diff --git a/model_zoo/official/cv/FCN8s/README.md b/model_zoo/official/cv/FCN8s/README.md
index 837d8ab74d..e0dc23af10 100644
--- a/model_zoo/official/cv/FCN8s/README.md
+++ b/model_zoo/official/cv/FCN8s/README.md
@@ -52,13 +52,13 @@ Dataset used:
 
 在通过官方网站安装MindSpore之后，你可以通过如下步骤开始训练以及评估：
 
-- runing on Ascend with default paramaters
+- running on Ascend with default parameters
 
   ```python
   # run training example
   python train.py --device_id device_id
 
-  # run evaluation example with default paramaters
+  # run evaluation example with default parameters
   python eval.py --device_id device_id
   ```
 
@@ -202,7 +202,7 @@ Dataset used:
 | outputs                    | probability
 | Loss                       | 0.038
 | Speed                      | 1pc: 564.652 ms/step;
-| Scripts                    | [FCN script](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/cv/FCN)
+| Scripts                    | [FCN script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/FCN8s)
 
 ### Inference Performance
 
diff --git a/model_zoo/official/cv/openpose/README.md b/model_zoo/official/cv/openpose/README.md
index 04e73e0e97..68798789dd 100644
--- a/model_zoo/official/cv/openpose/README.md
+++ b/model_zoo/official/cv/openpose/README.md
@@ -41,7 +41,7 @@ In the currently provided training script, the coco2017 data set is used as an e
  ````bash
      wget http://images.cocodataset.org/zips/train2017.zip
      wget http://images.cocodataset.org/zips/val2017.zip
-     wget http://images.cocodataset.org/annotations/annotations2017.zip
+     wget http://images.cocodataset.org/annotations/annotations_trainval2017.zip
 ````
 
 - Create the mask dataset.
diff --git a/model_zoo/research/recommend/autodis/README.md b/model_zoo/research/recommend/autodis/README.md
index c35e569ecc..d904ea0909 100644
--- a/model_zoo/research/recommend/autodis/README.md
+++ b/model_zoo/research/recommend/autodis/README.md
@@ -32,7 +32,7 @@ AutoDis leverages a set of meta-embeddings for each numerical field, which are s
 
 # [Dataset](#contents)
 
-- [1] A dataset [Criteo](https://s3-eu-west-1.amazonaws.com/kaggle-display-advertising-challenge-dataset/dac.tar.gz) used in  Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, Xiuqiang He. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction[J]. 2017.
+- [1] A dataset Criteo used in  Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, Xiuqiang He. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction[J]. 2017.
 
 # [Environment Requirements](#contents)
 
@@ -48,7 +48,7 @@ AutoDis leverages a set of meta-embeddings for each numerical field, which are s
 
 After installing MindSpore via the official website, you can start training and evaluation as follows:
 
-- runing on Ascend
+- running on Ascend
 
   ```python
   # run training example