Merge pull request #4841 from pkulzc/master

Update model zoo quantized model links.

research/object_detection/g3doc/detection_model_zoo.md

@@ -73,8 +73,8 @@ Some remarks on frozen inference graphs:
 | ------------ | :--------------: | :--------------: | :-------------: |
 | [ssd_mobilenet_v1_coco](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_coco_2018_01_28.tar.gz) | 30 | 21 | Boxes |
 | [ssd_mobilenet_v1_0.75_depth_coco ☆](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_0.75_depth_300x300_coco14_sync_2018_07_03.tar.gz) | 26 | 18 | Boxes |
-| [ssd_mobilenet_v1_quantized_coco ☆](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_quantized_300x300_coco14_sync_2018_07_03.tar.gz) | 29 | 18 | Boxes |
-| [ssd_mobilenet_v1_0.75_depth_quantized_coco ☆](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_0.75_depth_quantized_300x300_coco14_sync_2018_07_03.tar.gz) | 29 | 16 | Boxes |
+| [ssd_mobilenet_v1_quantized_coco ☆](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_quantized_300x300_coco14_sync_2018_07_18.tar.gz) | 29 | 18 | Boxes |
+| [ssd_mobilenet_v1_0.75_depth_quantized_coco ☆](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_0.75_depth_quantized_300x300_coco14_sync_2018_07_18.tar.gz) | 29 | 16 | Boxes |
 | [ssd_mobilenet_v1_ppn_coco ☆](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_ppn_shared_box_predictor_300x300_coco14_sync_2018_07_03.tar.gz) | 26 | 20 | Boxes |
 | [ssd_mobilenet_v1_fpn_coco ☆](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync_2018_07_03.tar.gz) | 56 | 32 | Boxes |
 | [ssd_resnet_50_fpn_coco ☆](http://download.tensorflow.org/models/object_detection/ssd_resnet50_v1_fpn_shared_box_predictor_640x640_coco14_sync_2018_07_03.tar.gz) | 76 | 35 | Boxes |
@@ -98,6 +98,8 @@ Some remarks on frozen inference graphs:
 
 Note: The asterisk (☆) at the end of model name indicates that this model supports TPU training.
 
+Note: If you download the tar.gz file of quantized models and un-tar, you will get different set of files - a checkpoint, a config file and tflite frozen graphs (txt/binary).
+
 ## Kitti-trained models
 
 Model name                                                                                                                                                        | Speed (ms) | Pascal mAP@0.5 | Outputs