Update app.py

app.py

@@ -1,15 +1,16 @@
-import gradio as gr
-from transformers import pipeline
+from PIL import Image
+import requests
 
-pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+from transformers import CLIPProcessor, CLIPModel
 
-def predict(image):
-  predictions = pipeline(image)
-  return {p["label"]: p["score"] for p in predictions}
+model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
 
-gr.Interface(
-    predict,
-    inputs=gr.inputs.Image(label="Upload hot dog candidate", type="filepath"),
-    outputs=gr.outputs.Label(num_top_classes=2),
-    title="Hot Dog? Or Not?",
-).launch()
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+
+inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="pt", padding=True)
+
+outputs = model(**inputs)
+logits_per_image = outputs.logits_per_image # this is the image-text similarity score
+probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities