chore: Update app.py with improved Gradio interface for Hot Dog Classifier

app.py

@@ -1,31 +1,18 @@
 import gradio as gr
 from transformers import pipeline
 
-# Initialize the pipeline
-pipe = pipeline("visual-question-answering", model="openbmb/MiniCPM-Llama3-V-2_5", trust_remote_code=True)
+pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
 
-# Define the Gradio components
-image = gr.Image(type="pil", label="Image")
-question = gr.Textbox(value="Using the standard 9x9 sudoku format, solve the sudoku puzzle in the image correctly.", label="Question")
-answer = gr.Textbox(label="Answer", show_label=True, show_copy_button=True)
+def predict(input_img):
+    predictions = pipeline(input_img)
+    return input_img, {p["label"]: p["score"] for p in predictions} 
 
-title = "Sudoku Solver by FG"
-description = "Sudoku Solver using MiniCPM-Llama3-V-2_5"
-
-# Define the function for solving Sudoku
-def solve_sudoku(image, question):
-    result = pipe(image, question)
-    return result[0]['answer']
-
-# Create the Gradio interface
-demo = gr.Interface(
-    fn=solve_sudoku,
-    inputs=[image, question],
-    outputs=answer,
-    title=title,
-    description=description,
-    theme="compact",
+gradio_app = gr.Interface(
+    predict,
+    inputs=gr.Image(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"),
+    outputs=[gr.Image(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)],
+    title="Hot Dog? Or Not?",
 )
 
-# Launch the interface
-demo.launch(share=True)
+if __name__ == "__main__":
+    gradio_app.launch()