updated the How to use section so that the code actually does what the live demo does

added some code to convert the raw outputs (which are not very useful/interpretable) to run it through the image processor and generate a message with text showing confidence and human-readable labels.

the output of this code snippet is now:

```
Detected remote with confidence 0.994 at location [46.96, 72.61, 181.02, 119.73]
Detected remote with confidence 0.975 at location [340.66, 79.19, 372.59, 192.65]
Detected cat with confidence 0.984 at location [12.27, 54.25, 319.42, 470.99]
Detected remote with confidence 0.922 at location [41.66, 71.96, 178.7, 120.33]
Detected cat with confidence 0.914 at location [342.34, 21.48, 638.64, 372.46]
```

which i think is useful and tells you if the model is working

README.md

@@ -35,7 +35,7 @@ You can use the raw model for object detection. See the [model hub](https://hugg
 Here is how to use this model:
 
 ```python
-from transformers import YolosFeatureExtractor, YolosForObjectDetection
+from transformers import YolosFeatureExtractor, YolosForObjectDetection, AutoImageProcessor
 from PIL import Image
 import requests
 
@@ -44,6 +44,7 @@ image = Image.open(requests.get(url, stream=True).raw)
 
 feature_extractor = YolosFeatureExtractor.from_pretrained('hustvl/yolos-tiny')
 model = YolosForObjectDetection.from_pretrained('hustvl/yolos-tiny')
+image_processor = AutoImageProcessor.from_pretrained("hustvl/yolos-tiny")
 
 inputs = feature_extractor(images=image, return_tensors="pt")
 outputs = model(**inputs)
@@ -51,6 +52,17 @@ outputs = model(**inputs)
 # model predicts bounding boxes and corresponding COCO classes
 logits = outputs.logits
 bboxes = outputs.pred_boxes
+
+
+# print results
+target_sizes = torch.tensor([image.size[::-1]])
+results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[0]
+for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+    box = [round(i, 2) for i in box.tolist()]
+    print(
+        f"Detected {model.config.id2label[label.item()]} with confidence "
+        f"{round(score.item(), 3)} at location {box}"
+    )
 ```
 
 Currently, both the feature extractor and model support PyTorch.