Update app.py

app.py

@@ -11,7 +11,7 @@ model = CLIPModel.from_pretrained("openai/clip-vit-base-patch16")
 # Function to make predictions from the image
 def predict_image_description(image):
     # Preprocess the image and generate text inputs
-    inputs = processor(text=["a photo of a cat", "a photo of a dog", "a photo of a car", "a photo of a tree", "a photo of a house"], 
+    inputs = processor(text=["a photo of an animal", "a photo of a human", "a photo of a car", "a photo of a tree", "a photo of a house"], 
                        images=image, 
                        return_tensors="pt", 
                        padding=True)
@@ -23,7 +23,7 @@ def predict_image_description(image):
 
     # Return top 3 predictions
     top_3_probabilities, top_3_indices = torch.topk(probs, 3)
-    labels = ["a cat", "a dog", "a car", "a tree", "a house"]
+    labels = ["an animal", "a human", "a car", "a tree", "a house"]
     
     predictions = []
     for i in range(3):