fixed incorrect path in GETTING_STARTED.md

Summary:
- updated path from "MODEL_ZOO.md" to "DENSEPOSE_IUV.md#ModelZoo" and "DENSEPOSE_CSE.md#ModelZoo".
- Because the file "MODEL_ZOO.md" does not exist in that path now.

Pull Request resolved: #3138

Reviewed By: wat3rBro

Differential Revision: D32609413

Pulled By: zhanghang1989

fbshipit-source-id: 8b651c1def95110ee13a030345fe0333f9612e72

Author: woo1

projects/DensePose/doc/GETTING_STARTED.md

@@ -2,7 +2,7 @@
 
 ## Inference with Pre-trained Models
 
-1. Pick a model and its config file from [Model Zoo](MODEL_ZOO.md), for example [densepose_rcnn_R_50_FPN_s1x.yaml](../configs/densepose_rcnn_R_50_FPN_s1x.yaml)
+1. Pick a model and its config file from [Model Zoo(IUV)](DENSEPOSE_IUV.md#ModelZoo), [Model Zoo(CSE)](DENSEPOSE_CSE.md#ModelZoo), for example [densepose_rcnn_R_50_FPN_s1x.yaml](../configs/densepose_rcnn_R_50_FPN_s1x.yaml)
 2. Run the [Apply Net](TOOL_APPLY_NET.md) tool to visualize the results or save the to disk. For example, to use contour visualization for DensePose, one can run:
 ```bash
 python apply_net.py show configs/densepose_rcnn_R_50_FPN_s1x.yaml densepose_rcnn_R_50_FPN_s1x.pkl image.jpg dp_contour,bbox --output image_densepose_contour.png
@@ -22,7 +22,7 @@ datasets/coco/
 </pre>
 
 To train a model one can use the [train_net.py](../train_net.py) script.
-This script was used to train all DensePose models in [Model Zoo](MODEL_ZOO.md).
+This script was used to train all DensePose models in [Model Zoo(IUV)](DENSEPOSE_IUV.md#ModelZoo), [Model Zoo(CSE)](DENSEPOSE_CSE.md#ModelZoo).
 For example, to launch end-to-end DensePose-RCNN training with ResNet-50 FPN backbone
 on 8 GPUs following the s1x schedule, one can run
 ```bash