Added another example

app.py

@@ -6,9 +6,7 @@ processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
 
 
 def inference(input_img, captions):
-    captions_list = captions.split(",")
-    #url = "http://images.cocodataset.org/val2017/000000039769.jpg"
-    #image = Image.open(requests.get(url, stream=True).raw)
+    captions_list = captions.split(",")   
     inputs = processor(text=captions_list, images=input_img, return_tensors="pt", padding=True)
     outputs = model(**inputs)
     logits_per_image = outputs.logits_per_image  # this is the image-text similarity score
@@ -19,7 +17,8 @@ def inference(input_img, captions):
 title = "TSAI S18 Assignment: Use a pretrained CLIP model and give a demo on its workig"
 description = "A simple Gradio interface that accepts an image and some captions, and gives a score as to how much the caption describes the image "
  
-examples = [["cats.jpg","a photo of a cat, a photo of a dog"]
+examples = [["cats.jpg","a photo of a cat, a photo of a dog"],
+            ["personBicycle.jpg","person riding bicycle, person driving car, photo of a dog"]
            ]
 
 demo = gr.Interface(