Update app.py

app.py

@@ -1,15 +1,32 @@
 import gradio as gr
 from transformers import pipeline
+import numpy as np
 
-pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+# Initialize the pipeline
+classifier = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
 
 def predict(image):
-  predictions = pipeline(image)
-  return {p["label"]: p["score"] for p in predictions}
+    # Check if the input is a file path or numpy array
+    if isinstance(image, str):
+        # If it's a file path, pass it directly to the pipeline
+        predictions = classifier(image)
+    else:
+        # If it's a numpy array, we need to convert it to PIL Image
+        from PIL import Image
+        image = Image.fromarray(image.astype('uint8'), 'RGB')
+        predictions = classifier(image)
+    
+    # Convert predictions to the format expected by Gradio
+    return {p["label"]: float(p["score"]) for p in predictions}
 
-gr.Interface(
-    predict,
-    inputs=gr.inputs.Image(label="Upload hot dog candidate", type="filepath"),
-    outputs=gr.outputs.Label(num_top_classes=2),
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(label="Upload hot dog candidate"),
+    outputs=gr.Label(num_top_classes=2),
     title="Hot Dog? Or Not?",
-).launch()
+    description="Upload an image to see if it's a hot dog or not!",
+)
+
+if __name__ == "__main__":
+    iface.launch()