From da00779cf20f018755eb2ffa07cbf6230246f6ba Mon Sep 17 00:00:00 2001
From: qiaolongfei <qiaolongfei@baidu.com>
Date: Fri, 15 Sep 2017 15:47:01 -0700
Subject: [PATCH] typo

---
 04.word2vec/README.cn.md  | 20 +++++++++++---------
 04.word2vec/README.md     | 20 +++++++++++---------
 04.word2vec/index.cn.html | 20 +++++++++++---------
 04.word2vec/index.html    | 20 +++++++++++---------
 4 files changed, 44 insertions(+), 36 deletions(-)

diff --git a/04.word2vec/README.cn.md b/04.word2vec/README.cn.md
index 8d9533b..f9aac91 100644
--- a/04.word2vec/README.cn.md
+++ b/04.word2vec/README.cn.md
@@ -209,15 +209,6 @@ N = 5 # 训练5-Gram
 
 用于保存和加载word_dict和embedding table的函数
 ```python
-def wordemb(inlayer):
-    wordemb = paddle.layer.table_projection(
-        input=inlayer,
-        size=embsize,
-        param_attr=paddle.attr.Param(
-            name="_proj", initial_std=0.001, learning_rate=1, l2_rate=0))
-    return wordemb
-
-
 # save and load word dict and embedding table
 def save_dict_and_embedding(word_dict, embeddings):
     with open("word_dict", "w") as f:
@@ -225,6 +216,17 @@ def save_dict_and_embedding(word_dict, embeddings):
             f.write(key + " " + str(word_dict[key]) + "\n")
     with open("embedding_table", "w") as f:
         numpy.savetxt(f, embeddings, delimiter=',', newline='\n')
+
+
+def load_dict_and_embedding():
+    word_dict = dict()
+    with open("word_dict", "r") as f:
+        for line in f:
+            key, value = line.strip().split(" ")
+            word_dict[key] = value
+
+    embeddings = numpy.loadtxt("embedding_table", delimiter=",")
+    return word_dict, embeddings
 ```
 
 接着，定义网络结构：
diff --git a/04.word2vec/README.md b/04.word2vec/README.md
index d86771b..4b11176 100644
--- a/04.word2vec/README.md
+++ b/04.word2vec/README.md
@@ -227,15 +227,6 @@ N = 5 # train 5-gram
 
 - functions used to save and load word dict and embedding table
 ```python
-def wordemb(inlayer):
-    wordemb = paddle.layer.table_projection(
-        input=inlayer,
-        size=embsize,
-        param_attr=paddle.attr.Param(
-            name="_proj", initial_std=0.001, learning_rate=1, l2_rate=0))
-    return wordemb
-
-
 # save and load word dict and embedding table
 def save_dict_and_embedding(word_dict, embeddings):
     with open("word_dict", "w") as f:
@@ -243,6 +234,17 @@ def save_dict_and_embedding(word_dict, embeddings):
             f.write(key + " " + str(word_dict[key]) + "\n")
     with open("embedding_table", "w") as f:
         numpy.savetxt(f, embeddings, delimiter=',', newline='\n')
+
+
+def load_dict_and_embedding():
+    word_dict = dict()
+    with open("word_dict", "r") as f:
+        for line in f:
+            key, value = line.strip().split(" ")
+            word_dict[key] = value
+
+    embeddings = numpy.loadtxt("embedding_table", delimiter=",")
+    return word_dict, embeddings
 ```
 
 - Map the $n-1$ words $w_{t-n+1},...w_{t-1}$ before $w_t$ to a D-dimensional vector though matrix of dimention $|V|\times D$ (D=32 in this example).
diff --git a/04.word2vec/index.cn.html b/04.word2vec/index.cn.html
index fef5c0e..f8a4a0b 100644
--- a/04.word2vec/index.cn.html
+++ b/04.word2vec/index.cn.html
@@ -251,15 +251,6 @@ N = 5 # 训练5-Gram
 
 用于保存和加载word_dict和embedding table的函数
 ```python
-def wordemb(inlayer):
-    wordemb = paddle.layer.table_projection(
-        input=inlayer,
-        size=embsize,
-        param_attr=paddle.attr.Param(
-            name="_proj", initial_std=0.001, learning_rate=1, l2_rate=0))
-    return wordemb
-
-
 # save and load word dict and embedding table
 def save_dict_and_embedding(word_dict, embeddings):
     with open("word_dict", "w") as f:
@@ -267,6 +258,17 @@ def save_dict_and_embedding(word_dict, embeddings):
             f.write(key + " " + str(word_dict[key]) + "\n")
     with open("embedding_table", "w") as f:
         numpy.savetxt(f, embeddings, delimiter=',', newline='\n')
+
+
+def load_dict_and_embedding():
+    word_dict = dict()
+    with open("word_dict", "r") as f:
+        for line in f:
+            key, value = line.strip().split(" ")
+            word_dict[key] = value
+
+    embeddings = numpy.loadtxt("embedding_table", delimiter=",")
+    return word_dict, embeddings
 ```
 
 接着，定义网络结构：
diff --git a/04.word2vec/index.html b/04.word2vec/index.html
index 1ed7c3a..b0c2b67 100644
--- a/04.word2vec/index.html
+++ b/04.word2vec/index.html
@@ -269,15 +269,6 @@ N = 5 # train 5-gram
 
 - functions used to save and load word dict and embedding table
 ```python
-def wordemb(inlayer):
-    wordemb = paddle.layer.table_projection(
-        input=inlayer,
-        size=embsize,
-        param_attr=paddle.attr.Param(
-            name="_proj", initial_std=0.001, learning_rate=1, l2_rate=0))
-    return wordemb
-
-
 # save and load word dict and embedding table
 def save_dict_and_embedding(word_dict, embeddings):
     with open("word_dict", "w") as f:
@@ -285,6 +276,17 @@ def save_dict_and_embedding(word_dict, embeddings):
             f.write(key + " " + str(word_dict[key]) + "\n")
     with open("embedding_table", "w") as f:
         numpy.savetxt(f, embeddings, delimiter=',', newline='\n')
+
+
+def load_dict_and_embedding():
+    word_dict = dict()
+    with open("word_dict", "r") as f:
+        for line in f:
+            key, value = line.strip().split(" ")
+            word_dict[key] = value
+
+    embeddings = numpy.loadtxt("embedding_table", delimiter=",")
+    return word_dict, embeddings
 ```
 
 - Map the $n-1$ words $w_{t-n+1},...w_{t-1}$ before $w_t$ to a D-dimensional vector though matrix of dimention $|V|\times D$ (D=32 in this example).
-- 
GitLab