From 75d77721cd826fcfdaacbb7e13e4b192761f4a18 Mon Sep 17 00:00:00 2001
From: HongyingG <44694098+HongyingG@users.noreply.github.com>
Date: Wed, 20 Feb 2019 19:43:22 +0800
Subject: [PATCH] inference_en (#599)

* inference_en

* Review
---
 .../api_guides/low_level/inference_en.rst     | 55 +++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100755 doc/fluid/api_guides/low_level/inference_en.rst

diff --git a/doc/fluid/api_guides/low_level/inference_en.rst b/doc/fluid/api_guides/low_level/inference_en.rst
new file mode 100755
index 000000000..956229375
--- /dev/null
+++ b/doc/fluid/api_guides/low_level/inference_en.rst
@@ -0,0 +1,55 @@
+..  _api_guide_inference_en:
+
+#################
+Inference Engine
+#################
+
+Inference engine provides interfaces to save inference model :ref:`api_fluid_io_save_inference_model` and load inference model :ref:`api_fluid_io_load_inference_model` .
+
+Format of Saved Inference Model
+=====================================
+
+There are two formats of saved inference model, which are controlled by :code:`model_filename`  and :code:`params_filename`  parameters in the two interfaces above.
+
+- Parameters are saved into independent separate files, such as :code:`model_filename` set as :code:`None` and :code:`params_filename` set as :code:`None`
+
+  .. code-block:: bash
+
+      ls recognize_digits_conv.inference.model/*
+      __model__ conv2d_1.w_0 conv2d_2.w_0 fc_1.w_0 conv2d_1.b_0 conv2d_2.b_0 fc_1.b_0
+
+- Parameters are saved into the same file, such as :code:`model_filename` set as :code:`None` and :code:`params_filename` set as :code:`__params__`
+
+  .. code-block:: bash
+
+      ls recognize_digits_conv.inference.model/*
+      __model__ __params__
+
+Save Inference model
+===============================
+
+.. code-block:: python
+
+    exe = fluid.Executor(fluid.CPUPlace())
+    path = "./infer_model"
+    fluid.io.save_inference_model(dirname=path, feeded_var_names=['img'], 
+        target_vars=[predict_var], executor=exe)
+
+In this example, :code:`fluid.io.save_inference_model` will tailor default :code:`fluid.Program` into useful parts for predicting :code:`predict_var` .
+After being tailored, :code:`program` will be saved under :code:`./infer_model/__model__` while parameters will be saved into independent files under :code:`./infer_model` .
+
+Load Inference Model
+=====================
+
+.. code-block:: python
+
+    exe = fluid.Executor(fluid.CPUPlace())
+    path = "./infer_model"
+    [inference_program, feed_target_names, fetch_targets] = 
+        fluid.io.load_inference_model(dirname=path, executor=exe)
+    results = exe.run(inference_program,
+                  feed={feed_target_names[0]: tensor_img},
+                  fetch_list=fetch_targets)
+
+In this example, at first we call :code:`fluid.io.load_inference_model` to get inference :code:`program` , :code:`variable` name of input data and :code:`variable` of output;
+then call :code:`executor` to run inference :code:`program` to get inferred result.
\ No newline at end of file
-- 
GitLab