Update app.py

app.py

@@ -1,39 +1,30 @@
 import gradio as gr
 from transformers import pipeline
 
-# Initialize the pipeline
 pipe = pipeline(
     "image-classification",
     model="ariG23498/vit_base_patch16_224.augreg2_in21k_ft_in1k.ft_food101"
 )
 
-# Function for classification
 def classify(image):
-    return pipe(image)[0]["label"]
+    results = pipe(image)
+    return {result["label"]: round(result["score"], 2) for result in results}
 
-# Gradio Interface with a detailed description
 demo = gr.Interface(
     fn=classify,
     inputs=gr.Image(type="pil", label="Upload an Image"),
-    outputs=gr.Textbox(label="Predicted Label"),
+    outputs=gr.Label(num_top_classes=3, label="Top Predictions"),
     examples=[["./sushi.png", "sushi"]],
     title="Food Classification with ViT 🥗🍣",
     description=(
-        "### Explore Food Classification with Vision Transformers (ViT) 🔍\n\n"
+        "# Explore Food Classification with Vision Transformers (ViT) 🔍\n\n"
         "This application demonstrates the power of Vision Transformers (ViT) for food classification tasks, "
         "leveraging the pre-trained model `vit_base_patch16_224.augreg2_in21k_ft_in1k.ft_food101` fine-tuned on the Food-101 dataset. "
         "With just a few lines of code, you can integrate state-of-the-art image classification models using the Hugging Face `pipeline` API.\n\n"
-        "#### How to Use:\n"
+        "## How to Use:\n"
         "1. Upload an image of food (e.g., sushi, pizza, or burgers).\n"
-        "2. The model will classify the image and provide the predicted label.\n"
+        "2. The model will classify the image and provide the predicted labels along with confidence scores.\n"
         "3. Try the provided example for a quick start or test your own food images!\n\n"
-        "#### About the Model:\n"
-        "- **Model Name**: `vit_base_patch16_224.augreg2_in21k_ft_in1k.ft_food101`\n"
-        "- **Dataset**: [Food-101](https://www.kaggle.com/dansbecker/food-101)\n"
-        "- **Architecture**: Vision Transformers (ViT), which process images by splitting them into patches and leveraging self-attention for feature extraction.\n\n"
-        "#### Learn More:\n"
-        "Discover more about Vision Transformers in the [Hugging Face blog](https://huggingface.co/blog). "
-        "Explore the Food-101 dataset [here](https://www.kaggle.com/dansbecker/food-101)."
     )
 )