diff --git a/modules/image/object_detection/yolov3_darknet53_pedestrian/README.md b/modules/image/object_detection/yolov3_darknet53_pedestrian/README.md
index 1cdc1376737f4604e673c401facf3ee541a2939d..c1ba42e790fcc8f6be8536448a80fe10b376a700 100644
--- a/modules/image/object_detection/yolov3_darknet53_pedestrian/README.md
+++ b/modules/image/object_detection/yolov3_darknet53_pedestrian/README.md
@@ -101,19 +101,13 @@
         - save\_path (str, optional): 识别结果的保存路径 (仅当visualization=True时存在)
 
   - ```python
-    def save_inference_model(dirname,
-                             model_filename=None,
-                             params_filename=None,
-                             combined=True)
+    def save_inference_model(dirname)
     ```
     - 将模型保存到指定路径。
 
     - **参数**
 
-      - dirname: 存在模型的目录名称； <br/>
-      - model\_filename: 模型文件名称，默认为\_\_model\_\_； <br/>
-      - params\_filename: 参数文件名称，默认为\_\_params\_\_(仅当`combined`为True时生效)；<br/>
-      - combined: 是否将参数保存到统一的一个文件中。
+      - dirname: 模型保存路径 <br/>
 
 
 ## 四、服务部署
@@ -171,6 +165,10 @@
 
    移除 fluid api
 
+* 1.1.0
+
+   修复推理模型无法导出的问题
+
   - ```shell
-    $ hub install yolov3_darknet53_pedestrian==1.0.3
+    $ hub install yolov3_darknet53_pedestrian==1.1.0
     ```
diff --git a/modules/image/object_detection/yolov3_darknet53_pedestrian/README_en.md b/modules/image/object_detection/yolov3_darknet53_pedestrian/README_en.md
index 09d82d3919cf9e53ee0ef625be26ee0a4468fd02..faaf48e3cd668ff9959c378b6b7f2fa5e7886293 100644
--- a/modules/image/object_detection/yolov3_darknet53_pedestrian/README_en.md
+++ b/modules/image/object_detection/yolov3_darknet53_pedestrian/README_en.md
@@ -100,19 +100,13 @@
         - save\_path (str, optional): output path for saving results
 
   - ```python
-    def save_inference_model(dirname,
-                             model_filename=None,
-                             params_filename=None,
-                             combined=True)
+    def save_inference_model(dirname)
     ```
     - Save model to specific path
 
     - **Parameters**
 
-      - dirname: output dir for saving model
-      - model\_filename: filename for saving model
-      - params\_filename: filename for saving parameters
-      - combined: whether save parameters into one file
+      - dirname: model save path
 
 
 ## IV.Server Deployment
@@ -170,6 +164,10 @@
 
    Remove fluid api
 
+* 1.1.0
+
+   Fix bug of save_inference_model
+
   - ```shell
-    $ hub install yolov3_darknet53_pedestrian==1.0.3
+    $ hub install yolov3_darknet53_pedestrian==1.1.0
     ```
diff --git a/modules/image/object_detection/yolov3_darknet53_pedestrian/module.py b/modules/image/object_detection/yolov3_darknet53_pedestrian/module.py
index 5b8a4c8424d6dc759d916c920cbe0ea70ccb6d88..7d52f1fef08894cdc5bbd68d14383b8459ebd23f 100644
--- a/modules/image/object_detection/yolov3_darknet53_pedestrian/module.py
+++ b/modules/image/object_detection/yolov3_darknet53_pedestrian/module.py
@@ -8,30 +8,29 @@ from functools import partial
 
 import numpy as np
 import paddle
+import paddle.jit
+import paddle.static
 from paddle.inference import Config
 from paddle.inference import create_predictor
-from yolov3_darknet53_pedestrian.data_feed import reader
-from yolov3_darknet53_pedestrian.processor import base64_to_cv2
-from yolov3_darknet53_pedestrian.processor import load_label_info
-from yolov3_darknet53_pedestrian.processor import postprocess
+from .data_feed import reader
+from .processor import base64_to_cv2
+from .processor import load_label_info
+from .processor import postprocess
 
-import paddlehub as hub
-from paddlehub.common.paddle_helper import add_vars_prefix
 from paddlehub.module.module import moduleinfo
 from paddlehub.module.module import runnable
 from paddlehub.module.module import serving
 
 
 @moduleinfo(name="yolov3_darknet53_pedestrian",
-            version="1.0.3",
+            version="1.1.0",
             type="CV/object_detection",
             summary="Baidu's YOLOv3 model for pedestrian detection, with backbone DarkNet53.",
             author="paddlepaddle",
             author_email="paddle-dev@baidu.com")
-class YOLOv3DarkNet53Pedestrian(hub.Module):
-
-    def _initialize(self):
-        self.default_pretrained_model_path = os.path.join(self.directory, "yolov3_darknet53_pedestrian_model")
+class YOLOv3DarkNet53Pedestrian:
+    def __init__(self):
+        self.default_pretrained_model_path = os.path.join(self.directory, "yolov3_darknet53_pedestrian_model", "model")
         self.label_names = load_label_info(os.path.join(self.directory, "label_file.txt"))
         self._set_config()
 
@@ -39,7 +38,9 @@ class YOLOv3DarkNet53Pedestrian(hub.Module):
         """
         predictor config setting.
         """
-        cpu_config = Config(self.default_pretrained_model_path)
+        model = self.default_pretrained_model_path+'.pdmodel'
+        params = self.default_pretrained_model_path+'.pdiparams'
+        cpu_config = Config(model, params)
         cpu_config.disable_glog_info()
         cpu_config.disable_gpu()
         cpu_config.switch_ir_optim(False)
@@ -52,7 +53,7 @@ class YOLOv3DarkNet53Pedestrian(hub.Module):
         except:
             use_gpu = False
         if use_gpu:
-            gpu_config = Config(self.default_pretrained_model_path)
+            gpu_config = Config(model, params)
             gpu_config.disable_glog_info()
             gpu_config.enable_use_gpu(memory_pool_init_size_mb=500, device_id=0)
             self.gpu_predictor = create_predictor(gpu_config)
@@ -125,24 +126,6 @@ class YOLOv3DarkNet53Pedestrian(hub.Module):
             res.extend(output)
         return res
 
-    def save_inference_model(self, dirname, model_filename=None, params_filename=None, combined=True):
-        if combined:
-            model_filename = "__model__" if not model_filename else model_filename
-            params_filename = "__params__" if not params_filename else params_filename
-        place = paddle.CPUPlace()
-        exe = paddle.Executor(place)
-
-        program, feeded_var_names, target_vars = paddle.static.load_inference_model(
-            dirname=self.default_pretrained_model_path, executor=exe)
-
-        paddle.static.save_inference_model(dirname=dirname,
-                                           main_program=program,
-                                           executor=exe,
-                                           feeded_var_names=feeded_var_names,
-                                           target_vars=target_vars,
-                                           model_filename=model_filename,
-                                           params_filename=params_filename)
-
     @serving
     def serving_method(self, images, **kwargs):
         """
diff --git a/modules/image/object_detection/yolov3_darknet53_pedestrian/processor.py b/modules/image/object_detection/yolov3_darknet53_pedestrian/processor.py
index 356ce0342b2eb0536ffbd4d1420c7f21b3124431..25390dcf85832d28f83348b5dd47aa9294890ee9 100644
--- a/modules/image/object_detection/yolov3_darknet53_pedestrian/processor.py
+++ b/modules/image/object_detection/yolov3_darknet53_pedestrian/processor.py
@@ -89,7 +89,7 @@ def load_label_info(file_path):
 
 def postprocess(paths, images, data_out, score_thresh, label_names, output_dir, handle_id, visualization=True):
     """
-    postprocess the lod_tensor produced by fluid.Executor.run
+    postprocess the lod_tensor produced by Executor.run
 
     Args:
         paths (list[str]): The paths of images.
diff --git a/modules/image/object_detection/yolov3_darknet53_pedestrian/test.py b/modules/image/object_detection/yolov3_darknet53_pedestrian/test.py
new file mode 100644
index 0000000000000000000000000000000000000000..72a015d8c75b06f554b8f7dbdb51031461103f1a
--- /dev/null
+++ b/modules/image/object_detection/yolov3_darknet53_pedestrian/test.py
@@ -0,0 +1,108 @@
+import os
+import shutil
+import unittest
+
+import cv2
+import requests
+import paddlehub as hub
+
+
+class TestHubModule(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        img_url = 'https://ai-studio-static-online.cdn.bcebos.com/15310014bf794c87a1e3b289d904ecae122aafe8c8fe47fd98634e79a8e4012f'
+        if not os.path.exists('tests'):
+            os.makedirs('tests')
+        response = requests.get(img_url)
+        assert response.status_code == 200, 'Network Error.'
+        with open('tests/test.jpg', 'wb') as f:
+            f.write(response.content)
+        cls.module = hub.Module(name="yolov3_darknet53_pedestrian")
+
+    @classmethod
+    def tearDownClass(cls) -> None:
+        shutil.rmtree('tests')
+        shutil.rmtree('inference')
+        shutil.rmtree('yolov3_pedestrian_detect_output')
+
+    def test_object_detection1(self):
+        results = self.module.object_detection(
+            paths=['tests/test.jpg']
+        )
+        bbox = results[0]['data'][0]
+        label = bbox['label']
+        confidence = bbox['confidence']
+        left = bbox['left']
+        right = bbox['right']
+        top = bbox['top']
+        bottom = bbox['bottom']
+
+        self.assertEqual(label, 'pedestrian')
+        self.assertTrue(confidence > 0.5)
+        self.assertTrue(0 < left < 1000)
+        self.assertTrue(1000 < right < 3500)
+        self.assertTrue(500 < top < 1500)
+        self.assertTrue(1000 < bottom < 4500)
+
+    def test_object_detection2(self):
+        results = self.module.object_detection(
+            images=[cv2.imread('tests/test.jpg')]
+        )
+        bbox = results[0]['data'][0]
+        label = bbox['label']
+        confidence = bbox['confidence']
+        left = bbox['left']
+        right = bbox['right']
+        top = bbox['top']
+        bottom = bbox['bottom']
+
+        self.assertEqual(label, 'pedestrian')
+        self.assertTrue(confidence > 0.5)
+        self.assertTrue(0 < left < 1000)
+        self.assertTrue(1000 < right < 3500)
+        self.assertTrue(500 < top < 1500)
+        self.assertTrue(1000 < bottom < 4500)
+
+    def test_object_detection3(self):
+        results = self.module.object_detection(
+            images=[cv2.imread('tests/test.jpg')],
+            visualization=False
+        )
+        bbox = results[0]['data'][0]
+        label = bbox['label']
+        confidence = bbox['confidence']
+        left = bbox['left']
+        right = bbox['right']
+        top = bbox['top']
+        bottom = bbox['bottom']
+
+        self.assertEqual(label, 'pedestrian')
+        self.assertTrue(confidence > 0.5)
+        self.assertTrue(0 < left < 1000)
+        self.assertTrue(1000 < right < 3500)
+        self.assertTrue(500 < top < 1500)
+        self.assertTrue(1000 < bottom < 4500)
+
+    def test_object_detection4(self):
+        self.assertRaises(
+            AssertionError,
+            self.module.object_detection,
+            paths=['no.jpg']
+        )
+
+    def test_object_detection5(self):
+        self.assertRaises(
+            AttributeError,
+            self.module.object_detection,
+            images=['test.jpg']
+        )
+
+    def test_save_inference_model(self):
+        self.module.save_inference_model('./inference/model')
+
+        self.assertTrue(os.path.exists('./inference/model.pdmodel'))
+        self.assertTrue(os.path.exists('./inference/model.pdiparams'))
+
+
+if __name__ == "__main__":
+    unittest.main()
\ No newline at end of file