Merge pull request #1307 from reyoung/feature/fix_bug_in_dp2

Temporary disable async load data in PyDP2.

.travis.yml

@@ -54,7 +54,9 @@ before_install:
     fi
   - if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then paddle/scripts/travis/before_install.osx.sh; fi
   - if [[ "$JOB" == "PRE_COMMIT" ]]; then sudo ln -s /usr/bin/clang-format-3.8 /usr/bin/clang-format; fi
-  - pip install numpy wheel protobuf sphinx recommonmark sphinx_rtd_theme virtualenv pre-commit requests==2.9.2 LinkChecker
+  # Paddle is using protobuf 3.1 currently. Protobuf 3.2 breaks the compatibility. So we specify the python 
+  # protobuf version.
+  - pip install numpy wheel 'protobuf==3.1' sphinx recommonmark sphinx_rtd_theme virtualenv pre-commit requests==2.9.2 LinkChecker
 script:
   - paddle/scripts/travis/main.sh
 notifications:

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);

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(

python/paddle/trainer_config_helpers/tests/configs/protostr/test_split_datasource.protostr

@@ -19,7 +19,7 @@ model_config {
 data_config {
   type: "py2"
   files: "train.list"
-  async_load_data: true
+  async_load_data: false
   for_test: false
   load_data_module: "a"
   load_data_object: "c"
@@ -58,7 +58,7 @@ opt_config {
 test_data_config {
   type: "py2"
   files: "test.list"
-  async_load_data: true
+  async_load_data: false
   for_test: true
   load_data_module: "b"
   load_data_object: "d"