From: 남궁석/동작제어Lab(SR)/Engineer/삼성전자 <sk.namkoong@samsung.com>
Date: Tue, 11 Dec 2018 00:39:47 +0000 (+0900)
Subject: [tflchef] Update README and related test (#2430)
X-Git-Tag: nncc_backup~1121
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=0ca29943bccd02f50c20fb7118b048f3abcc2fc7;p=platform%2Fcore%2Fml%2Fnnfw.git

[tflchef] Update README and related test (#2430)

This commit will introduce gaussian filler in tflchef
And also recipe of readme will be modified

Signed-off-by: Seok NamKoong <sk.namkoong@samsung.com>
---

diff --git a/contrib/tflchef/README.md b/contrib/tflchef/README.md
index 7d680e8..c940f22 100644
--- a/contrib/tflchef/README.md
+++ b/contrib/tflchef/README.md
@@ -10,7 +10,7 @@ Given a recipe, _tflchef_ will cook a tensorflow lite model for you.
 ## Tutorial: How to use?
 
 This example explains how to generate a tensorflow lite model with a single Conv2D operation
-with constant (1.1f) bias with _tflchef_.
+with a kernel filled with random values generated according to normal (or gaussian) distribution (mean = 0.0f / stddev = 1.0f) and bias with constant values (1.1f) with _tflchef_.
 
 The first step is to write a recipe!
 Type the following command, and then you may get ``sample.recipe``:
@@ -25,6 +25,11 @@ operand {
   name: "ker"
   type: FLOAT32
   shape { dim: 1 dim: 1 dim: 1 dim: 2 }
+  filler {
+    tag: "gaussian"
+    arg: "0.0"
+    arg: "1.0"
+  }
 }
 operand {
   name: "bias"
diff --git a/contrib/tflchef/tests/readme/test.recipe b/contrib/tflchef/tests/readme/test.recipe
index 36e13d3..bc41a3f 100644
--- a/contrib/tflchef/tests/readme/test.recipe
+++ b/contrib/tflchef/tests/readme/test.recipe
@@ -7,6 +7,11 @@ operand {
   name: "ker"
   type: FLOAT32
   shape { dim: 1 dim: 1 dim: 1 dim: 2 }
+  filler {
+    tag: "gaussian"
+    arg: "0.0"
+    arg: "1.0"
+  }
 }
 operand {
   name: "bias"