Merge branch 'develop' into seqconcat

demo/sentiment/dataprovider.py

@@ -32,4 +32,6 @@ def process(settings, file_name):
             word_slot = [
                 settings.word_dict[w] for w in words if w in settings.word_dict
             ]
+            if not word_slot:
+                continue
             yield word_slot, label

demo/sentiment/predict.py

@@ -138,7 +138,11 @@ def main():
 
     batch = []
     for line in sys.stdin:
-        batch.append([predict.get_index(line)])
+        words = predict.get_index(line)
+        if words:
+            batch.append([words])
+        else:
+            print('All the words in [%s] are not in the dictionary.' % line)
         if len(batch) == batch_size:
             predict.batch_predict(batch)
             batch = []

doc/design/reader/README.md

@@ -107,7 +107,7 @@ We decided to use dictionary (`{"image":0, "label":1}`) instead of list (`["imag
 ### How to create custom data reader
 
 ```python
-def image_reader(image_path, label_path):
+def image_reader(image_path, label_path, n):
 	f = open(image_path)
 	l = open(label_path)
 	images = numpy.fromfile(
@@ -117,9 +117,10 @@ def image_reader(image_path, label_path):
 	for i in xrange(n):
 		yield images[i, :], labels[i] # a single entry of data is created each time
 	f.close()
+	l.close()
 
 # use python lambda to change image_reader into a function with no parameters.
-reader = lambda : image_reader("/path/to/image_file", "/path/to/label_file")
+reader = lambda : image_reader("/path/to/image_file", "/path/to/label_file", 1024)
 paddle.train(reader, {"image":0, "label":1}, ...)
 ```