diff --git a/python/paddle/v2/dataset/flowers.py b/python/paddle/v2/dataset/flowers.py
index e2a21e6e3e04e79fdfc225ce1b4496b6b69d1e89..634388094c804827657dc83d5c205e680625b156 100644
--- a/python/paddle/v2/dataset/flowers.py
+++ b/python/paddle/v2/dataset/flowers.py
@@ -116,7 +116,7 @@ def reader_creator(data_file,
             data = batch['data']
             labels = batch['label']
             for sample, label in itertools.izip(data, batch['label']):
-                yield sample, int(label)
+                yield sample, int(label) - 1
 
     if use_xmap:
         return xmap_readers(mapper, reader, cpu_count(), buffered_size)