diff --git a/.travis.yml b/.travis.yml
index 5b14f8e61e6143bb22a3aad5e0a9b11688b1b4be..047ca6ffe79bdaf013f6ef6dbf1a82bdb2f1f2b3 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -56,7 +56,7 @@ before_install:
   - if [[ "$TRAVIS_OS_NAME" == "linux" ]]; then sudo paddle/scripts/travis/before_install.linux.sh; fi
   - if [[ "$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 wheel protobuf sphinx recommonmark virtualenv numpy sphinx_rtd_theme pre-commit
+  - pip install wheel protobuf sphinx recommonmark virtualenv numpy sphinx_rtd_theme pre-commit requests==2.9.2 LinkChecker
 script:
   - paddle/scripts/travis/main.sh
 notifications:
diff --git a/paddle/gserver/gradientmachines/GradientMachine.h b/paddle/gserver/gradientmachines/GradientMachine.h
index 579eca71d4cdd2545a3a8be1c7f1dacfdd5ef66b..ad82869aec8318cef42f5a51a7e29c233bd23a95 100644
--- a/paddle/gserver/gradientmachines/GradientMachine.h
+++ b/paddle/gserver/gradientmachines/GradientMachine.h
@@ -212,11 +212,7 @@ public:
    * @note    This function will only been implemented and used in a
    *          multithreaded environment.
    */
-  virtual void start(const TrainerConfig& config,
-                     DataProviderPtr dataProvider) {
-    (void)config;
-    (void)dataProvider;
-  }
+  virtual void start() {}
 
   /**
    * @brief   check  each work-thread whether is failed/error/finish,
diff --git a/paddle/gserver/gradientmachines/MultiGradientMachine.cpp b/paddle/gserver/gradientmachines/MultiGradientMachine.cpp
index 88c098b3559d8d2918309aa48329af067f79bdd5..95a4c0e16a91f572a0d78e2fee113e03a82d2056 100644
--- a/paddle/gserver/gradientmachines/MultiGradientMachine.cpp
+++ b/paddle/gserver/gradientmachines/MultiGradientMachine.cpp
@@ -441,7 +441,7 @@ TrainerThread::TrainerThread(const ModelConfig& config,
 TrainerThread::~TrainerThread() { stop(); }
 
 void TrainerThread::start() {
-  gradientMachine_->start(*(TrainerConfig*)nullptr, (DataProviderPtr) nullptr);
+  gradientMachine_->start();
 
   computeThread_.reset(new std::thread([this]() { computeThread(); }));
 
diff --git a/paddle/gserver/gradientmachines/MultiNetwork.cpp b/paddle/gserver/gradientmachines/MultiNetwork.cpp
index 6eb3d8db962161ed4123b4ef4a4bb42147bfdf19..f1308f3721f8d6cf2645d7cd54b14959311ae17f 100644
--- a/paddle/gserver/gradientmachines/MultiNetwork.cpp
+++ b/paddle/gserver/gradientmachines/MultiNetwork.cpp
@@ -109,10 +109,9 @@ void MultiNetwork::onPassEnd() {
   }
 }
 
-void MultiNetwork::start(const TrainerConfig& config,
-                         DataProviderPtr dataProvider) {
+void MultiNetwork::start() {
   for (auto& subNetwork : subNetworks_) {
-    subNetwork->start(config, dataProvider);
+    subNetwork->start();
   }
 }
 
diff --git a/paddle/gserver/gradientmachines/MultiNetwork.h b/paddle/gserver/gradientmachines/MultiNetwork.h
index 89fbf32b4f90bceab60b8335c27b369806faaee1..f04406b983746965d72071c6ea6cfd2b6afcf9dc 100644
--- a/paddle/gserver/gradientmachines/MultiNetwork.h
+++ b/paddle/gserver/gradientmachines/MultiNetwork.h
@@ -54,7 +54,7 @@ public:
     return subNetworks_;
   }
 
-  virtual void start(const TrainerConfig& config, DataProviderPtr dataProvider);
+  virtual void start();
 
   virtual void finish();
 
diff --git a/paddle/gserver/gradientmachines/ParallelNeuralNetwork.cpp b/paddle/gserver/gradientmachines/ParallelNeuralNetwork.cpp
index 980a5851a2734ce42b3417d16a37987dc5ed6b24..c6e3a3b321efb06a1678ec760c514fe1181cd3d7 100644
--- a/paddle/gserver/gradientmachines/ParallelNeuralNetwork.cpp
+++ b/paddle/gserver/gradientmachines/ParallelNeuralNetwork.cpp
@@ -131,11 +131,7 @@ void ParallelNeuralNetwork::forwardBackward(const std::vector<Argument>& inArgs,
   backward(callback);
 }
 
-void ParallelNeuralNetwork::start(const TrainerConfig& config,
-                                  DataProviderPtr dataProvider) {
-  (void)config;
-  (void)dataProvider;
-
+void ParallelNeuralNetwork::start() {
   for (auto& thread : threads_) {
     thread->start();
   }
diff --git a/paddle/gserver/gradientmachines/ParallelNeuralNetwork.h b/paddle/gserver/gradientmachines/ParallelNeuralNetwork.h
index 8f445b1ded3eb8960dc06512dd3f80b00d284acc..39f5682a58e653cabaf4f3d3382d1e0bac5dece9 100644
--- a/paddle/gserver/gradientmachines/ParallelNeuralNetwork.h
+++ b/paddle/gserver/gradientmachines/ParallelNeuralNetwork.h
@@ -56,7 +56,7 @@ public:
                        PassType passType,
                        const UpdateCallback &callback = NULL);
 
-  virtual void start(const TrainerConfig &config, DataProviderPtr dataProvider);
+  virtual void start();
 
   void addComputeThread(int deviceId);
 
diff --git a/paddle/gserver/tests/LayerGradUtil.cpp b/paddle/gserver/tests/LayerGradUtil.cpp
index 1d5e7de1ba624d98c953efe1cdd2318548c4e914..57c176810fddf96828c210807673b7d1a3c739c0 100644
--- a/paddle/gserver/tests/LayerGradUtil.cpp
+++ b/paddle/gserver/tests/LayerGradUtil.cpp
@@ -303,13 +303,31 @@ void initDataLayer(TestConfig testConf,
   ICpuGpuVectorPtr sequenceStartPositions;
   ICpuGpuVectorPtr subSequenceStartPositions;
   IVectorPtr cpuSequenceDims;
-  for (size_t i = 0; i < testConf.inputDefs.size(); i++) {
+  for (size_t i = 0; i < testConf.inputDefs.size(); ++i) {
+    if (testConf.inputDefs[i].inputType != INPUT_SEQUENCE_LABEL) continue;
+
+    const std::vector<int>& labelSeqStartPositions =
+        testConf.inputDefs[i].labelSeqStartPositions;
+    if (labelSeqStartPositions.size() != 0) {
+      CHECK(!sequenceStartPositions);
+      CHECK_GE(labelSeqStartPositions.size(), 2);
+
+      sequenceStartPositions =
+          ICpuGpuVector::create(labelSeqStartPositions.size(), useGpu);
+      sequenceStartPositions->copyFrom(
+          labelSeqStartPositions.data(), labelSeqStartPositions.size(), useGpu);
+    }
+  }
+
+  for (size_t i = 0; i < testConf.inputDefs.size(); ++i) {
     LayerConfig config;
     config.set_name(testConf.inputDefs[i].name);
     config.set_type("data");
     config.set_size(testConf.inputDefs[i].dim);
     LayerPtr layer = LayerPtr(new DataLayer(config));
-    size_t numSequence = batchSize / 10 + 1;
+    size_t numSequence = sequenceStartPositions
+                             ? sequenceStartPositions->getSize() - 1
+                             : batchSize / 10 + 1;
 
     Argument data;
     auto fillData = [&](bool trans, int height, int width) {
@@ -336,9 +354,17 @@ void initDataLayer(TestConfig testConf,
         break;
       case INPUT_LABEL:
       case INPUT_SEQUENCE_LABEL:
-        data.ids = VectorT<int>::create(batchSize, useGpu);
-        // now rand number can be 0 to inputDefs[i].dim
-        data.ids->rand(testConf.inputDefs[i].dim);
+        if (testConf.inputDefs[i].labelInitValue.size() != 0) {
+          const std::vector<int>& labelInitValue =
+              testConf.inputDefs[i].labelInitValue;
+          CHECK_EQ(labelInitValue.size(), batchSize);
+          data.ids = VectorT<int>::create(batchSize, useGpu);
+          data.ids->copyFrom(labelInitValue.data(), batchSize);
+        } else {
+          data.ids = VectorT<int>::create(batchSize, useGpu);
+          // now rand number can be 0 to inputDefs[i].dim
+          data.ids->rand(testConf.inputDefs[i].dim);
+        }
         break;
       case INPUT_SPARSE_NON_VALUE_DATA:
         data.value = makeRandomSparseMatrix(
diff --git a/paddle/gserver/tests/LayerGradUtil.h b/paddle/gserver/tests/LayerGradUtil.h
index 62ac2d160fd916c5bb114341a442eac7df114c99..4e88ac0e81ef2596f14995be53f7c5c20ddba2d7 100644
--- a/paddle/gserver/tests/LayerGradUtil.h
+++ b/paddle/gserver/tests/LayerGradUtil.h
@@ -64,6 +64,9 @@ struct InputDef {
   size_t paraSize;
   ParaSparse sparse;
   bool isStatic;
+  std::vector<int> labelInitValue;
+  std::vector<int> labelSeqStartPositions;
+
   InputDef(InputType type, string nameIn, size_t dimIn, size_t sizeIn) {
     inputType = type;
     name = nameIn;
@@ -72,6 +75,23 @@ struct InputDef {
     sparse = {""};
     isStatic = false;
   }
+
+  InputDef(InputType type,
+           string nameIn,
+           size_t dimIn,
+           size_t sizeIn,
+           const std::vector<int>& labelInitValue,
+           const std::vector<int>& labelSeqStartPositions)
+      : labelInitValue(labelInitValue),
+        labelSeqStartPositions(labelSeqStartPositions) {
+    inputType = type;
+    name = nameIn;
+    dim = dimIn;
+    paraSize = sizeIn;
+    sparse = {""};
+    isStatic = false;
+  }
+
   InputDef(InputType type,
            string nameIn,
            size_t dimIn,
diff --git a/paddle/gserver/tests/test_ConvTrans.cpp b/paddle/gserver/tests/test_ConvTrans.cpp
index 99202c2d5702a9569c3a9a92897a8a0e38b8e2a6..dd3378304b433c135881310eb89273b6bf492af2 100644
--- a/paddle/gserver/tests/test_ConvTrans.cpp
+++ b/paddle/gserver/tests/test_ConvTrans.cpp
@@ -206,8 +206,8 @@ TEST(Layer, convTransLayerFwd2) {
                  /* filter_size */ 5,
                  result);
 
-  float resultData[] = {1, 2, 2, 2, 1, 2, 4, 4, 4, 2, 2, 4, 4,
-                        4, 2, 2, 4, 4, 4, 2, 1, 2, 2, 2, 1};
+  real resultData[] = {1, 2, 2, 2, 1, 2, 4, 4, 4, 2, 2, 4, 4,
+                       4, 2, 2, 4, 4, 4, 2, 1, 2, 2, 2, 1};
   result->setData(resultData);
   doOneConvtTest(/* imgSize */ 5,
                  /* output_x */ 2,
@@ -216,8 +216,8 @@ TEST(Layer, convTransLayerFwd2) {
                  /* filter_size */ 4,
                  result);
 
-  float resultData2[] = {1, 2, 2, 2, 1, 2, 4, 4, 4, 2, 2, 4, 4,
-                         4, 2, 2, 4, 4, 4, 2, 1, 2, 2, 2, 1};
+  real resultData2[] = {1, 2, 2, 2, 1, 2, 4, 4, 4, 2, 2, 4, 4,
+                        4, 2, 2, 4, 4, 4, 2, 1, 2, 2, 2, 1};
   result->setData(resultData2);
   doOneConvtTest(/* imgSize */ 5,
                  /* output_x */ 2,
@@ -226,8 +226,8 @@ TEST(Layer, convTransLayerFwd2) {
                  /* filter_size */ 5,
                  result);
 
-  float resultData3[] = {1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 2, 2, 4,
-                         2, 2, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1};
+  real resultData3[] = {1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 2, 2, 4,
+                        2, 2, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1};
   result->setData(resultData3);
   doOneConvtTest(/* imgSize */ 5,
                  /* output_x */ 2,
diff --git a/paddle/gserver/tests/test_ConvUnify.cpp b/paddle/gserver/tests/test_ConvUnify.cpp
index 2ab18f886848d198b9063c7559790497ce131efe..ad99b50245cf56eb7db227fa582f6e3f41b47a7a 100644
--- a/paddle/gserver/tests/test_ConvUnify.cpp
+++ b/paddle/gserver/tests/test_ConvUnify.cpp
@@ -106,8 +106,8 @@ TEST(Layer, convParaUnified) {
 #ifndef PADDLE_ONLY_CPU
   MatrixPtr input, resultCpu, resultGpu;
   input = Matrix::create(1, 4 * 4, false, false);
-  float inputData[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16};
-  float param[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 9, 8, 7, 6, 5, 4, 3, 2, 1};
+  real inputData[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16};
+  real param[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 9, 8, 7, 6, 5, 4, 3, 2, 1};
 
   input->setData(inputData);
 
@@ -137,26 +137,9 @@ TEST(Layer, convParaUnified) {
   checkMatrixEqual(resultCpu, resultGpu);
 
   input = Matrix::create(1, 3 * 3 * 2, false, false);
-  float inputData2[] = {1,
-                        2,
-                        3,
-                        4,
-                        5,
-                        6,
-                        7,
-                        8,
-                        9,
-
-                        10,
-                        11,
-                        12,
-                        13,
-                        14,
-                        15,
-                        16,
-                        17,
-                        18};
-  float param2[] = {1, 2, 3, 4, 5, 6, 7, 8, 8, 7, 6, 5, 4, 3, 2, 1};
+  real inputData2[] = {
+      1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18};
+  real param2[] = {1, 2, 3, 4, 5, 6, 7, 8, 8, 7, 6, 5, 4, 3, 2, 1};
 
   input->setData(inputData2);
 
@@ -185,7 +168,7 @@ TEST(Layer, convParaUnified) {
                             true);
   checkMatrixEqual(resultCpu, resultGpu);
 
-  float param3[] = {1, 2, 3, 4, 4, 3, 2, 1};
+  real param3[] = {1, 2, 3, 4, 4, 3, 2, 1};
 
   resultCpu = doOneConvTest(/* imgSize */ 3,
                             /* output_x */ 2,
diff --git a/paddle/gserver/tests/test_NetworkCompare.cpp b/paddle/gserver/tests/test_NetworkCompare.cpp
index fc60228f816e0cea30ef764c59a8c7875ed4a0e8..0d261059555c971cd509e64802d6c70abc9d2fef 100644
--- a/paddle/gserver/tests/test_NetworkCompare.cpp
+++ b/paddle/gserver/tests/test_NetworkCompare.cpp
@@ -114,7 +114,7 @@ void calcGradient(DataIn& in, DataOut& out, const std::string& configPath) {
       parameters[i]->getBuf(PARAMETER_VALUE)->copyFrom(*in.paraValues[i]);
     }
   }
-  gradientMachine->start(trainer.getConfig(), nullptr);
+  gradientMachine->start();
   gradientMachine->forward(in.inArgs, &outArgs, PASS_TRAIN);
   for (size_t i = 0; i < in.outGrads.size(); i++) {
     // If the all the layers in the config have no parameters, also
diff --git a/paddle/gserver/tests/test_RecurrentGradientMachine.cpp b/paddle/gserver/tests/test_RecurrentGradientMachine.cpp
index e19cf35cd5eb0148879fc3d0d40ea9b106947f9a..150850da4d49a2320acc70ed370cf8728d5c9def 100644
--- a/paddle/gserver/tests/test_RecurrentGradientMachine.cpp
+++ b/paddle/gserver/tests/test_RecurrentGradientMachine.cpp
@@ -28,7 +28,7 @@ class TrainerForTest : public paddle::Trainer {
 public:
   void startTrain() {
     GradientMachine& gm = *this->trainerInternal_.getGradientMachine();
-    gm.start(this->getConfig(), dataProvider_);
+    gm.start();
   }
 
   void finishTrain() {
diff --git a/paddle/parameter/ParameterUpdaterBase.h b/paddle/parameter/ParameterUpdaterBase.h
index 88148d9b769e9b6eca90f9651a121e926543d7c2..b230e170c15f1b004c5357fb7d0ad2204d01f44b 100644
--- a/paddle/parameter/ParameterUpdaterBase.h
+++ b/paddle/parameter/ParameterUpdaterBase.h
@@ -38,7 +38,7 @@ public:
   virtual void startPass() {}
 
   // called by Trainer then finishing a pass, ruturn true if pass accepted
-  virtual bool finishPass(real cost = 0) { return true; }
+  virtual bool finishPass() { return true; }
 
   // called by Trainer before backward() of a batch
   // Return the type of pass it needs. This pass type will be passed
@@ -112,9 +112,9 @@ public:
         [&](int tid, size_t numThreads) { updaters_[tid]->startPass(); });
   }
 
-  virtual bool finishPass(real cost = 0) {
+  virtual bool finishPass() {
     syncThreadPool_->execPlusOwner(
-        [&](int tid, size_t numThreads) { updaters_[tid]->finishPass(cost); });
+        [&](int tid, size_t numThreads) { updaters_[tid]->finishPass(); });
     return true;
   }
 
diff --git a/paddle/scripts/travis/docs.sh b/paddle/scripts/travis/docs.sh
index 0bbb76a8a3caa27da0911af0fe87df7fbff617b4..8690fe1d40c935e119fefbc02f3a228d76d8c0f9 100755
--- a/paddle/scripts/travis/docs.sh
+++ b/paddle/scripts/travis/docs.sh
@@ -7,6 +7,10 @@ source ./common.sh
 cmake .. -DCMAKE_BUILD_TYPE=Debug -DWITH_GPU=OFF -DWITH_DOC=ON
 make paddle_docs paddle_docs_cn
 
+# check websites for broken links
+linkchecker doc/en/html/index.html
+linkchecker doc/cn/html/index.html
+
 # Parse Github URL
 REPO=`git config remote.origin.url`
 SSH_REPO=${REPO/https:\/\/github.com\//git@github.com:}
@@ -35,8 +39,8 @@ git checkout $TARGET_BRANCH || git checkout --orphan $TARGET_BRANCH
 
 # remove old docs. mv new docs.
 rm -rf doc doc_cn
-mv ../doc_cn/html doc_cn
-mv ../doc/html doc
+mv ../doc/cn/html doc_cn
+mv ../doc/en/html doc
 
 # Check is there anything changed.
 set +e
diff --git a/paddle/trainer/ParameterUpdater.h b/paddle/trainer/ParameterUpdater.h
index 4dae77567f8f4d097c583567275d4b90122feb6a..c3207e63ce72b73a57c2e40c72c5259f0ae61bc9 100644
--- a/paddle/trainer/ParameterUpdater.h
+++ b/paddle/trainer/ParameterUpdater.h
@@ -102,9 +102,9 @@ public:
    * @param cost sum cost during one pass.
    * @return true if accept (used for owlqn).
    */
-  virtual bool finishPass(real cost) {
+  virtual bool finishPass() {
     optimizer_->finishPass();
-    return ParameterUpdater::finishPass(cost);
+    return ParameterUpdater::finishPass();
   }
 
   /**
@@ -220,9 +220,9 @@ public:
     averager_->startPass();
     SgdLocalUpdater::startPass();
   }
-  virtual bool finishPass(real cost) {
+  virtual bool finishPass() {
     averager_->finishPass();
-    return SgdLocalUpdater::finishPass(cost);
+    return SgdLocalUpdater::finishPass();
   }
 
   /// apply the averaged parameter to PARAMETER_VALUE
diff --git a/paddle/trainer/RemoteParameterUpdater.cpp b/paddle/trainer/RemoteParameterUpdater.cpp
index 630f55d998d9f5b5b2880aa02b025e6e56e1f064..6939738203f41e0c1f7204d54834e34b2cd90682 100644
--- a/paddle/trainer/RemoteParameterUpdater.cpp
+++ b/paddle/trainer/RemoteParameterUpdater.cpp
@@ -309,7 +309,7 @@ void RemoteParameterUpdater::startPass() {
   }
 }
 
-bool RemoteParameterUpdater::finishPass(real cost) {
+bool RemoteParameterUpdater::finishPass() {
   if (localUpdater_) {
     localUpdater_->finishPass();
   }
@@ -712,7 +712,7 @@ void SparseRemoteParameterUpdater::startPass() {
   }
 }
 
-bool SparseRemoteParameterUpdater::finishPass(real cost) {
+bool SparseRemoteParameterUpdater::finishPass() {
   if (config_.algorithm() == TrainAlgorithm::SGD) {
     parameterClient_->waitPassFinish();
   } else {
diff --git a/paddle/trainer/RemoteParameterUpdater.h b/paddle/trainer/RemoteParameterUpdater.h
index ec6ed443d33db1d695194092b34d6090a4b5ab94..7794b209009a3429e810074b61e1d5bffa8b3a4e 100644
--- a/paddle/trainer/RemoteParameterUpdater.h
+++ b/paddle/trainer/RemoteParameterUpdater.h
@@ -90,7 +90,7 @@ public:
    */
   virtual void finishBatch(real cost);
   virtual void startPass();
-  virtual bool finishPass(real cost);
+  virtual bool finishPass();
 
 #ifndef PADDLE_DISABLE_TIMER
   virtual void setForwardbackwardTime(uint64_t delta) {
@@ -281,7 +281,7 @@ public:
   /// send all sparse related parameters to all pservers
   virtual void finishBatch(real cost);
   virtual void startPass();
-  virtual bool finishPass(real cost);
+  virtual bool finishPass();
 
   virtual void apply();
   virtual void restore();
diff --git a/paddle/trainer/Tester.cpp b/paddle/trainer/Tester.cpp
index 24fac3e5a8141cbec912d276833ec491385b97ab..13aa28ae5d9699d267858d48e46797c756487ddd 100644
--- a/paddle/trainer/Tester.cpp
+++ b/paddle/trainer/Tester.cpp
@@ -257,7 +257,7 @@ void Tester::test() {
   CHECK(testDataProvider_) << "TestData is not specified";
   testDataProvider_->setSkipShuffle();
   testDataProvider_->reset();
-  gradientMachine_->start(*config_, testDataProvider_);
+  gradientMachine_->start();
 
   // For evaluation
   std::vector<std::string> modelList;
diff --git a/paddle/trainer/ThreadParameterUpdater.cpp b/paddle/trainer/ThreadParameterUpdater.cpp
index 2a76d5723ccb68896f8ddbfad31a9d7d84adcf55..870d4a4b0246fe244bbd3796ec14449eb181aad2 100644
--- a/paddle/trainer/ThreadParameterUpdater.cpp
+++ b/paddle/trainer/ThreadParameterUpdater.cpp
@@ -70,7 +70,7 @@ void SgdThreadUpdater::startPass() {
   }
 }
 
-bool SgdThreadUpdater::finishPass(real cost) {
+bool SgdThreadUpdater::finishPass() {
   catchUpWith();
 
   for (auto& para : parameters_) {
diff --git a/paddle/trainer/ThreadParameterUpdater.h b/paddle/trainer/ThreadParameterUpdater.h
index 198435c0f30056a9467b8a076c8443ae243e7c3f..880f1f9ddc49a1193ce23901419d988cae84eb88 100644
--- a/paddle/trainer/ThreadParameterUpdater.h
+++ b/paddle/trainer/ThreadParameterUpdater.h
@@ -47,7 +47,7 @@ public:
   virtual void startPass();
 
   // Use the finishPass() function of the base optimizer.
-  virtual bool finishPass(real cost);
+  virtual bool finishPass();
 
   virtual void init(const std::vector<ParameterPtr>& parameters);
   virtual PassType startBatch(int64_t batchSize);
diff --git a/paddle/trainer/Trainer.cpp b/paddle/trainer/Trainer.cpp
index 1eec2c432d235ef484b688db08aae8a39f878a85..09e0a213ab2d71890cfafb905b5969383acfe95a 100644
--- a/paddle/trainer/Trainer.cpp
+++ b/paddle/trainer/Trainer.cpp
@@ -308,7 +308,7 @@ static double genPerturbation(real* d, real* grad, size_t dim) {
 }
 
 real Trainer::checkGradient() {
-  trainerInternal_.getGradientMachine()->start(*config_, dataProvider_);
+  trainerInternal_.getGradientMachine()->start();
   std::vector<ParameterPtr>& parameters =
       trainerInternal_.getGradientMachine()->getNonStaticParameters();
   DataBatch dataBatch;
@@ -390,7 +390,7 @@ void Trainer::startTrain() {
     dataProvider_->reset();
   }
 
-  trainerInternal_.getGradientMachine()->start(*config_, dataProvider_);
+  trainerInternal_.getGradientMachine()->start();
 }
 
 void Trainer::finishTrain() { trainerInternal_.getGradientMachine()->finish(); }
@@ -537,7 +537,7 @@ void Trainer::trainOnePassBatch(int passId) {
 
   trainerInternal_.getGradientMachine()->onPassEnd();
 
-  bool accepted = trainerInternal_.getParameterUpdater()->finishPass(cost);
+  bool accepted = trainerInternal_.getParameterUpdater()->finishPass();
 
   globalStat.setThreadInfo(true);
   globalStat.printAllStatus();
diff --git a/paddle/trainer/tests/test_Compare.cpp b/paddle/trainer/tests/test_Compare.cpp
index 72fc76bea35e433eeb08ba625b4bf6afdda491fb..e855a8fe2e09aa0f16a73f3e7bcc2f32921092f8 100644
--- a/paddle/trainer/tests/test_Compare.cpp
+++ b/paddle/trainer/tests/test_Compare.cpp
@@ -50,7 +50,7 @@ void calcGradient(bool useGpu, comData& Data) {
   trainer.getDataProvider()->getNextBatch(batchSize, &dataBatch);
   CHECK(dataBatch.getSize()) << "No data from data provider";
   vector<Argument>& inArgs = dataBatch.getStreams();
-  trainer.getGradientMachine()->start(trainer.getConfig(), nullptr);
+  trainer.getGradientMachine()->start();
   for (int i = 0; i < 2; ++i) {
     trainer.getGradientMachine()->forwardBackward(
         inArgs, &Data.outArgs, PASS_TRAIN);
diff --git a/paddle/trainer/tests/test_CompareTwoNets.cpp b/paddle/trainer/tests/test_CompareTwoNets.cpp
index 80c61e259e71dd31d7637072248b22a2910c532e..94f65e545d116c802fb4877dc14f07aaaf83a4fb 100644
--- a/paddle/trainer/tests/test_CompareTwoNets.cpp
+++ b/paddle/trainer/tests/test_CompareTwoNets.cpp
@@ -72,7 +72,7 @@ void calcGradient(ComData& data, const string configFile) {
   CHECK(dataBatch.getSize()) << "No data from data provider";
   vector<Argument>& inArgs = dataBatch.getStreams();
 
-  trainer.getGradientMachine()->start(trainer.getConfig(), nullptr);
+  trainer.getGradientMachine()->start();
   trainer.getGradientMachine()->forwardBackward(
       inArgs, &data.outArgs, PASS_TRAIN);
 
diff --git a/python/paddle/trainer/config_parser.py b/python/paddle/trainer/config_parser.py
index 1f537d403220c1816218b9e356734a49297267fc..62e8258c98a68d5fea5498bf0260511a9ba7782b 100644
--- a/python/paddle/trainer/config_parser.py
+++ b/python/paddle/trainer/config_parser.py
@@ -498,9 +498,16 @@ class Input(Cfg):
             is_static=None,
             is_shared=None,
             update_hooks=None,
-            input_layer_argument=None, ):
+            input_layer_argument=None,
+            make_layer_name_in_submodel=True, ):
+        """
+        @param make_layer_name_in_submodel True by defalut, you might need to
+        set it carefully when adding Input in config_parser.py.
+        """
         self.add_keys(locals())
-        self.input_layer_name = MakeLayerNameInSubmodel(input_layer_name)
+        self.input_layer_name = MakeLayerNameInSubmodel(
+            input_layer_name
+        ) if make_layer_name_in_submodel else input_layer_name
 
 
 # Define a projection for iexed layer
@@ -1848,7 +1855,8 @@ class BatchNormLayer(LayerBase):
                     initial_std=0.0,
                     initial_mean=0.0,
                     is_static=True,
-                    is_shared=is_shared, ))
+                    is_shared=is_shared,
+                    make_layer_name_in_submodel=False, ))
 
         parallel_nn = bool(int(g_command_config_args.get("parallel_nn", 0)))
         cudnn_version = int(g_command_config_args.get("cudnn_version", 0))
@@ -1880,7 +1888,7 @@ class BatchNormLayer(LayerBase):
         # when either of it is non-zero. 
         if input_layer.width != 0 or input_layer.height != 0:
             self.set_cnn_layer(name, image_conf.img_size_y, image_conf.img_size,
-                               image_conf.channels, True)
+                               image_conf.channels, False)
         else:
             self.set_layer_size(input_layer.size)