diff --git a/python/paddle/fluid/inferencer.py b/python/paddle/fluid/inferencer.py
index 8c6dbd3b5ae5d8bcd8d0a136457c20003fd23ded..0c2620d69268ba701600f1e184b51b0aeec3f387 100644
--- a/python/paddle/fluid/inferencer.py
+++ b/python/paddle/fluid/inferencer.py
@@ -12,6 +12,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import contextlib
+
 import core
 
 import executor
@@ -41,31 +43,36 @@ class Inferencer(object):
             with unique_name.guard():
                 self.predict_var = infer_func()
 
+        with self._prog_and_scope_guard():
+            # load params from param_path into scope
+            io.load_params(executor.Executor(self.place), param_path)
+
         if parallel:
-            self.exe = parallel_executor.ParallelExecutor(
-                use_cuda=isinstance(self.place, core.CUDAPlace),
-                loss_name=self.predict_var.name)
+            with self._prog_and_scope_guard():
+                self.exe = parallel_executor.ParallelExecutor(
+                    use_cuda=isinstance(self.place, core.CUDAPlace),
+                    loss_name=self.predict_var.name)
         else:
             self.exe = executor.Executor(self.place)
-        with executor.scope_guard(self.scope):
-            # load params from param_path into scope
-            io.load_params(self.exe, param_path, self.inference_program)
 
-    def infer(self, inputs, return_numpy=True):
+    def infer(self, inputs):
         """
         :param inputs: a map of {"input_name": input_var} that will be feed into the inference program
         to get the predict value
-        :param return_numpy: if return numpy value for row tensor
         :return: the predict value of the inference model
         """
         if not isinstance(inputs, dict):
             raise ValueError(
                 "inputs should be a map of {'input_name': input_var}")
 
-        with executor.scope_guard(self.scope):
-            results = self.exe.run(self.inference_program,
-                                   feed=inputs,
-                                   fetch_list=[self.predict_var],
-                                   return_numpy=return_numpy)
+        with self._prog_and_scope_guard():
+            results = self.exe.run(feed=inputs,
+                                   fetch_list=[self.predict_var.name])
 
         return results
+
+    @contextlib.contextmanager
+    def _prog_and_scope_guard(self):
+        with framework.program_guard(main_program=self.inference_program):
+            with executor.scope_guard(self.scope):
+                yield
diff --git a/python/paddle/fluid/tests/book/high-level-api/fit_a_line/test_fit_a_line.py b/python/paddle/fluid/tests/book/high-level-api/fit_a_line/test_fit_a_line.py
index fbcf2a282f6421a546723a1d429c59fb304a0cc2..973142ccdfa3c8a6f56abeb2a5a5081784aa8db1 100644
--- a/python/paddle/fluid/tests/book/high-level-api/fit_a_line/test_fit_a_line.py
+++ b/python/paddle/fluid/tests/book/high-level-api/fit_a_line/test_fit_a_line.py
@@ -94,7 +94,7 @@ def infer(use_cuda, inference_program, save_dirname=None):
     tensor_x = numpy.random.uniform(0, 10, [batch_size, 13]).astype("float32")
 
     results = inferencer.infer({'x': tensor_x})
-    print("infer results: ", results[0])
+    print("infer results: ", numpy.array(results[0]))
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_conv.py b/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_conv.py
index f252a7e2b98b05d0c64533e9e24a902559be2f39..c1bae77ec449b341d86d1906dd7105271892ce1e 100644
--- a/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_conv.py
+++ b/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_conv.py
@@ -118,7 +118,7 @@ def infer(use_cuda, inference_program, save_dirname=None):
 
     results = inferencer.infer({'img': tensor_img})
 
-    print("infer results: ", results[0])
+    print("infer results: ", numpy.array(results[0]))
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_mlp.py b/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_mlp.py
index 9427a772f54fb58ca1f50ed792cccf5d8f9b3d84..ae915b8458a728aa0b9fdcdb1ae0ba4727c56d07 100644
--- a/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_mlp.py
+++ b/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_mlp.py
@@ -99,7 +99,7 @@ def infer(use_cuda, inference_program, save_dirname=None):
 
     results = inferencer.infer({'img': tensor_img})
 
-    print("infer results: ", results[0])
+    print("infer results: ", numpy.array(results[0]))
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/word2vec/no_test_word2vec_new_api.py b/python/paddle/fluid/tests/book/high-level-api/word2vec/no_test_word2vec_new_api.py
index 4f861e5aaeca7ce0f73450c09f9ddc1ed7417469..6d7495e4dd1cd4ae1486fb9a6dc5264bb26a5940 100644
--- a/python/paddle/fluid/tests/book/high-level-api/word2vec/no_test_word2vec_new_api.py
+++ b/python/paddle/fluid/tests/book/high-level-api/word2vec/no_test_word2vec_new_api.py
@@ -127,14 +127,12 @@ def infer(use_cuda, inference_program, save_path):
     third_word = create_random_lodtensor(lod, place, low=0, high=dict_size - 1)
     fourth_word = create_random_lodtensor(lod, place, low=0, high=dict_size - 1)
 
-    result = inferencer.infer(
-        {
-            'firstw': first_word,
-            'secondw': second_word,
-            'thirdw': third_word,
-            'forthw': fourth_word
-        },
-        return_numpy=False)
+    result = inferencer.infer({
+        'firstw': first_word,
+        'secondw': second_word,
+        'thirdw': third_word,
+        'forthw': fourth_word
+    })
     print(np.array(result[0]))