public domain image examples for SSD outputs

examples/ssd/README.md

@@ -13,14 +13,14 @@ The inference service would return the response in the format - '[(object_class,
 
 ## Step 1 - Download the pre-trained SSD Model
 
+You will need the model files to use for the export. Check this example's directory in case they're already downloaded. Otherwise, you can `curl` the files or download them via your browser:
+
 ```bash
- wget https://s3.amazonaws.com/model-server/models/resnet50_ssd/resnet50_ssd_model-symbol.json
- wget https://s3.amazonaws.com/model-server/models/resnet50_ssd/resnet50_ssd_model-0000.params
+ curl -O https://s3.amazonaws.com/model-server/models/resnet50_ssd/resnet50_ssd_model-symbol.json
+ curl -O https://s3.amazonaws.com/model-server/models/resnet50_ssd/resnet50_ssd_model-0000.params
 ```
 
-or
-
-Use these links to download the Symbol and Params files:
+Alternatively, use these links to download the Symbol and Params files via your browser:
 1. <a href="https://s3.amazonaws.com/model-server/models/resnet50_ssd/resnet50_ssd_model-symbol.json" download>resnet50_ssd_model-symbol.json</a>
 2. <a href="https://s3.amazonaws.com/model-server/models/resnet50_ssd/resnet50_ssd_model-0000.params" download>resnet50_ssd_model-0000.params</a>
 
@@ -137,88 +137,45 @@ Awesome! we have successfully exported a pre-trained MXNet model, extended MMS w
 
 ## Step 7 - Test sample inference
 
-Let us try the inference server we just started. Open another terminal on the same host. Download a sample image.
+Let us try the inference server we just started. Open another terminal on the same host. Download a sample image, or try any jpeg image that contains the one or more of the object classes mentioned earlier: 'aeroplane', 'bicycle', 'bird', 'boat', etc...
 
-```bash
-wget https://www.dphotographer.co.uk/users/21963/thm1024/1337890426_Img_8133.jpg
-```
+You can also use this image of three dogs on a beach.
+![3 dogs on beach](3dogs.jpg)
 
 Use curl to make a prediction call by passing the downloaded image as input to the prediction request.
 
 ```bash
- curl -X POST http://127.0.0.1:8080/SSD/predict -F "data=@1337890426_Img_8133.jpg"
+curl -X POST http://127.0.0.1:8080/ssd/predict -F "data=@3dogs.jpg"
 ```
 
 You can expect the response similar to below. The output format is `[(object_class, xmin, ymin, xmax, ymax)]`.
 Where, xmin, ymin, xmax and ymax are the bounding box coordinates of the detected object.
 
 ```
 {
-"prediction": [
-  [
-    "person",
-    494,
-    153,
-    702,
-    630
-  ],
-  [
-    "person",
-    108,
-    108,
-    351,
-    591
-  ],
-  [
-    "dog",
-    306,
-    446,
-    468,
-    530
-  ],
-  [
-    "car",
-    9,
-    166,
-    96,
-    245
-  ],
-  [
-    "person",
-    826,
-    127,
-    1008,
-    601
-  ],
-  [
-    "person",
-    480,
-    177,
-    511,
-    253
-  ],
-  [
-    "person",
-    555,
-    175,
-    581,
-    242
-  ],
-  [
-    "person",
-    514,
-    177,
-    547,
-    250
-  ],
-  [
-    "person",
-    62,
-    334,
-    185,
-    467
+  "prediction": [
+    [
+      "dog",
+      399,
+      128,
+      570,
+      290
+    ],
+    [
+      "dog",
+      278,
+      196,
+      417,
+      286
+    ],
+    [
+      "cow",
+      205,
+      116,
+      297,
+      272
+    ]
   ]
-]
 }
 ```
 
@@ -228,11 +185,11 @@ For better visualization on the input and how we can use the inference output, s
 
 Input Image
 
-![Street Input Image](https://s3.amazonaws.com/model-server/models/resnet50_ssd/street.jpg)
+![Street Input Image](dogs-before.jpg)
 
 Output Image
 
-![Street Output Image](https://s3.amazonaws.com/model-server/models/resnet50_ssd/street_output.jpg)
+![Street Output Image](dogs-after.jpg)
 
 
 # References

examples/ssd/example_outputs.md

@@ -0,0 +1,139 @@
+# SSD Example Outputs
+
+### Dog Beach
+
+![dog beach](https://farm9.staticflickr.com/8184/8081332083_3a5c242b8b_z_d.jpg)
+```bash
+curl -o dogbeach.jpg https://farm9.staticflickr.com/8184/8081332083_3a5c242b8b_z_d.jpg
+curl -X POST http://127.0.0.1:8080/ssd/predict -F "data=@dogbeach.jpg"
+{
+  "prediction": [
+    [
+      "person",
+      203,
+      213,
+      248,
+      347
+    ],
+    [
+      "dog",
+      334,
+      175,
+      403,
+      235
+    ],
+    [
+      "person",
+      109,
+      211,
+      144,
+      291
+    ],
+    [
+      "person",
+      529,
+      31,
+      562,
+      103
+    ],
+    [
+      "person",
+      155,
+      12,
+      189,
+      98
+    ],
+    [
+      "horse",
+      465,
+      3,
+      527,
+      40
+    ],
+    [
+      "person",
+      51,
+      372,
+      96,
+      427
+    ],
+    [
+      "dog",
+      80,
+      56,
+      131,
+      96
+    ],
+    [
+      "person",
+      70,
+      89,
+      96,
+      155
+    ],
+    [
+      "cow",
+      292,
+      188,
+      344,
+      231
+    ],
+    [
+      "dog",
+      294,
+      186,
+      349,
+      231
+    ]
+  ]
+}
+```
+
+### 3 Dogs on Beach
+![3 dogs on beach](https://farm9.staticflickr.com/8051/8081326814_64756479c6_z_d.jpg)
+```bash
+curl -o 3dogs.jpg https://farm9.staticflickr.com/8051/8081326814_64756479c6_z_d.jpg
+curl -X POST http://127.0.0.1:8080/ssd/predict -F "data=@3dogs.jpg"
+{
+  "prediction": [
+    [
+      "dog",
+      399,
+      128,
+      570,
+      290
+    ],
+    [
+      "dog",
+      278,
+      196,
+      417,
+      286
+    ],
+    [
+      "cow",
+      205,
+      116,
+      297,
+      272
+    ]
+  ]
+}
+```
+### Sailboat
+![sailboat](https://farm9.staticflickr.com/8316/7990362092_84a688a089_z_d.jpg)
+```bash
+curl -o sailboat.jpg https://farm9.staticflickr.com/8316/7990362092_84a688a089_z_d.jpg
+curl -X POST http://127.0.0.1:8080/ssd/predict -F "data=@sailboat.jpg"
+{
+  "prediction": [
+    [
+      "boat",
+      160,
+      87,
+      249,
+      318
+    ]
+  ]
+}
+```