Fix typo in docs

research/deeplab/README.md

@@ -39,12 +39,11 @@ work:
 }
 ```
 
-
 In the current implementation, we support adopting the following network
 backbones:
 
 1.  MobileNetv2 [8]: A fast network structure designed for mobile devices. **We
-will provide MobileNetv2 support in the next update. Please stay tuned.**
+    will provide MobileNetv2 support in the next update. Please stay tuned.**
 
 2.  Xception [9, 10]: A powerful network structure intended for server-side
     deployment.
@@ -86,13 +85,14 @@ Models:
 
 Misc:
 
-*   Please check <a href='g3doc/faq.md'>FAQ<a/a> if you have some questions before reporting the issues.<br>
+*   Please check <a href='g3doc/faq.md'>FAQ</a> if you have some questions before reporting the issues.<br>
 
 ## Getting Help
 
 To get help with issues you may encounter while using the DeepLab Tensorflow
-implementation, create a new question on [StackOverflow](https://stackoverflow.com/)
-with the tags "tensorflow" and "deeplab".
+implementation, create a new question on
+[StackOverflow](https://stackoverflow.com/) with the tags "tensorflow" and
+"deeplab".
 
 Please report bugs (i.e., broken code, not usage questions) to the
 tensorflow/models GitHub [issue

research/deeplab/g3doc/model_zoo.md

@@ -23,31 +23,10 @@ is available, since we have already fine-tuned the batch normalization for you.
 In the latter case, one could directly evaluate the checkpoints on VOC 2012 test
 set or use this checkpoint for demo.
 
-| Checkpoint name               | Network      | Pretrained | ASPP  | Decoder |
-:                               : backbone     : dataset    :       :         :
-| ----------------------------- | :----------: | :--------: | :---: | :-----: |
-| xception_coco_voc_trainaug    | Xception_65  | MS-COCO    | [6,   | OS = 4  |
-:                               :              : <br> VOC   : 12,   :         :
-:                               :              : 2012       : 18]   :         :
-:                               :              : train_aug  : for   :         :
-:                               :              : set        : OS=16 :         :
-:                               :              :            : <br>  :         :
-:                               :              :            : [12,  :         :
-:                               :              :            : 24,   :         :
-:                               :              :            : 36]   :         :
-:                               :              :            : for   :         :
-:                               :              :            : OS=8  :         :
-| xception_coco_voc_trainval    | Xception_65  | MS-COCO    | [6,   | OS = 4  |
-:                               :              : <br> VOC   : 12,   :         :
-:                               :              : 2012       : 18]   :         :
-:                               :              : train_aug  : for   :         :
-:                               :              : + trainval : OS=16 :         :
-:                               :              : sets       : <br>  :         :
-:                               :              :            : [12,  :         :
-:                               :              :            : 24,   :         :
-:                               :              :            : 36]   :         :
-:                               :              :            : for   :         :
-:                               :              :            : OS=8  :         :
+Checkpoint name             | Network backbone | Pretrained  dataset | ASPP  | Decoder
+--------------------------- | :--------------: | :-----------------: | :---: | :-----:
+xception_coco_voc_trainaug  | Xception_65  | MS-COCO <br> VOC 2012 train_aug set| [6,12,18] for OS=16 <br> [12,24,36] for OS=8 | OS = 4
+xception_coco_voc_trainval  | Xception_65  | MS-COCO <br> VOC 2012 train_aug + trainval sets | [6,12,18] for OS=16 <br> [12,24,36] for OS=8 | OS = 4
 
 In the table, **OS** denotes output stride.