test bingcaht recomendation

app.py

@@ -1,18 +1,45 @@
 import gradio as gr
 from transformers import pipeline
 
-pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+model = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+def preprocess(image):
+    # Define your preprocessing function here to break the uploaded image into multiple images
+    # For example:
+    images = [image.crop((0, 0, 100, 100)), image.crop((100, 100, 200, 200))]
+    return images
 
 def predict(image):
-    predictions = pipeline(image)
-    return {p["label"]: p["score"] for p in predictions}
-
-gr.Interface(
-    predict,
-    inputs=gr.inputs.Image(label="Upload hot dog candidate", type="filepath"),
-    outputs=[gr.outputs.Image(type='pil', label='Image'), gr.outputs.Label(num_top_classes=2)], # gr.outputs.Label(num_top_classes=2),
-    title="Hot Dog? Or Not?",
-).launch()
+    # Apply preprocessing function to uploaded image
+    images = preprocess(image)
+    
+    # Apply model to all preprocessed images
+    predictions = []
+    for img in images:
+        pred = model(img)
+        predictions.append(pred[0])
+    
+    # Return predictions alongside images
+    return images, predictions
+
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.inputs.Image(type='pil'),
+    outputs=[gr.outputs.Image(type='pil', label='Image'), 'label']
+)
+
+# Launch Gradio app
+iface.launch()
+
+# def predict(image):
+#     predictions = model(image)
+#     return {p["label"]: p["score"] for p in predictions}
+
+# gr.Interface(
+#     predict,
+#     inputs=gr.inputs.Image(label="Upload hot dog candidate", type="filepath"),
+#     outputs=[gr.outputs.Image(type='pil', label='Image'), gr.outputs.Label(num_top_classes=2)], # gr.outputs.Label(num_top_classes=2),
+#     title="Hot Dog? Or Not?",
+# ).launch()
 
 # def greet(name):
 #     return "Hello " + name + "!!"