From cff7e36b938bff5e8cdf4823bf0385642374b3ff Mon Sep 17 00:00:00 2001
From: JiabinYang <marsyang199376@gmail.com>
Date: Tue, 8 Jan 2019 06:22:43 +0000
Subject: [PATCH] refine readme and fix net conf bug

---
 fluid/PaddleRec/word2vec/README.md       |  2 +-
 fluid/PaddleRec/word2vec/network_conf.py | 18 ++++++++++++------
 fluid/PaddleRec/word2vec/train.py        |  2 +-
 3 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/fluid/PaddleRec/word2vec/README.md b/fluid/PaddleRec/word2vec/README.md
index 01e0696a..3534fa71 100644
--- a/fluid/PaddleRec/word2vec/README.md
+++ b/fluid/PaddleRec/word2vec/README.md
@@ -29,7 +29,7 @@ This model implement a skip-gram model of word2vector.
 Preprocess the training data to generate a word dict.
 
 ```bash
-python preprocess.py --data_path ./data/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled --dict_path data/1-billion_dict
+python preprocess.py --data_path ./data/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled --is_local --dict_path data/1-billion_dict
 ```
 if you would like to use our supported third party vocab, please set --other_dict_path as the directory of where you
 save the vocab you will use and set --with_other_dict flag on to using it.
diff --git a/fluid/PaddleRec/word2vec/network_conf.py b/fluid/PaddleRec/word2vec/network_conf.py
index 5b8e9513..16178c33 100644
--- a/fluid/PaddleRec/word2vec/network_conf.py
+++ b/fluid/PaddleRec/word2vec/network_conf.py
@@ -95,8 +95,7 @@ def skip_gram_word2vec(dict_size,
         capacity=64, feed_list=datas, name='py_reader', use_double_buffer=True)
 
     words = fluid.layers.read_file(py_reader)
-
-    emb = fluid.layers.embedding(
+    target_emb = fluid.layers.embedding(
         input=words[0],
         is_sparse=is_sparse,
         size=[dict_size, embedding_size],
@@ -104,16 +103,23 @@ def skip_gram_word2vec(dict_size,
             name='embeding',
             initializer=fluid.initializer.Normal(scale=1 /
                                                  math.sqrt(dict_size))))
-
+    context_emb = fluid.layers.embedding(
+        input=words[1],
+        is_sparse=is_sparse,
+        size=[dict_size, embedding_size],
+        param_attr=fluid.ParamAttr(
+            name='embeding',
+            initializer=fluid.initializer.Normal(scale=1 /
+                                                 math.sqrt(dict_size))))
     cost, cost_nce, cost_hs = None, None, None
 
     if with_nce:
-        cost_nce = nce_layer(emb, words[1], embedding_size, dict_size, 5,
+        cost_nce = nce_layer(target_emb, words[1], embedding_size, dict_size, 5,
                              "uniform", word_frequencys, None)
         cost = cost_nce
     if with_hsigmoid:
-        cost_hs = hsigmoid_layer(emb, words[1], words[2], words[3], dict_size,
-                                 is_sparse)
+        cost_hs = hsigmoid_layer(context_emb, words[0], words[2], words[3],
+                                 dict_size, is_sparse)
         cost = cost_hs
     if with_nce and with_hsigmoid:
         cost = fluid.layers.elementwise_add(cost_nce, cost_hs)
diff --git a/fluid/PaddleRec/word2vec/train.py b/fluid/PaddleRec/word2vec/train.py
index 40f7729f..ec4be60f 100644
--- a/fluid/PaddleRec/word2vec/train.py
+++ b/fluid/PaddleRec/word2vec/train.py
@@ -278,7 +278,7 @@ def train(args):
 
     optimizer = None
     if args.with_Adam:
-        optimizer = fluid.optimizer.Adam(learning_rate=1e-4)
+        optimizer = fluid.optimizer.Adam(learning_rate=1e-4, lazy_mode=True)
     else:
         optimizer = fluid.optimizer.SGD(learning_rate=1e-4)
 
-- 
GitLab