diff --git a/README.md b/README.md
index 67d65e98e8d7b978e25d9582cf21d2b222858e69..1ce6fabb55e231a7748bf2baeefc2d2fb4ffb2e5 100644
--- a/README.md
+++ b/README.md
@@ -42,7 +42,7 @@ The above pictures are the visualizations of the general ppocr_server model. For
 - Scan the QR code below with your Wechat, you can access to official technical exchange group. Look forward to your participation.
 
 <div align="center">
-<img src="./doc/joinus.PNG"  width = "200" height = "200" />
+<img src="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/joinus.PNG"  width = "200" height = "200" />
 </div>
 
 
diff --git a/README_ch.md b/README_ch.md
index d4870710a24a3c17a997a603b34d447ce8f9f0bd..9fe853f92510e540e35b7452f6ab00e5898ddb55 100755
--- a/README_ch.md
+++ b/README_ch.md
@@ -46,7 +46,7 @@ PaddleOCR同时支持动态图与静态图两种编程范式
 - 微信扫描二维码加入官方交流群，获得更高效的问题答疑，与各行各业开发者充分交流，期待您的加入。
 
 <div align="center">
-<img src="./doc/joinus.PNG"  width = "200" height = "200" />
+<img src="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/joinus.PNG"  width = "200" height = "200" />
 </div>
 
 ## 快速体验
diff --git a/tools/infer/predict_det.py b/tools/infer/predict_det.py
index 76c6a4478ae37e650901c8b8704e15e4a94911c4..b14825bdd8bad55b709d84bdf6df6575d90c7d95 100755
--- a/tools/infer/predict_det.py
+++ b/tools/infer/predict_det.py
@@ -39,10 +39,7 @@ class TextDetector(object):
         self.args = args
         self.det_algorithm = args.det_algorithm
         pre_process_list = [{
-            'DetResizeForTest': {
-                'limit_side_len': args.det_limit_side_len,
-                'limit_type': args.det_limit_type
-            }
+            'DetResizeForTest': None
         }, {
             'NormalizeImage': {
                 'std': [0.229, 0.224, 0.225],
diff --git a/tools/infer_det.py b/tools/infer_det.py
index d890970ec14c25815fed8366d9257495f7485e0d..913d617defea18fe881e6fd2212b1df20f7d26d3 100755
--- a/tools/infer_det.py
+++ b/tools/infer_det.py
@@ -97,7 +97,7 @@ def main():
             preds = model(images)
             post_result = post_process_class(preds, shape_list)
             boxes = post_result[0]['points']
-            # write resule
+            # write result
             dt_boxes_json = []
             for box in boxes:
                 tmp_json = {"transcription": ""}