Add back example output images as lfs tracked files (#166)

* lfs track images now

* add back example images

* modify paths

* modify paths part 2

* correct paths in each model's readme

README.md

@@ -2,7 +2,7 @@
 
 This model estimates 21 hand keypoints per detected hand from [palm detector](../palm_detection_mediapipe). (The image below is referenced from [MediaPipe Hands Keypoints](https://github.com/tensorflow/tfjs-models/tree/master/hand-pose-detection#mediapipe-hands-keypoints-used-in-mediapipe-hands))
  
-![MediaPipe Hands Keypoints](./examples/hand_keypoints.png)
+![MediaPipe Hands Keypoints](./example_outputs/hand_keypoints.png)
 
 This model is converted from TFlite to ONNX using following tools:
 - TFLite model to ONNX: https://github.com/onnx/tensorflow-onnx
@@ -24,7 +24,7 @@ python demo.py -i /path/to/image -v
 
 ### Example outputs
 
-![webcam demo](./examples/mphandpose_demo.webp)
+![webcam demo](./example_outputs/mphandpose_demo.webp)
 
 ## License