diff --git a/PaddleCV/PaddleDetection/slim/infer.py b/PaddleCV/PaddleDetection/slim/infer.py
index 4a212ad6b385fbc5e10dd8e04a8934645c3bd689..96a527f2e15d64ea59a9983049916b1654b2f423 100644
--- a/PaddleCV/PaddleDetection/slim/infer.py
+++ b/PaddleCV/PaddleDetection/slim/infer.py
@@ -19,6 +19,7 @@ from __future__ import print_function
 import os
 import sys
 import glob
+import time
 
 import numpy as np
 from PIL import Image
@@ -166,8 +167,29 @@ def main():
 
     imid2path = reader.imid2path
     keys = ['bbox']
+    infer_time = True
     for iter_id, data in enumerate(reader()):
         feed_data = [[d[0], d[1]] for d in data]
+        # for infer time
+        if infer_time:
+            warmup_times = 10
+            repeats_time = 30
+            feed_data_dict = feeder.feed(feed_data);
+            for i in range(warmup_times):
+                exe.run(infer_prog,
+                        feed=feed_data_dict,
+                        fetch_list=fetch_list,
+                        return_numpy=False)
+            start_time = time.time()
+            for i in range(repeats_time):
+                exe.run(infer_prog,
+                        feed=feed_data_dict,
+                        fetch_list=fetch_list,
+                        return_numpy=False)
+
+            print("infer time: {} ms/sample".format((time.time()-start_time) * 1000 / repeats_time))
+            infer_time = False
+
         outs = exe.run(infer_prog,
                        feed=feeder.feed(feed_data),
                        fetch_list=fetch_list,
diff --git a/PaddleCV/PaddleDetection/slim/quantization/README.md b/PaddleCV/PaddleDetection/slim/quantization/README.md
index f8378776584c0d5cae5d8507624b00b674e84d1f..c151678b7c08f8eb6fa5b9bf516832e6f75b3dea 100644
--- a/PaddleCV/PaddleDetection/slim/quantization/README.md
+++ b/PaddleCV/PaddleDetection/slim/quantization/README.md
@@ -228,7 +228,7 @@ FP32模型可使用PaddleLite进行加载预测，可参见教程[Paddle-Lite如
 
 >当前release的结果并非超参调优后的最好结果，仅做示例参考，后续我们会优化当前结果。
 
-### MobileNetV1
+### MobileNetV1-YOLO-V3
 
 | weight量化方式 | activation量化方式| Box ap |Paddle Fluid inference time(ms)| Paddle Lite inference time(ms)|
 |---|---|---|---|---|
@@ -237,8 +237,6 @@ FP32模型可使用PaddleLite进行加载预测，可参见教程[Paddle-Lite如
 |abs_max|moving_average_abs_max|- |- |-|
 |channel_wise_abs_max|abs_max|- |- |-|
 
->训练超参：
-
 
 ## FAQ
 
diff --git a/PaddleSlim/classification/infer.py b/PaddleSlim/classification/infer.py
index 9f87230153d70b0bf4bfda382f641f15f7915617..9d5680f3606487618bf81ace5b3dbb9f19b1ed4a 100644
--- a/PaddleSlim/classification/infer.py
+++ b/PaddleSlim/classification/infer.py
@@ -17,6 +17,7 @@ import sys
 import numpy as np
 import argparse
 import functools
+import time
 
 import paddle
 import paddle.fluid as fluid
@@ -46,9 +47,26 @@ def infer(args):
     test_reader = paddle.batch(reader.test(), batch_size=1)
     feeder = fluid.DataFeeder(place=place, feed_list=feed_target_names, program=test_program)
 
-    results=[] 
+    results=[]
+    #for infer time, if you don't need, please change infer_time to False
+    infer_time = True
     for batch_id, data in enumerate(test_reader()):
-
+        # for infer time
+        if infer_time:
+            warmup_times = 10
+            repeats_time = 30
+            feed_data = feeder.feed(data)
+            for i in range(warmup_times):
+                exe.run(test_program,
+                        feed=feed_data,
+                        fetch_list=fetch_targets)
+            start_time = time.time()
+            for i in range(repeats_time):
+                exe.run(test_program,
+                        feed=feed_data,
+                        fetch_list=fetch_targets)
+            print("infer time: {} ms/sample".format((time.time()-start_time) * 1000 / repeats_time))
+            infer_time = False
         # top1_acc, top5_acc
         result = exe.run(test_program,
                           feed=feeder.feed(data),