update readme

minor fix so the bounding boxes returned can be drawn on the original image. Similar to the example in this page: https://huggingface.co/docs/transformers/en/model_doc/owlv2

README.md

@@ -64,7 +64,7 @@ def get_preprocessed_image(pixel_values):
 
 unnormalized_image = get_preprocessed_image(inputs.pixel_values)
 
-target_sizes = torch.Tensor([unnormalized_image.size[::-1]])
+target_sizes = torch.Tensor([image.size[::-1]]) # the bounding boxes can be drawn on the original image
 # Convert outputs (bounding boxes and class logits) to final bounding boxes and scores
 results = processor.post_process_object_detection(
     outputs=outputs, threshold=0.2, target_sizes=target_sizes