From d1b8eaa4022d4837c8a92faabca70767d9e034f8 Mon Sep 17 00:00:00 2001 From: dabinat Date: Tue, 31 Dec 2019 14:20:25 -0800 Subject: [PATCH] TRAINING.rst - Include exact command for getting mmap tool --- TRAINING.rst | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/TRAINING.rst b/TRAINING.rst index 8c90bfd7..4f58e960 100644 --- a/TRAINING.rst +++ b/TRAINING.rst @@ -181,7 +181,11 @@ Making a mmap-able model for inference The ``output_graph.pb`` model file generated in the above step will be loaded in memory to be dealt with when running inference. This will result in extra loading time and memory consumption. One way to avoid this is to directly read data from the disk. -TensorFlow has tooling to achieve this: it requires building the target ``//tensorflow/contrib/util:convert_graphdef_memmapped_format`` (binaries are produced by our TaskCluster for some systems including Linux/amd64 and macOS/amd64), use ``util/taskcluster.py`` tool to download, specifying ``tensorflow`` as a source and ``convert_graphdef_memmapped_format`` as artifact. +TensorFlow has tooling to achieve this: it requires building the target ``//tensorflow/contrib/util:convert_graphdef_memmapped_format`` (binaries are produced by our TaskCluster for some systems including Linux/amd64 and macOS/amd64), use ``util/taskcluster.py`` tool to download: + +.. code-block:: + + $ python3 util/taskcluster.py --source tensorflow --artifact convert_graphdef_memmapped_format --branch r1.14 --target . Producing a mmap-able model is as simple as: