div> +</div> +</li> +<li><p class="first">alexnet-parallel.cc. It trains the AlexNet model using the CPP APIs on two CudaGPU devices. +The two devices run synchronously to compute the gradients of the mode parameters, which are +averaged on the host CPU device and then be applied to update the parameters.</p> +<div class="highlight-python"><div class="highlight"><pre> ./run-parallel.sh +</pre></div> +</div> +</li> +<li><p class="first">vgg-parallel.cc. It trains the VGG model using the CPP APIs on two CudaGPU devices similar to alexnet-parallel.cc.</p> +</li> +</ol> +</div> +<div class="section" id="prediction"> +<span id="prediction"></span><h3>Prediction<a class="headerlink" href="#prediction" title="Permalink to this headline">¶</a></h3> +<p>predict.py includes the prediction function</p> +<div class="highlight-python"><div class="highlight"><pre> def predict(net, images, dev, topk=5) +</pre></div> +</div> +<p>The net is created by loading the previously trained model; Images consist of +a numpy array of images (one row per image); dev is the training device, e.g., +a CudaGPU device or the host CppCPU device; It returns the topk labels for each instance.</p> +<p>The predict.py file’s main function provides an example of using the pre-trained alexnet model to do prediction for new images. +The ‘model.bin’ file generated by the training program should be placed at the cifar10 folder to run</p> +<div class="highlight-python"><div class="highlight"><pre> python predict.py +</pre></div> +</div> +</div> +</div> +</div> + + + </div> + </div> + <footer> + + <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> + + <a href="../char-rnn/README.html" class="btn btn-neutral float-right" title="Train Char-RNN over plain text" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a> + + + <a href="../index.html" class="btn btn-neutral" title="Model Zoo" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a> + + </div> + + + <hr/> + + <div role="contentinfo"> + <p> + © Copyright 2016 The Apache Software Foundation. All rights reserved. Apache Singa, Apache, the Apache feather logo, and the Apache Singa project logos are trademarks of The Apache Software Foundation. All other marks mentioned may be trademarks or registered trademarks of their respective owners.. + + </p> + </div> + Built with <a href="http://sphinx-doc.org/";>Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme";>theme</a> provided by <a href="https://readthedocs.org";>Read the Docs</a>. + +</footer> + + </div> + </div> + + </section> + + </div> + + + + + + <script type="text/javascript"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../', + VERSION:'1.0.1', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true + }; + </script> + <script type="text/javascript" src="../../../_static/jquery.js"></script> + <script type="text/javascript" src="../../../_static/underscore.js"></script> + <script type="text/javascript" src="../../../_static/doctools.js"></script> + + + + + + <script type="text/javascript" src="../../../_static/js/theme.js"></script> + + + + + <script type="text/javascript"> + jQuery(function () { + SphinxRtdTheme.StickyNav.enable(); + }); + </script> + + +<div class="rst-versions shift-up" data-toggle="rst-versions" role="note" aria-label="versions"> +<a href="http://incubator.apache.org/";> +<img src= "../../../_static/apache.jpg"> +</a> + + <span class="rst-current-version" data-toggle="rst-current-version"> + <span class="fa fa-book"> incubator-singa </span> + v: 1.0 + <span class="fa fa-caret-down"></span> + </span> + <div class="rst-other-versions"> + <dl> + <dt>Languages</dt> + <dd><a href="../../../../en/index.html">English</a></dd> + <dd><a href="../../../../zh/index.html">ä¸æ</a></dd> + </dl> + <dl> + <dt>Versions</dt> + <dd><a href="http://singa.apache.org/v0.3.0/";>0.3</a></dd> + </dl> + + </div> +</div> + + <a href="https://github.com/apache/incubator-singa";> + <img style="position: absolute; top: 0; right: 0; border: 0; z-index: 10000;" + src="https://s3.amazonaws.com/github/ribbons/forkme_right_orange_ff7600.png"; + alt="Fork me on GitHub"> +</a> + + + + +</body> +</html> \ No newline at end of file Added: incubator/singa/site/trunk/en/docs/model_zoo/imagenet/README.html URL: http://svn.apache.org/viewvc/incubator/singa/site/trunk/en/docs/model_zoo/imagenet/README.html?rev=1779877&view=auto ============================================================================== --- incubator/singa/site/trunk/en/docs/model_zoo/imagenet/README.html (added) +++ incubator/singa/site/trunk/en/docs/model_zoo/imagenet/README.html Mon Jan 23 04:55:46 2017 @@ -0,0 +1,358 @@ + + + +<!DOCTYPE html> +<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> +<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> +<head> + <meta charset="utf-8"> + + <meta name="viewport" content="width=device-width, initial-scale=1.0"> + + <title>Train AlexNet over ImageNet — incubator-singa 1.0.1 documentation</title> + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="top" title="incubator-singa 1.0.1 documentation" href="../../../index.html"/> + <link rel="up" title="Model Zoo" href="../index.html"/> + <link rel="next" title="Development Schedule" href="../../../develop/schedule.html"/> + <link rel="prev" title="Train Char-RNN over plain text" href="../char-rnn/README.html"/> + <link href="../../../_static/style.css" rel="stylesheet" type="text/css"> + + + + <script src="../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + <div class="wy-grid-for-nav"> + + + <nav data-toggle="wy-nav-shift" class="wy-nav-side"> + <div class="wy-side-scroll"> + <div class="wy-side-nav-search"> + + + + <a href="../../../index.html" class="icon icon-home"> incubator-singa + + + + + <img src="../../../_static/singa.png" class="logo" /> + + </a> + + + + + <div class="version"> + 1.0 + </div> + + + + +<div role="search"> + <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get"> + <input type="text" name="q" placeholder="Search docs" /> + <input type="hidden" name="check_keywords" value="yes" /> + <input type="hidden" name="area" value="default" /> + </form> +</div> + + + </div> + + <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> + + + + <ul class="current"> +<li class="toctree-l1"><a class="reference internal" href="../../../downloads.html">Download SINGA</a></li> +<li class="toctree-l1 current"><a class="reference internal" href="../../index.html">Documentation</a><ul class="current"> +<li class="toctree-l2"><a class="reference internal" href="../../installation.html">Installation</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../software_stack.html">Software Stack</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../device.html">Device</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../tensor.html">Tensor</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../layer.html">Layer</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../net.html">FeedForward Net</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../initializer.html">Initializer</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../loss.html">Loss</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../metric.html">Metric</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../optimizer.html">Optimizer</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../data.html">Data</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../image_tool.html">Image Tool</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../snapshot.html">Snapshot</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../converter.html">Caffe Converter</a></li> +<li class="toctree-l2"><a class="reference internal" href="../../utils.html">Utils</a></li> +<li class="toctree-l2 current"><a class="reference internal" href="../index.html">Model Zoo</a><ul class="current"> +<li class="toctree-l3"><a class="reference internal" href="../cifar10/README.html">Train CNN over Cifar-10</a></li> +<li class="toctree-l3"><a class="reference internal" href="../char-rnn/README.html">Train Char-RNN over plain text</a></li> +<li class="toctree-l3 current"><a class="current reference internal" href="">Train AlexNet over ImageNet</a><ul> +<li class="toctree-l4"><a class="reference internal" href="#instructions">Instructions</a></li> +</ul> +</li> +</ul> +</li> +</ul> +</li> +</ul> +<p class="caption"><span class="caption-text">Development</span></p> +<ul> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/schedule.html">Development Schedule</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/how-contribute.html">How to Contribute to SINGA</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/contribute-code.html">How to Contribute Code</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../develop/contribute-docs.html">How to Contribute to Documentation</a></li> +</ul> +<p class="caption"><span class="caption-text">Community</span></p> +<ul> +<li class="toctree-l1"><a class="reference internal" href="../../../community/source-repository.html">Source Repository</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../community/mail-lists.html">Project Mailing Lists</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../community/issue-tracking.html">Issue Tracking</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../community/team-list.html">The SINGA Team</a></li> +</ul> + + + + </div> + </div> + </nav> + + <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> + + + <nav class="wy-nav-top" role="navigation" aria-label="top navigation"> + <i data-toggle="wy-nav-top" class="fa fa-bars"></i> + <a href="../../../index.html">incubator-singa</a> + </nav> + + + + <div class="wy-nav-content"> + <div class="rst-content"> + + + + + + +<div role="navigation" aria-label="breadcrumbs navigation"> + <ul class="wy-breadcrumbs"> + <li><a href="../../../index.html">Docs</a> »</li> + + <li><a href="../../index.html">Documentation</a> »</li> + + <li><a href="../index.html">Model Zoo</a> »</li> + + <li>Train AlexNet over ImageNet</li> + <li class="wy-breadcrumbs-aside"> + + + + </li> + </ul> + <hr/> +</div> + <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article";> + <div itemprop="articleBody"> + + <div class="section" id="train-alexnet-over-imagenet"> +<span id="train-alexnet-over-imagenet"></span><h1>Train AlexNet over ImageNet<a class="headerlink" href="#train-alexnet-over-imagenet" title="Permalink to this headline">¶</a></h1> +<p>Convolution neural network (CNN) is a type of feed-forward neural +network widely used for image and video classification. In this example, we will +use a <a class="reference external" href="http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks";>deep CNN model</a> +to do image classification against the ImageNet dataset.</p> +<div class="section" id="instructions"> +<span id="instructions"></span><h2>Instructions<a class="headerlink" href="#instructions" title="Permalink to this headline">¶</a></h2> +<div class="section" id="compile-singa"> +<span id="compile-singa"></span><h3>Compile SINGA<a class="headerlink" href="#compile-singa" title="Permalink to this headline">¶</a></h3> +<p>Please compile SINGA with CUDA, CUDNN and OpenCV. You can manually turn on the +options in CMakeLists.txt or run <code class="docutils literal"><span class="pre">ccmake</span> <span class="pre">..</span></code> in build/ folder.</p> +<p>We have tested CUDNN V4 and V5 (V5 requires CUDA 7.5)</p> +</div> +<div class="section" id="data-download"> +<span id="data-download"></span><h3>Data download<a class="headerlink" href="#data-download" title="Permalink to this headline">¶</a></h3> +<ul class="simple"> +<li>Please refer to step1-3 on <a class="reference external" href="https://github.com/amd/OpenCL-caffe/wiki/Instructions-to-create-ImageNet-2012-data";>Instructions to create ImageNet 2012 data</a> +to download and decompress the data.</li> +<li>You can download the training and validation list by +<a class="reference external" href="https://github.com/BVLC/caffe/blob/master/data/ilsvrc12/get_ilsvrc_aux.sh";>get_ilsvrc_aux.sh</a> +or from <a class="reference external" href="http://www.image-net.org/download-images";>Imagenet</a>.</li> +</ul> +</div> +<div class="section" id="data-preprocessing"> +<span id="data-preprocessing"></span><h3>Data preprocessing<a class="headerlink" href="#data-preprocessing" title="Permalink to this headline">¶</a></h3> +<ul> +<li><p class="first">Assuming you have downloaded the data and the list. +Now we should transform the data into binary files. You can run:</p> +<div class="highlight-python"><div class="highlight"><pre> sh create_data.sh +</pre></div> +</div> +<p>The script will generate a test file(<code class="docutils literal"><span class="pre">test.bin</span></code>), a mean file(<code class="docutils literal"><span class="pre">mean.bin</span></code>) and +several training files(<code class="docutils literal"><span class="pre">trainX.bin</span></code>) in the specified output folder.</p> +</li> +<li><p class="first">You can also change the parameters in <code class="docutils literal"><span class="pre">create_data.sh</span></code>.</p> +<ul class="simple"> +<li><code class="docutils literal"><span class="pre">-trainlist</span> <span class="pre"><file></span></code>: the file of training list;</li> +<li><code class="docutils literal"><span class="pre">-trainfolder</span> <span class="pre"><folder></span></code>: the folder of training images;</li> +<li><code class="docutils literal"><span class="pre">-testlist</span> <span class="pre"><file></span></code>: the file of test list;</li> +<li><code class="docutils literal"><span class="pre">-testfolder</span> <span class="pre"><floder></span></code>: the folder of test images;</li> +<li><code class="docutils literal"><span class="pre">-outdata</span> <span class="pre"><folder></span></code>: the folder to save output files, including mean, training and test files. +The script will generate these files in the specified folder;</li> +<li><code class="docutils literal"><span class="pre">-filesize</span> <span class="pre"><int></span></code>: number of training images that stores in each binary file.</li> +</ul> +</li> +</ul> +</div> +<div class="section" id="training"> +<span id="training"></span><h3>Training<a class="headerlink" href="#training" title="Permalink to this headline">¶</a></h3> +<ul> +<li><p class="first">After preparing data, you can run the following command to train the Alexnet model.</p> +<div class="highlight-python"><div class="highlight"><pre> sh run.sh +</pre></div> +</div> +</li> +<li><p class="first">You may change the parameters in <code class="docutils literal"><span class="pre">run.sh</span></code>.</p> +<ul class="simple"> +<li><code class="docutils literal"><span class="pre">-epoch</span> <span class="pre"><int></span></code>: number of epoch to be trained, default is 90;</li> +<li><code class="docutils literal"><span class="pre">-lr</span> <span class="pre"><float></span></code>: base learning rate, the learning rate will decrease each 20 epochs, +more specifically, <code class="docutils literal"><span class="pre">lr</span> <span class="pre">=</span> <span class="pre">lr</span> <span class="pre">*</span> <span class="pre">exp(0.1</span> <span class="pre">*</span> <span class="pre">(epoch</span> <span class="pre">/</span> <span class="pre">20))</span></code>;</li> +<li><code class="docutils literal"><span class="pre">-batchsize</span> <span class="pre"><int></span></code>: batchsize, it should be changed regarding to your memory;</li> +<li><code class="docutils literal"><span class="pre">-filesize</span> <span class="pre"><int></span></code>: number of training images that stores in each binary file, it is the +same as the <code class="docutils literal"><span class="pre">filesize</span></code> in data preprocessing;</li> +<li><code class="docutils literal"><span class="pre">-ntrain</span> <span class="pre"><int></span></code>: number of training images;</li> +<li><code class="docutils literal"><span class="pre">-ntest</span> <span class="pre"><int></span></code>: number of test images;</li> +<li><code class="docutils literal"><span class="pre">-data</span> <span class="pre"><folder></span></code>: the folder which stores the binary files, it is exactly the output +folder in data preprocessing step;</li> +<li><code class="docutils literal"><span class="pre">-pfreq</span> <span class="pre"><int></span></code>: the frequency(in batch) of printing current model status(loss and accuracy);</li> +<li><code class="docutils literal"><span class="pre">-nthreads</span> <span class="pre"><int></span></code>: the number of threads to load data which feed to the model.</li> +</ul> +</li> +</ul> +</div> +</div> +</div> + + + </div> + </div> + <footer> + + <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> + + <a href="../../../develop/schedule.html" class="btn btn-neutral float-right" title="Development Schedule" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a> + + + <a href="../char-rnn/README.html" class="btn btn-neutral" title="Train Char-RNN over plain text" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a> + + </div> + + + <hr/> + + <div role="contentinfo"> + <p> + © Copyright 2016 The Apache Software Foundation. All rights reserved. Apache Singa, Apache, the Apache feather logo, and the Apache Singa project logos are trademarks of The Apache Software Foundation. All other marks mentioned may be trademarks or registered trademarks of their respective owners.. + + </p> + </div> + Built with <a href="http://sphinx-doc.org/";>Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme";>theme</a> provided by <a href="https://readthedocs.org";>Read the Docs</a>. + +</footer> + + </div> + </div> + + </section> + + </div> + + + + + + <script type="text/javascript"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../', + VERSION:'1.0.1', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true + }; + </script> + <script type="text/javascript" src="../../../_static/jquery.js"></script> + <script type="text/javascript" src="../../../_static/underscore.js"></script> + <script type="text/javascript" src="../../../_static/doctools.js"></script> + + + + + + <script type="text/javascript" src="../../../_static/js/theme.js"></script> + + + + + <script type="text/javascript"> + jQuery(function () { + SphinxRtdTheme.StickyNav.enable(); + }); + </script> + + +<div class="rst-versions shift-up" data-toggle="rst-versions" role="note" aria-label="versions"> +<a href="http://incubator.apache.org/";> +<img src= "../../../_static/apache.jpg"> +</a> + + <span class="rst-current-version" data-toggle="rst-current-version"> + <span class="fa fa-book"> incubator-singa </span> + v: 1.0 + <span class="fa fa-caret-down"></span> + </span> + <div class="rst-other-versions"> + <dl> + <dt>Languages</dt> + <dd><a href="../../../../en/index.html">English</a></dd> + <dd><a href="../../../../zh/index.html">ä¸æ</a></dd> + </dl> + <dl> + <dt>Versions</dt> + <dd><a href="http://singa.apache.org/v0.3.0/";>0.3</a></dd> + </dl> + + </div> +</div> + + <a href="https://github.com/apache/incubator-singa";> + <img style="position: absolute; top: 0; right: 0; border: 0; z-index: 10000;" + src="https://s3.amazonaws.com/github/ribbons/forkme_right_orange_ff7600.png"; + alt="Fork me on GitHub"> +</a> + + + + +</body> +</html> \ No newline at end of file
![https://s3.amazonaws.com/github/ribbons/forkme_right_orange_ff7600.png"](https://s3.amazonaws.com/github/ribbons/forkme_right_orange_ff7600.png"){kind=link}