diff --git a/paddle/gserver/dataproviders/PyDataProvider2.cpp b/paddle/gserver/dataproviders/PyDataProvider2.cpp
index c26e242534f2afcff396762adb085bf99303e2b5..b8079dc0796d0e300e65ac6b6b8d3bc826b1e504 100644
--- a/paddle/gserver/dataproviders/PyDataProvider2.cpp
+++ b/paddle/gserver/dataproviders/PyDataProvider2.cpp
@@ -647,7 +647,7 @@ public:
       DataBatch& gpuBatch = *batch;
       std::vector<Argument>& gpuArguments = gpuBatch.getStreams();
       gpuArguments.resize(cpuArguments.size());
-      gpuBatch.setSize(size);
+      gpuBatch.setSize(bsize);
       for (size_t i = 0; i < headers_.size(); ++i) {
         gpuArguments[i].resizeAndCopyFrom(
             cpuArguments[i], useGpu_, HPPL_STREAM_1);
diff --git a/python/paddle/trainer_config_helpers/data_sources.py b/python/paddle/trainer_config_helpers/data_sources.py
index 0ea8fc77eef9f5daeaa262ce7808db3e980f991c..ab9a2562dcccb394c0b24741ceeb10061e40cb9a 100644
--- a/python/paddle/trainer_config_helpers/data_sources.py
+++ b/python/paddle/trainer_config_helpers/data_sources.py
@@ -201,7 +201,7 @@ def define_py_data_sources2(train_list, test_list, module, obj, args=None):
         data.load_data_module = load_data_module
         data.load_data_object = load_data_object
         data.load_data_args = load_data_args
-        data.async_load_data = True
+        data.async_load_data = False
         return data
 
     define_py_data_sources(