You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
<spanclass="p">}</span></pre><p>For MacOS, replace "Unix Makefiles" with "Xcode".</p><blockquote><p>[!NOTE] Examples require additional dependencies to the main library. As such, it is</p></blockquote><p>required to supply <code>-o examples=True</code> to the <code>conan install</code> command.</p><p>In the examples below, for GPU support add <code>-o gpu=True</code> to the <code>conan install</code> command.</p><blockquote><p>[!NOTE] The tensorflow-lite conan package disables GPU by default and as such these</p></blockquote><p>steps will not work currently. I have patched the recipe locally to enable GPU support and will make this available on Conan Center or another repository soon. In the mean time, my custom recipe can be be used as outlined <ahref="https://github.com/neuralize-ai/tensorflow-lite-conan">here</a>. If you have previously <code>conan install</code>ed, remove the existing TFLite package(s) using <code>conan remove "tensorflow-lite"</code>. Make sure to create the TFLite package version that is required in <ahref="/conanfile.py">conanfile</a>.</p><sectionid="autotoc_md9"><h2><ahref="#autotoc_md9">Unix</a></h2><p>Run all examples using one of the following methods from the project root directory.</p><p>For <code>Debug</code>:</p><preclass="m-code">conan<spanclass="w"></span>install<spanclass="w"></span>.<spanclass="w"></span>-b<spanclass="w"></span>missing<spanclass="w"></span>-s<spanclass="w"></span><spanclass="nv">build_type</span><spanclass="o">=</span>Debug<spanclass="w"></span>-o<spanclass="w"></span><spanclass="nv">examples</span><spanclass="o">=</span>True
77
+
<spanclass="p">}</span></pre><p>For MacOS, replace "Unix Makefiles" with "Xcode".</p><blockquote><p>[!NOTE] Examples require additional dependencies to the main library. As such, it is</p></blockquote><p>required to supply <code>-o examples=True</code> to the <code>conan install</code> command.</p><p>In the examples below, for GPU support add <code>-o gpu=True</code> to the <code>conan install</code> command.</p><blockquote><p>[!NOTE] The tensorflow-lite conan package disables GPU by default and as such these</p></blockquote><p>steps will not work currently. I have patched the recipe locally to enable GPU support and will make this available on Conan Center or another repository soon. In the mean time, my custom recipe can be be used as outlined <ahref="https://github.com/neuralize-ai/tensorflow-lite-conan">here</a>. If you have previously <code>conan install</code>ed, remove the existing TFLite package(s) using <code>conan remove "tensorflow-lite"</code>. Make sure to create the TFLite package version that is required in <ahref="/conanfile.py">conanfile</a>.</p><p>GPU support requires a functioning OpenCL installation. Refer to your OS documentation for the steps for setting this up correctly for your GPU vendor.</p><sectionid="autotoc_md9"><h2><ahref="#autotoc_md9">Unix</a></h2><p>Run all examples using one of the following methods from the project root directory.</p><p>For <code>Debug</code>:</p><preclass="m-code">conan<spanclass="w"></span>install<spanclass="w"></span>.<spanclass="w"></span>-b<spanclass="w"></span>missing<spanclass="w"></span>-s<spanclass="w"></span><spanclass="nv">build_type</span><spanclass="o">=</span>Debug<spanclass="w"></span>-o<spanclass="w"></span><spanclass="nv">examples</span><spanclass="o">=</span>True
0 commit comments