diff --git a/official/cv/faster_rcnn/README.md b/official/cv/faster_rcnn/README.md
index 9086d9017b771c7b2b56c3a6153ca17a7b257c5f..b39180f0435890aecf1b14921c86bc4df2d696b1 100644
--- a/official/cv/faster_rcnn/README.md
+++ b/official/cv/faster_rcnn/README.md
@@ -101,8 +101,8 @@ After installing MindSpore via the official website, you can start training and
 Note:
 
 1. the first run will generate the mindeocrd file, which will take a long time.
-2. pretrained model is a resnet50 checkpoint that trained over ImageNet2012.you can train it with [resnet50](https://gitee.com/qujianwei/mindspore/tree/master/model_zoo/official/cv/resnet) scripts in modelzoo, and use src/convert_checkpoint.py to get the pretrain model.
-3. BACKBONE_MODEL is a checkpoint file trained with [resnet50](https://gitee.com/qujianwei/mindspore/tree/master/model_zoo/official/cv/resnet) scripts in modelzoo.PRETRAINED_MODEL is a checkpoint file after convert.VALIDATION_JSON_FILE is label file. CHECKPOINT_PATH is a checkpoint file after trained.
+2. pretrained model is a resnet50 checkpoint that trained over ImageNet2012.you can train it with [resnet50](https://gitee.com/mindspore/models/tree/master/official/cv/resnet) scripts in modelzoo, and use src/convert_checkpoint.py to get the pretrain model.
+3. BACKBONE_MODEL is a checkpoint file trained with [resnet50](https://gitee.com/mindspore/models/tree/master/official/cv/resnet) scripts in modelzoo.PRETRAINED_MODEL is a checkpoint file after convert.VALIDATION_JSON_FILE is label file. CHECKPOINT_PATH is a checkpoint file after trained.
 
 ## Run on Ascend
 
diff --git a/official/cv/faster_rcnn/README_CN.md b/official/cv/faster_rcnn/README_CN.md
index 405fbdd17ac900353bbe163a50b04df761d73dd8..192809e95e6c8a05aae9aa54dfaad7d6fc4310e4 100644
--- a/official/cv/faster_rcnn/README_CN.md
+++ b/official/cv/faster_rcnn/README_CN.md
@@ -102,8 +102,8 @@ Faster R-CNN鏄竴涓袱闃舵鐩爣妫€娴嬬綉缁滐紝璇ョ綉缁滈噰鐢≧PN锛屽彲浠�
 娉ㄦ剰锛�
 
 1. 绗竴娆¤繍琛岀敓鎴怣indRecord鏂囦欢锛岃€楁椂杈冮暱銆�
-2. 棰勮缁冩ā鍨嬫槸鍦↖mageNet2012涓婅缁冪殑ResNet-50妫€鏌ョ偣銆備綘鍙互浣跨敤ModelZoo涓� [resnet50](https://gitee.com/qujianwei/mindspore/tree/master/model_zoo/official/cv/resnet) 鑴氭湰鏉ヨ缁�, 鐒跺悗浣跨敤src/convert_checkpoint.py鎶婅缁冨ソ鐨剅esnet50鐨勬潈閲嶆枃浠惰浆鎹负鍙姞杞界殑鏉冮噸鏂囦欢銆�
-3. BACKBONE_MODEL鏄€氳繃modelzoo涓殑[resnet50](https://gitee.com/qujianwei/mindspore/tree/master/model_zoo/official/cv/resnet)鑴氭湰璁粌鐨勩€侾RETRAINED_MODEL鏄粡杩囪浆鎹㈠悗鐨勬潈閲嶆枃浠躲€俈ALIDATION_JSON_FILE涓烘爣绛炬枃浠躲€侰HECKPOINT_PATH鏄缁冨悗鐨勬鏌ョ偣鏂囦欢銆�
+2. 棰勮缁冩ā鍨嬫槸鍦↖mageNet2012涓婅缁冪殑ResNet-50妫€鏌ョ偣銆備綘鍙互浣跨敤ModelZoo涓� [resnet50](https://gitee.com/mindspore/models/tree/master/official/cv/resnet) 鑴氭湰鏉ヨ缁�, 鐒跺悗浣跨敤src/convert_checkpoint.py鎶婅缁冨ソ鐨剅esnet50鐨勬潈閲嶆枃浠惰浆鎹负鍙姞杞界殑鏉冮噸鏂囦欢銆�
+3. BACKBONE_MODEL鏄€氳繃modelzoo涓殑[resnet50](https://gitee.com/mindspore/models/tree/master/official/cv/resnet)鑴氭湰璁粌鐨勩€侾RETRAINED_MODEL鏄粡杩囪浆鎹㈠悗鐨勬潈閲嶆枃浠躲€俈ALIDATION_JSON_FILE涓烘爣绛炬枃浠躲€侰HECKPOINT_PATH鏄缁冨悗鐨勬鏌ョ偣鏂囦欢銆�
 
 ## 鍦ˋscend涓婅繍琛�
 
diff --git a/official/cv/maskrcnn/README.md b/official/cv/maskrcnn/README.md
index f27275e927ab87d2e75042f53e2562e841512743..6d5c0851390d065e0617c6789f295329ae6cafde 100644
--- a/official/cv/maskrcnn/README.md
+++ b/official/cv/maskrcnn/README.md
@@ -115,7 +115,7 @@ pip install mmcv=0.2.14
     Note:
     1. To speed up data preprocessing, MindSpore provide a data format named MindRecord, hence the first step is to generate MindRecord files based on COCO2017 dataset before training. The process of converting raw COCO2017 dataset to MindRecord format may take about 4 hours.
     2. For distributed training, a [hccl configuration file](https://gitee.com/mindspore/models/tree/master/utils/hccl_tools) with JSON format needs to be created in advance.
-    3. PRETRAINED_CKPT is a resnet50 checkpoint that trained over ImageNet2012.you can train it with [resnet50](https://gitee.com/qujianwei/mindspore/tree/master/model_zoo/official/cv/resnet) scripts in modelzoo, and use src/convert_checkpoint.py to get the pretrain checkpoint file.
+    3. PRETRAINED_CKPT is a resnet50 checkpoint that trained over ImageNet2012.you can train it with [resnet50](https://gitee.com/mindspore/models/tree/master/official/cv/resnet) scripts in modelzoo, and use src/convert_checkpoint.py to get the pretrain checkpoint file.
     4. For large models like MaskRCNN, it's better to export an external environment variable `export HCCL_CONNECT_TIMEOUT=600` to extend hccl connection checking time from the default 120 seconds to 600 seconds. Otherwise, the connection could be timeout since compiling time increases with the growth of model size.
 
 4. Execute eval script.
diff --git a/official/cv/maskrcnn/README_CN.md b/official/cv/maskrcnn/README_CN.md
index 38c6c8b0850655c8f85fcb2f13397c4573050985..1aaa9fd8b9aea08c6ebdef85d736c06d40ff48c5 100644
--- a/official/cv/maskrcnn/README_CN.md
+++ b/official/cv/maskrcnn/README_CN.md
@@ -117,7 +117,7 @@ pip install mmcv=0.2.14
     娉細
     1. 涓哄姞蹇暟鎹澶勭悊閫熷害锛孧indSpore鎻愪緵浜哅indRecord鏁版嵁鏍煎紡銆傚洜姝わ紝璁粌鍓嶉鍏堥渶瑕佺敓鎴愬熀浜嶤OCO2017鏁版嵁闆嗙殑MindRecord鏂囦欢銆侰OCO2017鍘熷鏁版嵁闆嗚浆鎹负MindRecord鏍煎紡澶ф闇€瑕�4灏忔椂銆�
     2. 杩涜鍒嗗竷寮忚缁冨墠锛岄渶瑕佹彁鍓嶅垱寤篔SON鏍煎紡鐨刐hccl閰嶇疆鏂囦欢](https://gitee.com/mindspore/models/tree/master/utils/hccl_tools)銆�
-    3. PRETRAINED_CKPT鏄竴涓猂esNet50妫€鏌ョ偣锛岄€氳繃ImageNet2012璁粌銆備綘鍙互浣跨敤ModelZoo涓� [resnet50](https://gitee.com/qujianwei/mindspore/tree/master/model_zoo/official/cv/resnet) 鑴氭湰鏉ヨ缁�, 鐒跺悗浣跨敤src/convert_checkpoint.py鎶婅缁冨ソ鐨剅esnet50鐨勬潈閲嶆枃浠惰浆鎹负鍙姞杞界殑鏉冮噸鏂囦欢銆�
+    3. PRETRAINED_CKPT鏄竴涓猂esNet50妫€鏌ョ偣锛岄€氳繃ImageNet2012璁粌銆備綘鍙互浣跨敤ModelZoo涓� [resnet50](https://gitee.com/mindspore/models/tree/master/official/cv/resnet) 鑴氭湰鏉ヨ缁�, 鐒跺悗浣跨敤src/convert_checkpoint.py鎶婅缁冨ソ鐨剅esnet50鐨勬潈閲嶆枃浠惰浆鎹负鍙姞杞界殑鏉冮噸鏂囦欢銆�
 
 4. 鎵ц璇勪及鑴氭湰銆�
    璁粌缁撴潫鍚庯紝鎸夌収濡備笅姝ラ鍚姩璇勪及锛�