Update app.py

app.py

@@ -2,7 +2,6 @@ import gradio as gr
 import numpy as np
 from PIL import Image
 from transformers import AutoImageProcessor, AutoModelForImageClassification
-import requests
 
 model_names = [
     "0-ma/swin-geometric-shapes-tiny",
@@ -47,23 +46,27 @@ def predict(image, selected_model):
     return confidences
 
 title = "Geometric Shape Classifier"
-description = "Select a model to classify geometric shapes."
+description = "Select a model and upload an image to classify geometric shapes."
 
-# Create examples with both image and default model
-examples = [[img, model_names[0]] for img in example_images]
+with gr.Blocks() as demo:
+    gr.Markdown(f"# {title}")
+    gr.Markdown(description)
+    
+    with gr.Row():
+        model_dropdown = gr.Dropdown(choices=model_names, label="Select Model", value=model_names[0])
+        image_input = gr.Image(type="pil")
+    
+    submit_button = gr.Button("Classify")
+    output = gr.Label()
 
-# Create the Gradio interface
-iface = gr.Interface(
-    fn=predict,
-    inputs=[
-        gr.Image(type="pil"),
-        gr.Dropdown(choices=model_names, label="Select Model", value=model_names[0])
-    ],
-    outputs=gr.Label(),
-    title=title,
-    description=description,
-    examples=examples
-)
+    submit_button.click(fn=predict, inputs=[image_input, model_dropdown], outputs=output)
 
-# Launch the interface
-iface.launch()
+    gr.Examples(
+        examples=[[img, model_names[0]] for img in example_images],
+        inputs=[image_input, model_dropdown],
+        outputs=output,
+        fn=predict,
+        cache_examples=True,
+    )
+
+demo.launch()